duplicated block id: 1
size: 256 cleaned lines of code
in 2 files:
 - src/app/app.py (246:523)
 - src/predict_many_samples.py (262:539)

duplicated block id: 2
size: 251 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (256:529)
 - src/predict_one_sample.py (259:532)

duplicated block id: 3
size: 246 cleaned lines of code
in 2 files:
 - src/app/app.py (246:513)
 - src/predict_one_sample.py (265:532)

duplicated block id: 4
size: 172 cleaned lines of code
in 2 files:
 - src/app/app.py (42:243)
 - src/predict_many_samples.py (52:253)

duplicated block id: 5
size: 136 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (95:254)
 - src/predict_one_sample.py (97:256)

duplicated block id: 6
size: 135 cleaned lines of code
in 2 files:
 - src/app/app.py (85:243)
 - src/predict_one_sample.py (97:255)

duplicated block id: 7
size: 99 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (650:765)
 - src/deep_baselines/run.py (608:723)

duplicated block id: 8
size: 88 cleaned lines of code
in 2 files:
 - src/predict.py (35:156)
 - src/predict_many_samples.py (35:155)

duplicated block id: 9
size: 87 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (541:647)
 - src/deep_baselines/run.py (498:604)

duplicated block id: 10
size: 85 cleaned lines of code
in 2 files:
 - src/app/app.py (42:145)
 - src/predict.py (51:156)

duplicated block id: 11
size: 82 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (673:761)
 - src/predict_one_sample.py (657:745)

duplicated block id: 12
size: 74 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (266:351)
 - src/deep_baselines/cheer.py (409:494)

duplicated block id: 13
size: 70 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (99:179)
 - src/deep_baselines/cheer.py (415:494)

duplicated block id: 14
size: 70 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (99:179)
 - src/deep_baselines/cheer.py (272:351)

duplicated block id: 15
size: 70 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (824:908)
 - src/deep_baselines/run.py (783:867)

duplicated block id: 16
size: 69 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (39:129)
 - src/plot/plot_map_pie_fig_aff4_2.py (38:126)

duplicated block id: 17
size: 68 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (107:185)
 - src/deep_baselines/virtifier.py (117:195)

duplicated block id: 18
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (272:346)
 - src/deep_baselines/virseeker.py (109:183)

duplicated block id: 19
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (99:173)
 - src/deep_baselines/virtifier.py (119:193)

duplicated block id: 20
size: 66 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (336:411)
 - src/deep_baselines/virtifier.py (119:193)

duplicated block id: 21
size: 66 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (336:411)
 - src/deep_baselines/cheer.py (99:173)

duplicated block id: 22
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (415:489)
 - src/deep_baselines/virhunter.py (93:167)

duplicated block id: 23
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (99:173)
 - src/deep_baselines/virseeker.py (109:183)

duplicated block id: 24
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (93:167)
 - src/deep_baselines/virtifier.py (119:193)

duplicated block id: 25
size: 66 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (336:411)
 - src/deep_baselines/cheer.py (272:346)

duplicated block id: 26
size: 66 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (336:411)
 - src/deep_baselines/cheer.py (415:489)

duplicated block id: 27
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (415:489)
 - src/deep_baselines/virtifier.py (119:193)

duplicated block id: 28
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (272:346)
 - src/deep_baselines/virtifier.py (119:193)

duplicated block id: 29
size: 66 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (336:411)
 - src/deep_baselines/virseeker.py (109:183)

duplicated block id: 30
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (415:489)
 - src/deep_baselines/virseeker.py (109:183)

duplicated block id: 31
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (93:167)
 - src/deep_baselines/virseeker.py (109:183)

duplicated block id: 32
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (99:173)
 - src/deep_baselines/virhunter.py (93:167)

duplicated block id: 33
size: 66 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (336:411)
 - src/deep_baselines/virhunter.py (93:167)

duplicated block id: 34
size: 66 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (272:346)
 - src/deep_baselines/virhunter.py (93:167)

duplicated block id: 35
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/deep_baselines/virseeker.py (112:183)

duplicated block id: 36
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/deep_baselines/cheer.py (418:489)

duplicated block id: 37
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/deep_baselines/cheer.py (275:346)

duplicated block id: 38
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/deep_baselines/virhunter.py (96:167)

duplicated block id: 39
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/deep_baselines/virtifier.py (122:193)

duplicated block id: 40
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/deep_baselines/cheer.py (102:173)

duplicated block id: 41
size: 63 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (249:321)
 - src/baselines/dnn.py (339:411)

duplicated block id: 42
size: 61 cleaned lines of code
in 2 files:
 - src/predict.py (187:257)
 - src/predict_one_sample.py (185:255)

duplicated block id: 43
size: 61 cleaned lines of code
in 2 files:
 - src/predict.py (646:716)
 - src/predict_many_samples.py (698:765)

duplicated block id: 44
size: 61 cleaned lines of code
in 2 files:
 - src/predict.py (187:257)
 - src/predict_many_samples.py (183:253)

duplicated block id: 45
size: 61 cleaned lines of code
in 2 files:
 - src/app/app.py (173:243)
 - src/predict.py (187:257)

duplicated block id: 46
size: 59 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (113:174)
 - src/baselines/xgb.py (112:172)

duplicated block id: 47
size: 59 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (155:213)
 - src/baselines/xgb.py (110:168)

duplicated block id: 48
size: 59 cleaned lines of code
in 2 files:
 - src/predict.py (646:712)
 - src/predict_one_sample.py (682:745)

duplicated block id: 49
size: 57 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (157:213)
 - src/baselines/lgbm.py (113:170)

duplicated block id: 50
size: 51 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (911:970)
 - src/deep_baselines/run.py (871:930)

duplicated block id: 51
size: 48 cleaned lines of code
in 2 files:
 - src/predict.py (94:156)
 - src/predict_one_sample.py (97:157)

duplicated block id: 52
size: 47 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (143:192)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (119:167)

duplicated block id: 53
size: 47 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (117:164)
 - src/data_preprocess/subword.py (65:113)

duplicated block id: 54
size: 46 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (572:619)
 - src/predict_one_sample.py (570:617)

duplicated block id: 55
size: 45 cleaned lines of code
in 2 files:
 - src/predict.py (542:586)
 - src/predict_one_sample.py (590:634)

duplicated block id: 56
size: 43 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (24:91)
 - src/predict_one_sample.py (24:90)

duplicated block id: 57
size: 43 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (767:821)
 - src/deep_baselines/run.py (725:779)

duplicated block id: 58
size: 41 cleaned lines of code
in 2 files:
 - src/evaluater.py (118:158)
 - src/predictor.py (124:164)

duplicated block id: 59
size: 39 cleaned lines of code
in 2 files:
 - src/predict.py (35:90)
 - src/predict_one_sample.py (34:90)

duplicated block id: 60
size: 38 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (70:123)
 - src/deep_baselines/run.py (77:130)

duplicated block id: 61
size: 37 cleaned lines of code
in 2 files:
 - src/app/app.py (347:384)
 - src/predict.py (348:384)

duplicated block id: 62
size: 37 cleaned lines of code
in 2 files:
 - src/predict.py (348:384)
 - src/predict_many_samples.py (363:400)

duplicated block id: 63
size: 37 cleaned lines of code
in 2 files:
 - src/evaluater.py (121:157)
 - src/trainer.py (206:242)

duplicated block id: 64
size: 37 cleaned lines of code
in 2 files:
 - src/predictor.py (127:163)
 - src/trainer.py (206:242)

duplicated block id: 65
size: 37 cleaned lines of code
in 2 files:
 - src/predict.py (348:384)
 - src/predict_one_sample.py (366:403)

duplicated block id: 66
size: 36 cleaned lines of code
in 2 files:
 - src/app/app.py (42:81)
 - src/predict_one_sample.py (51:90)

duplicated block id: 67
size: 36 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (394:434)
 - src/predict.py (745:785)

duplicated block id: 68
size: 32 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (548:583)
 - src/predict.py (912:948)

duplicated block id: 69
size: 32 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (199:234)
 - src/deep_baselines/virtifier.py (221:256)

duplicated block id: 70
size: 31 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (189:223)
 - src/deep_baselines/virtifier.py (222:256)

duplicated block id: 71
size: 31 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (189:223)
 - src/deep_baselines/virseeker.py (200:234)

duplicated block id: 72
size: 30 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (482:519)
 - src/deep_baselines/run.py (439:476)

duplicated block id: 73
size: 29 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (586:620)
 - src/predict.py (955:989)

duplicated block id: 74
size: 29 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (376:409)
 - src/baselines/xgb.py (342:374)

duplicated block id: 75
size: 28 cleaned lines of code
in 2 files:
 - src/data_loader.py (557:592)
 - src/data_loader.py (1000:1035)

duplicated block id: 76
size: 28 cleaned lines of code
in 2 files:
 - src/predict.py (542:569)
 - src/predict_many_samples.py (590:619)

duplicated block id: 77
size: 27 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (652:686)
 - src/trainer.py (249:283)

duplicated block id: 78
size: 27 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:46)
 - src/deep_baselines/virtifier.py (3:46)

duplicated block id: 79
size: 27 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (610:644)
 - src/trainer.py (249:283)

duplicated block id: 80
size: 26 cleaned lines of code
in 2 files:
 - src/predict.py (265:293)
 - src/predict_one_sample.py (274:302)

duplicated block id: 81
size: 26 cleaned lines of code
in 2 files:
 - src/data_loader.py (323:348)
 - src/deep_baselines/run.py (244:269)

duplicated block id: 82
size: 26 cleaned lines of code
in 2 files:
 - src/predict.py (265:293)
 - src/predict_many_samples.py (271:299)

duplicated block id: 83
size: 26 cleaned lines of code
in 2 files:
 - src/app/app.py (255:283)
 - src/predict.py (265:293)

duplicated block id: 84
size: 24 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (30:60)
 - src/geo_map/get_biosample_from_update.py (31:61)

duplicated block id: 85
size: 23 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (707:733)
 - src/trainer.py (325:350)

duplicated block id: 86
size: 23 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (411:438)
 - src/baselines/xgb.py (376:403)

duplicated block id: 87
size: 23 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (456:484)
 - src/predict.py (807:835)

duplicated block id: 88
size: 23 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (665:691)
 - src/trainer.py (325:350)

duplicated block id: 89
size: 23 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (665:692)
 - src/baselines/xgb.py (627:654)

duplicated block id: 90
size: 22 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (125:150)
 - src/deep_baselines/run.py (160:185)

duplicated block id: 91
size: 22 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (173:197)
 - src/data_preprocess/tf_records_generator.py (101:126)

duplicated block id: 92
size: 22 cleaned lines of code
in 2 files:
 - src/common/metrics.py (426:450)
 - src/utils.py (271:295)

duplicated block id: 93
size: 22 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (621:642)
 - src/predict_one_sample.py (619:640)

duplicated block id: 94
size: 21 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (840:866)
 - src/predictor.py (100:126)

duplicated block id: 95
size: 21 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (750:778)
 - src/evaluater.py (92:120)

duplicated block id: 96
size: 21 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (354:378)
 - src/deep_baselines/cheer.py (496:520)

duplicated block id: 97
size: 21 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (881:907)
 - src/predictor.py (100:126)

duplicated block id: 98
size: 21 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (792:820)
 - src/evaluater.py (92:120)

duplicated block id: 99
size: 20 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (477:496)
 - src/predict_one_sample.py (509:528)

duplicated block id: 100
size: 20 cleaned lines of code
in 2 files:
 - src/app/app.py (490:509)
 - src/predict_many_samples.py (474:493)

duplicated block id: 101
size: 20 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (506:525)
 - src/predict_one_sample.py (477:496)

duplicated block id: 102
size: 20 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (474:493)
 - src/predict_one_sample.py (509:528)

duplicated block id: 103
size: 20 cleaned lines of code
in 2 files:
 - src/app/app.py (490:509)
 - src/predict_one_sample.py (477:496)

duplicated block id: 104
size: 20 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (474:493)
 - src/predict_many_samples.py (506:525)

duplicated block id: 105
size: 20 cleaned lines of code
in 2 files:
 - src/app/app.py (458:477)
 - src/app/app.py (490:509)

duplicated block id: 106
size: 20 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (238:258)
 - src/deep_baselines/cheer.py (384:404)

duplicated block id: 107
size: 20 cleaned lines of code
in 2 files:
 - src/app/app.py (458:477)
 - src/predict_many_samples.py (506:525)

duplicated block id: 108
size: 20 cleaned lines of code
in 2 files:
 - src/app/app.py (458:477)
 - src/predict_one_sample.py (509:528)

duplicated block id: 109
size: 20 cleaned lines of code
in 2 files:
 - src/data_loader.py (1404:1423)
 - src/data_loader.py (1429:1448)

duplicated block id: 110
size: 19 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (486:506)
 - src/predict.py (837:857)

duplicated block id: 111
size: 19 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:24)
 - src/geo_map/get_biosample_from_update.py (3:24)

duplicated block id: 112
size: 19 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:24)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:24)

duplicated block id: 113
size: 18 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (636:655)
 - src/baselines/xgb.py (597:616)

duplicated block id: 114
size: 18 cleaned lines of code
in 2 files:
 - src/data_loader.py (370:388)
 - src/data_loader.py (442:460)

duplicated block id: 115
size: 18 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (514:531)
 - src/predict.py (867:884)

duplicated block id: 116
size: 18 cleaned lines of code
in 2 files:
 - src/app/app.py (311:328)
 - src/predict.py (308:325)

duplicated block id: 117
size: 18 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (149:167)
 - src/data_preprocess/tf_records_generator.py (101:120)

duplicated block id: 118
size: 18 cleaned lines of code
in 2 files:
 - src/predict.py (308:325)
 - src/predict_many_samples.py (327:344)

duplicated block id: 119
size: 18 cleaned lines of code
in 2 files:
 - src/predict.py (308:325)
 - src/predict_one_sample.py (330:347)

duplicated block id: 120
size: 17 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (213:232)
 - src/deep_baselines/virhunter.py (188:206)

duplicated block id: 121
size: 17 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (359:378)
 - src/deep_baselines/virhunter.py (188:206)

duplicated block id: 122
size: 17 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (68:89)
 - src/baselines/lgbm.py (61:82)

duplicated block id: 123
size: 17 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (144:160)
 - src/deep_baselines/run.py (320:336)

duplicated block id: 124
size: 17 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (213:232)
 - src/deep_baselines/cheer.py (359:378)

duplicated block id: 125
size: 17 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (213:232)
 - src/deep_baselines/cheer.py (501:520)

duplicated block id: 126
size: 17 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (501:520)
 - src/deep_baselines/virhunter.py (188:206)

duplicated block id: 127
size: 17 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (189:205)
 - src/deep_baselines/run.py (320:336)

duplicated block id: 128
size: 17 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (24:66)
 - src/deep_baselines/run.py (24:71)

duplicated block id: 129
size: 17 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (146:162)
 - src/deep_baselines/run.py (320:336)

duplicated block id: 130
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (418:435)
 - src/deep_baselines/cheer.py (361:378)

duplicated block id: 131
size: 16 cleaned lines of code
in 2 files:
 - src/data_loader.py (661:677)
 - src/data_loader.py (1098:1113)

duplicated block id: 132
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (361:378)
 - src/deep_baselines/virseeker.py (200:217)

duplicated block id: 133
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (418:435)
 - src/deep_baselines/cheer.py (215:232)

duplicated block id: 134
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (497:517)
 - src/run.py (774:792)

duplicated block id: 135
size: 16 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:21)
 - src/common/multi_label_metrics.py (3:21)

duplicated block id: 136
size: 16 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:21)
 - src/plot/plot_map_pie_fig4_2.py (3:21)

duplicated block id: 137
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (215:232)
 - src/deep_baselines/virtifier.py (222:239)

duplicated block id: 138
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (418:435)
 - src/deep_baselines/cheer.py (503:520)

duplicated block id: 139
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (418:435)
 - src/deep_baselines/virseeker.py (200:217)

duplicated block id: 140
size: 16 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:21)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:21)

duplicated block id: 141
size: 16 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:21)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:21)

duplicated block id: 142
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (503:520)
 - src/deep_baselines/virtifier.py (222:239)

duplicated block id: 143
size: 16 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:21)
 - src/common/metrics.py (3:21)

duplicated block id: 144
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (539:555)
 - src/baselines/xgb.py (503:519)

duplicated block id: 145
size: 16 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:21)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:21)

duplicated block id: 146
size: 16 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:21)
 - src/protein_structure/structure_from_esm_v1.py (3:21)

duplicated block id: 147
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:21)
 - src/baselines/xgb.py (3:21)

duplicated block id: 148
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (481:496)
 - src/baselines/xgb.py (441:456)

duplicated block id: 149
size: 16 cleaned lines of code
in 2 files:
 - src/data_loader.py (679:694)
 - src/data_loader.py (1115:1130)

duplicated block id: 150
size: 16 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (647:664)
 - src/predict_one_sample.py (639:656)

duplicated block id: 151
size: 16 cleaned lines of code
in 2 files:
 - src/common/metrics.py (177:192)
 - src/common/metrics.py (241:256)

duplicated block id: 152
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (521:539)
 - src/deep_baselines/run.py (478:496)

duplicated block id: 153
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (418:435)
 - src/deep_baselines/virtifier.py (222:239)

duplicated block id: 154
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (361:378)
 - src/deep_baselines/virtifier.py (222:239)

duplicated block id: 155
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (418:435)
 - src/deep_baselines/virhunter.py (189:206)

duplicated block id: 156
size: 16 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:21)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:21)

duplicated block id: 157
size: 16 cleaned lines of code
in 2 files:
 - src/predict.py (571:586)
 - src/predict_many_samples.py (621:636)

duplicated block id: 158
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (454:474)
 - src/run.py (774:792)

duplicated block id: 159
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (215:232)
 - src/deep_baselines/virseeker.py (200:217)

duplicated block id: 160
size: 16 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (503:520)
 - src/deep_baselines/virseeker.py (200:217)

duplicated block id: 161
size: 16 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (62:82)
 - src/deep_baselines/run.py (77:96)

duplicated block id: 162
size: 16 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:21)
 - src/common/multi_label_metrics.py (3:21)

duplicated block id: 163
size: 15 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (74:88)
 - src/plot/plot_map_pie_fig4_2.py (104:118)

duplicated block id: 164
size: 15 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (137:152)
 - src/plot/plot_map_pie_fig_aff4_2.py (134:149)

duplicated block id: 165
size: 15 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (211:231)
 - src/plot/plot_map_pie_fig_aff4_2.py (210:229)

duplicated block id: 166
size: 15 cleaned lines of code
in 2 files:
 - src/data_loader.py (614:628)
 - src/data_loader.py (1052:1066)

duplicated block id: 167
size: 15 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (115:135)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (93:113)

duplicated block id: 168
size: 15 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (74:88)
 - src/plot/plot_map_pie_fig_aff4_2.py (102:116)

duplicated block id: 169
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 170
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 171
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 172
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/SSFN/modeling_bert.py (3:19)

duplicated block id: 173
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 174
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 175
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 176
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 177
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 178
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 179
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 180
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 181
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 182
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/run.py (3:19)

duplicated block id: 183
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 184
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 185
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 186
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 187
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 188
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 189
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 190
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 191
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (32:65)
 - src/predict_many_samples.py (35:64)

duplicated block id: 192
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/run.py (3:19)

duplicated block id: 193
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 194
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 195
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 196
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/run.py (3:19)

duplicated block id: 197
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 198
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 199
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 200
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 201
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 202
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 203
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 204
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 205
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 206
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 207
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 208
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 209
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 210
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 211
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 212
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 213
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 214
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 215
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 216
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 217
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 218
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 219
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 220
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 221
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 222
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 223
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 224
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 225
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 226
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 227
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 228
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 229
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 230
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 231
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/run.py (3:19)

duplicated block id: 232
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 233
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 234
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 235
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 236
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 237
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 238
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 239
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 240
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 241
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 242
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 243
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 244
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 245
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 246
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 247
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 248
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 249
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 250
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 251
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 252
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 253
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 254
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 255
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 256
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 257
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 258
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 259
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 260
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 261
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 262
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 263
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 264
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 265
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 266
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 267
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 268
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 269
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 270
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/run.py (3:19)

duplicated block id: 271
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 272
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 273
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 274
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 275
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 276
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 277
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 278
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 279
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 280
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 281
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 282
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 283
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/baselines/dnn.py (3:19)

duplicated block id: 284
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 285
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 286
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:19)
 - src/deep_baselines/virseeker.py (3:19)

duplicated block id: 287
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 288
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 289
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 290
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 291
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 292
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:462)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:507)

duplicated block id: 293
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 294
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 295
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 296
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 297
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 298
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 299
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 300
size: 14 cleaned lines of code
in 2 files:
 - src/result_process/process_predict_result.py (3:19)
 - src/run.py (3:19)

duplicated block id: 301
size: 14 cleaned lines of code
in 2 files:
 - src/result_process/process_predict_result.py (49:64)
 - src/utils.py (190:205)

duplicated block id: 302
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 303
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 304
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/run.py (3:19)

duplicated block id: 305
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 306
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 307
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 308
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 309
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/SSFN/layers.py (3:19)

duplicated block id: 310
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 311
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 312
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 313
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 314
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 315
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 316
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 317
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 318
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 319
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 320
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 321
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 322
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 323
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 324
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 325
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 326
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 327
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 328
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 329
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 330
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/run.py (3:19)

duplicated block id: 331
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 332
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 333
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 334
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 335
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 336
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 337
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:19)
 - src/deep_baselines/virtifier.py (3:19)

duplicated block id: 338
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 339
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/run.py (3:19)

duplicated block id: 340
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 341
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 342
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 343
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 344
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 345
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 346
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 347
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:19)
 - src/deep_baselines/virtifier.py (3:19)

duplicated block id: 348
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 349
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 350
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 351
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 352
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 353
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 354
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 355
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 356
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 357
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 358
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 359
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:19)
 - src/deep_baselines/virseeker.py (3:19)

duplicated block id: 360
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 361
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 362
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 363
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 364
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 365
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 366
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/run.py (3:19)

duplicated block id: 367
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 368
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 369
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 370
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 371
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 372
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 373
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 374
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 375
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 376
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 377
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 378
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 379
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 380
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 381
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 382
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 383
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 384
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/run.py (3:19)

duplicated block id: 385
size: 14 cleaned lines of code
in 2 files:
 - src/run.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 386
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 387
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 388
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 389
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 390
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:19)
 - src/deep_baselines/virseeker.py (3:19)

duplicated block id: 391
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 392
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 393
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 394
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 395
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 396
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 397
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 398
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 399
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 400
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 401
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 402
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 403
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 404
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 405
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 406
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 407
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 408
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 409
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 410
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 411
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 412
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 413
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 414
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 415
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 416
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 417
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 418
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 419
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 420
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 421
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 422
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 423
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 424
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 425
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 426
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 427
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 428
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 429
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 430
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 431
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 432
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 433
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 434
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 435
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 436
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 437
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 438
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 439
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 440
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 441
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 442
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 443
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 444
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 445
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 446
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 447
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 448
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 449
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 450
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 451
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 452
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 453
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 454
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 455
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 456
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 457
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 458
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 459
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 460
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:19)
 - src/deep_baselines/virtifier.py (3:19)

duplicated block id: 461
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 462
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 463
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 464
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 465
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 466
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 467
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 468
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 469
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 470
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 471
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 472
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 473
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 474
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/baselines/dnn.py (3:19)

duplicated block id: 475
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 476
size: 14 cleaned lines of code
in 2 files:
 - src/run.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 477
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 478
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 479
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 480
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 481
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 482
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 483
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 484
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/run.py (3:19)

duplicated block id: 485
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 486
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 487
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 488
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 489
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 490
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 491
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 492
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 493
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 494
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 495
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 496
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/baselines/lgbm.py (3:19)

duplicated block id: 497
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 498
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 499
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 500
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 501
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 502
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 503
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 504
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 505
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 506
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 507
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 508
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 509
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 510
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 511
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 512
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 513
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 514
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 515
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 516
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 517
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 518
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 519
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 520
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 521
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 522
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 523
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 524
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 525
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 526
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 527
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 528
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 529
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 530
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 531
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 532
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 533
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 534
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 535
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 536
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 537
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 538
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 539
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 540
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 541
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 542
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 543
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 544
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 545
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 546
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 547
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 548
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 549
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 550
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 551
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 552
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (53:66)
 - src/protein_structure/structure_from_esm_v1.py (352:365)

duplicated block id: 553
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 554
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 555
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 556
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 557
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 558
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 559
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 560
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 561
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 562
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 563
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 564
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 565
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 566
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 567
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/SSFN/model.py (3:19)

duplicated block id: 568
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 569
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 570
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/run.py (3:19)

duplicated block id: 571
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 572
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 573
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 574
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 575
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 576
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 577
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 578
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 579
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 580
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 581
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 582
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 583
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 584
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 585
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 586
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 587
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 588
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 589
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 590
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 591
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 592
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (488:502)
 - src/deep_baselines/predict_deep_baselines.py (516:529)

duplicated block id: 593
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 594
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 595
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 596
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 597
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 598
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 599
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 600
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 601
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 602
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/baselines/lgbm.py (3:19)

duplicated block id: 603
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 604
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 605
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 606
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 607
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 608
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 609
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 610
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 611
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 612
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 613
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 614
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 615
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:19)
 - src/deep_baselines/virseeker.py (3:19)

duplicated block id: 616
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 617
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/baselines/lgbm.py (3:19)

duplicated block id: 618
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 619
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 620
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 621
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 622
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 623
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 624
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1771:1789)
 - src/SSFN/modeling_bert.py (1857:1881)

duplicated block id: 625
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 626
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 627
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 628
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 629
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 630
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 631
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 632
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (839:853)
 - src/predict.py (869:882)

duplicated block id: 633
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 634
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 635
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (32:65)
 - src/predict_one_sample.py (34:63)

duplicated block id: 636
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 637
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 638
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/baselines/dnn.py (3:19)

duplicated block id: 639
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 640
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 641
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 642
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 643
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 644
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 645
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 646
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (125:138)
 - src/predict_one_sample.py (136:150)

duplicated block id: 647
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 648
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 649
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 650
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 651
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 652
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 653
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 654
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 655
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 656
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 657
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 658
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 659
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 660
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 661
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 662
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 663
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 664
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 665
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 666
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 667
size: 14 cleaned lines of code
in 2 files:
 - src/app/app.py (124:138)
 - src/deep_baselines/predict_deep_baselines.py (125:138)

duplicated block id: 668
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 669
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 670
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 671
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 672
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 673
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 674
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 675
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 676
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 677
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 678
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 679
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 680
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 681
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:19)
 - src/deep_baselines/virhunter.py (3:19)

duplicated block id: 682
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 683
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:19)
 - src/deep_baselines/virhunter.py (3:19)

duplicated block id: 684
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 685
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 686
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 687
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 688
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 689
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 690
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 691
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 692
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 693
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 694
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 695
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 696
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 697
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 698
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 699
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 700
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 701
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 702
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 703
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (488:502)
 - src/predict.py (869:882)

duplicated block id: 704
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 705
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 706
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 707
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 708
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 709
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 710
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 711
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 712
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 713
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/run.py (3:19)

duplicated block id: 714
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 715
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 716
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 717
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 718
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 719
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 720
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/SSFN/modeling_bert.py (3:19)

duplicated block id: 721
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 722
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 723
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 724
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 725
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (98:111)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (61:74)

duplicated block id: 726
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:19)
 - src/deep_baselines/statistics.py (3:19)

duplicated block id: 727
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 728
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 729
size: 14 cleaned lines of code
in 2 files:
 - src/trainer.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 730
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 731
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 732
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 733
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 734
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 735
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 736
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 737
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 738
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 739
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 740
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 741
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 742
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 743
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 744
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 745
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (37:52)
 - src/plot/plot_map_pie_fig_aff4_2.py (210:225)

duplicated block id: 746
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 747
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 748
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 749
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 750
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 751
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 752
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 753
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 754
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 755
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 756
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 757
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:19)
 - src/deep_baselines/virhunter.py (3:19)

duplicated block id: 758
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 759
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 760
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 761
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 762
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 763
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 764
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 765
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 766
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 767
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 768
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 769
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 770
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/predict.py (3:19)

duplicated block id: 771
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 772
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 773
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 774
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 775
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 776
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 777
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 778
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 779
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 780
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 781
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 782
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/SSFN/pooling.py (3:19)

duplicated block id: 783
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 784
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 785
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 786
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 787
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/predictor.py (3:19)

duplicated block id: 788
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 789
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 790
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 791
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/SSFN/pooling.py (3:19)

duplicated block id: 792
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 793
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 794
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 795
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 796
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 797
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 798
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 799
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 800
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 801
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 802
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/run.py (3:19)

duplicated block id: 803
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 804
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 805
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/run.py (3:19)

duplicated block id: 806
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 807
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 808
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 809
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 810
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 811
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 812
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 813
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 814
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 815
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 816
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 817
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 818
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 819
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 820
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 821
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 822
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 823
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 824
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 825
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 826
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 827
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 828
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 829
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 830
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 831
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 832
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 833
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 834
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 835
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 836
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 837
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 838
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 839
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 840
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 841
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 842
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 843
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/run.py (3:19)

duplicated block id: 844
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 845
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 846
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/predict_one_sample.py (3:19)

duplicated block id: 847
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 848
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 849
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 850
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 851
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 852
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 853
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 854
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 855
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 856
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 857
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 858
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 859
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 860
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 861
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/run.py (3:19)

duplicated block id: 862
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 863
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 864
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 865
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 866
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 867
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/run.py (3:19)

duplicated block id: 868
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/run.py (3:19)

duplicated block id: 869
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 870
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 871
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 872
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 873
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/baselines/dnn.py (3:19)

duplicated block id: 874
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 875
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 876
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 877
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 878
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 879
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 880
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 881
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 882
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 883
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 884
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 885
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 886
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 887
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 888
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 889
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 890
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 891
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 892
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/utils.py (3:19)

duplicated block id: 893
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 894
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 895
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 896
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 897
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 898
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 899
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 900
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (634:648)
 - src/data_loader.py (1073:1086)

duplicated block id: 901
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 902
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 903
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 904
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 905
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 906
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 907
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 908
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 909
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 910
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 911
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 912
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 913
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 914
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 915
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 916
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 917
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 918
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 919
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 920
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 921
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (117:135)
 - src/data_preprocess/tf_records_generator.py (60:78)

duplicated block id: 922
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 923
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 924
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 925
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 926
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 927
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 928
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 929
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 930
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 931
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 932
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/run.py (3:19)

duplicated block id: 933
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 934
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 935
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 936
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 937
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 938
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 939
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 940
size: 14 cleaned lines of code
in 2 files:
 - src/result_process/process_predict_result.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 941
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 942
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 943
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 944
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1578:1593)
 - src/SSFN/modeling_bert.py (1689:1704)

duplicated block id: 945
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 946
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 947
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 948
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 949
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 950
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 951
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 952
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/run.py (3:19)

duplicated block id: 953
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 954
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 955
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 956
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 957
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 958
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 959
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 960
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/run.py (3:19)

duplicated block id: 961
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 962
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 963
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 964
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 965
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 966
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 967
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 968
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 969
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 970
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 971
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 972
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 973
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 974
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 975
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 976
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 977
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 978
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 979
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 980
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 981
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 982
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 983
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 984
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 985
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 986
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 987
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/run.py (3:19)

duplicated block id: 988
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 989
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 990
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 991
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 992
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 993
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 994
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 995
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 996
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 997
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 998
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 999
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1000
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1001
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1002
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1003
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1004
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1005
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1006
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1007
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1008
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1009
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 1010
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1011
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1012
size: 14 cleaned lines of code
in 2 files:
 - src/result_process/process_predict_result.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1013
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1014
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1015
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1016
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1017
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1018
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1019
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 1020
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1021
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1022
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1023
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1024
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1025
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1026
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/evaluater.py (3:19)

duplicated block id: 1027
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1028
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/SSFN/model.py (3:19)

duplicated block id: 1029
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1030
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1031
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1032
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1033
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1034
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1035
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1036
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 1037
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1038
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1039
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 1040
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1041
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1042
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1043
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1044
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1045
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1046
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1047
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1048
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 1049
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1050
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 1051
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (574:587)
 - src/baselines/xgb.py (542:555)

duplicated block id: 1052
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1053
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1054
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1055
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1056
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1057
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1058
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 1059
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1060
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/baselines/predict.py (3:19)

duplicated block id: 1061
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1062
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1063
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1064
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 1065
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 1066
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1067
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1068
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 1069
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1070
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1071
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1072
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1073
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1074
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1075
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1076
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1077
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1078
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1079
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1080
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1081
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 1082
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1083
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1084
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1085
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1086
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1087
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1088
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1089
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 1090
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1091
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1092
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/SSFN/pooling.py (3:19)

duplicated block id: 1093
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1094
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1095
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1096
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1097
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1098
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (334:353)
 - src/baselines/xgb.py (311:330)

duplicated block id: 1099
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1100
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1101
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1102
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1103
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1104
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1105
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1106
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (177:192)
 - src/plot/plot_map_pie_fig4_2.py (211:226)

duplicated block id: 1107
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1108
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1109
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1110
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 1111
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1112
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1113
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1114
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1115
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1116
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1117
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1118
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1119
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1120
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1121
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1122
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1123
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1124
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1125
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1126
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/baselines/xgb.py (3:19)

duplicated block id: 1127
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1128
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1129
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1130
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1131
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1132
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/baselines/lgbm.py (3:19)

duplicated block id: 1133
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1134
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:19)
 - src/deep_baselines/virtifier.py (3:19)

duplicated block id: 1135
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/run.py (3:19)

duplicated block id: 1136
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1137
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1138
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (516:529)
 - src/predict.py (839:853)

duplicated block id: 1139
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1140
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1141
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1142
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1143
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1144
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1145
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1146
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 1147
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 1148
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 1149
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1150
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1151
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/baselines/lgbm.py (3:19)

duplicated block id: 1152
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1153
size: 14 cleaned lines of code
in 2 files:
 - src/predictor.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1154
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1155
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1156
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1157
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1158
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1159
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1160
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1161
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 1162
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1163
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1164
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1165
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1166
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1167
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1168
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (125:138)
 - src/predict_many_samples.py (134:148)

duplicated block id: 1169
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1170
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1171
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1172
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1173
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1174
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 1175
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1176
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1177
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1178
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1179
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1180
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:19)
 - src/deep_baselines/statistics.py (3:19)

duplicated block id: 1181
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1182
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1183
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1184
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1185
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1186
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 1187
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1188
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 1189
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1190
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1191
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1192
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1193
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1194
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1195
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1196
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1197
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1198
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1199
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1200
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1201
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 1202
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1203
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 1204
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1205
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1206
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1207
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1208
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1209
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1210
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 1211
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1212
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1213
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1214
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1215
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1216
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1217
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 1218
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1219
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1220
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1221
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1222
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1223
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1224
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1225
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1226
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1227
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1228
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1229
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 1230
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1231
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1232
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1233
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1234
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1235
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1236
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1237
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1238
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1239
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1240
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1241
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1242
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1243
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1244
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1245
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1246
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1247
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1248
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1249
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1250
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1251
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:19)
 - src/deep_baselines/run.py (3:19)

duplicated block id: 1252
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1253
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1254
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1255
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1256
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1257
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1258
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1259
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1260
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (37:52)
 - src/plot/plot_map_pie_fig4_2.py (211:226)

duplicated block id: 1261
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1262
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1263
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1264
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1265
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1266
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1267
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1268
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1269
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1270
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1271
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1272
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (125:138)
 - src/predict.py (135:149)

duplicated block id: 1273
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1274
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1275
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1276
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1277
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1278
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1279
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1280
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1281
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1282
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1283
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/SSFN/pooling.py (3:19)

duplicated block id: 1284
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1285
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1286
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 1287
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/SSFN/modeling_bert.py (3:19)

duplicated block id: 1288
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1289
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1290
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1291
size: 14 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1292
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1293
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1294
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1295
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 1296
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1297
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1298
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1299
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1300
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1301
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1302
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1303
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1304
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1305
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1306
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1307
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1308
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1309
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (32:65)
 - src/predict.py (35:63)

duplicated block id: 1310
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1311
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1312
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1313
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1314
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)

duplicated block id: 1315
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (177:192)
 - src/plot/plot_map_pie_fig_aff4_2.py (210:225)

duplicated block id: 1316
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1317
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1318
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1319
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1320
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1321
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1322
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1323
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1324
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1325
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1326
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1327
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1328
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1329
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 1330
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1331
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1332
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 1333
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 1334
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1335
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1336
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1337
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)

duplicated block id: 1338
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1339
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1340
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (332:345)
 - src/protein_structure/embedding_from_esmfold.py (351:364)

duplicated block id: 1341
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1342
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 1343
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1344
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1345
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1346
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1347
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1348
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1349
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 1350
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1351
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1352
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1353
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/common/loss.py (3:19)

duplicated block id: 1354
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1355
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1356
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 1357
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_loader.py (3:19)

duplicated block id: 1358
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (95:113)
 - src/data_preprocess/tf_records_generator.py (60:78)

duplicated block id: 1359
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1360
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1361
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1362
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1363
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/biotoolbox/structure_file_reader.py (3:19)

duplicated block id: 1364
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1365
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1366
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1367
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1368
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1369
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1370
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1371
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1372
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1373
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1374
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/data_preprocess/tf_records_generator.py (3:19)

duplicated block id: 1375
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1376
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1377
size: 14 cleaned lines of code
in 2 files:
 - src/predict.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1378
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1379
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1380
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/deep_baselines/predict_deep_baselines.py (1:17)

duplicated block id: 1381
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1382
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1383
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1384
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1385
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/baselines/dnn.py (3:19)

duplicated block id: 1386
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1387
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1388
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1389
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1390
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1391
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1392
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1393
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1394
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1395
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1396
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1397
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 1398
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/protein_structure/embedding_from_esmfold.py (3:19)

duplicated block id: 1399
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1400
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1401
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1402
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)

duplicated block id: 1403
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1404
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1405
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1406
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/geo_map/get_biosample_from_update.py (3:19)

duplicated block id: 1407
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1408
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1409
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1410
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/extract_attr_from_biosample_page.py (3:19)
 - src/geo_map/standardization_lat_lon_info.py (3:19)

duplicated block id: 1411
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1412
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1413
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1414
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1415
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1416
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1417
size: 14 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1418
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/data_preprocess/verify_train_dataset.py (3:19)

duplicated block id: 1419
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1420
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1421
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/common/metrics.py (3:19)

duplicated block id: 1422
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1423
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/trainer.py (3:19)

duplicated block id: 1424
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1425
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1426
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1427
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:19)

duplicated block id: 1428
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1429
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1430
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/biotoolbox/contact_map_generator.py (3:19)

duplicated block id: 1431
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 1432
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)

duplicated block id: 1433
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1434
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1435
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:19)
 - src/data_preprocess/subword.py (3:19)

duplicated block id: 1436
size: 14 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1437
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1438
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1439
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (37:52)
 - src/plot/plot_map_pie_fig4_1.py (177:192)

duplicated block id: 1440
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/baselines/lgbm.py (3:19)

duplicated block id: 1441
size: 14 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1442
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1443
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:19)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)

duplicated block id: 1444
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)
 - src/protein_structure/structure_from_esm_v1.py (3:19)

duplicated block id: 1445
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/predict.py (3:19)

duplicated block id: 1446
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1447
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1448
size: 14 cleaned lines of code
in 2 files:
 - src/evaluater.py (3:19)
 - src/result_process/process_predict_result.py (3:19)

duplicated block id: 1449
size: 14 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:19)

duplicated block id: 1450
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1451
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (3:19)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:19)

duplicated block id: 1452
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1453
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/protein_structure/predict_structure.py (3:19)

duplicated block id: 1454
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1455
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/run.py (3:19)

duplicated block id: 1456
size: 14 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:17)
 - src/geo_map/get_biosample_from_entrez.py (3:19)

duplicated block id: 1457
size: 14 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:19)
 - src/plot/plot_map_pie_fig4_1.py (3:19)

duplicated block id: 1458
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:19)
 - src/biotoolbox/contact_map_builder.py (3:19)

duplicated block id: 1459
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1460
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:19)
 - src/geo_map/get_biosample_from_manual.py (3:19)

duplicated block id: 1461
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:19)

duplicated block id: 1462
size: 14 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (3:19)
 - src/utils.py (3:19)

duplicated block id: 1463
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (3:19)
 - src/trainer.py (3:19)

duplicated block id: 1464
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/plot/plot_map_pie_fig4_2.py (3:19)

duplicated block id: 1465
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:19)
 - src/evaluater.py (3:19)

duplicated block id: 1466
size: 14 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (3:19)
 - src/protein_structure/merge_embedding_pdb_result.py (3:19)

duplicated block id: 1467
size: 14 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:19)
 - src/predict_one_sample.py (3:19)

duplicated block id: 1468
size: 14 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:19)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:19)

duplicated block id: 1469
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_update.py (3:19)
 - src/predict_many_samples.py (3:19)

duplicated block id: 1470
size: 14 cleaned lines of code
in 2 files:
 - src/geo_map/download_biosample_page.py (3:19)
 - src/predictor.py (3:19)

duplicated block id: 1471
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:19)

duplicated block id: 1472
size: 14 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:19)
 - src/geo_map/download_biosample_page.py (3:19)

duplicated block id: 1473
size: 14 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:19)
 - src/common/multi_label_metrics.py (3:19)

duplicated block id: 1474
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/deep_baselines/cheer.py (361:374)

duplicated block id: 1475
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/deep_baselines/cheer.py (503:516)

duplicated block id: 1476
size: 13 cleaned lines of code
in 2 files:
 - src/common/metrics.py (363:375)
 - src/common/metrics.py (411:423)

duplicated block id: 1477
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (196:208)
 - src/baselines/xgb.py (190:202)

duplicated block id: 1478
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (525:539)
 - src/baselines/xgb.py (406:420)

duplicated block id: 1479
size: 13 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (157:169)
 - src/data_preprocess/tf_records_generator.py (101:113)

duplicated block id: 1480
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1107:1151)
 - src/SSFN/modeling_bert.py (1857:1879)

duplicated block id: 1481
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1107:1151)
 - src/SSFN/modeling_bert.py (1771:1787)

duplicated block id: 1482
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (743:755)
 - src/trainer.py (366:378)

duplicated block id: 1483
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1107:1151)
 - src/SSFN/modeling_bert.py (1570:1588)

duplicated block id: 1484
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (126:138)
 - src/deep_baselines/run.py (305:317)

duplicated block id: 1485
size: 13 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (647:659)
 - src/trainer.py (296:308)

duplicated block id: 1486
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/deep_baselines/cheer.py (215:228)

duplicated block id: 1487
size: 13 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (157:169)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (173:185)

duplicated block id: 1488
size: 13 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (173:185)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (133:145)

duplicated block id: 1489
size: 13 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (311:325)
 - src/plot/plot_map_pie_fig_aff4_2.py (327:341)

duplicated block id: 1490
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1656:1668)
 - src/SSFN/modeling_bert.py (1757:1769)

duplicated block id: 1491
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (253:265)
 - src/baselines/xgb.py (241:253)

duplicated block id: 1492
size: 13 cleaned lines of code
in 2 files:
 - src/predict.py (327:339)
 - src/predict_one_sample.py (348:360)

duplicated block id: 1493
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (128:140)
 - src/deep_baselines/run.py (305:317)

duplicated block id: 1494
size: 13 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (536:552)
 - src/predict_one_sample.py (534:550)

duplicated block id: 1495
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (441:455)
 - src/baselines/xgb.py (406:420)

duplicated block id: 1496
size: 13 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (337:350)
 - src/plot/plot_map_pie_fig_aff4_2.py (354:368)

duplicated block id: 1497
size: 13 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (133:145)
 - src/data_preprocess/tf_records_generator.py (101:113)

duplicated block id: 1498
size: 13 cleaned lines of code
in 2 files:
 - src/run.py (788:801)
 - src/run.py (811:823)

duplicated block id: 1499
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/deep_baselines/virhunter.py (189:202)

duplicated block id: 1500
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (177:189)
 - src/baselines/xgb.py (173:185)

duplicated block id: 1501
size: 13 cleaned lines of code
in 2 files:
 - src/predict.py (327:339)
 - src/predict_many_samples.py (345:357)

duplicated block id: 1502
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (171:183)
 - src/deep_baselines/run.py (305:317)

duplicated block id: 1503
size: 13 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (701:713)
 - src/trainer.py (366:378)

duplicated block id: 1504
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1556:1568)
 - src/SSFN/modeling_bert.py (1656:1668)

duplicated block id: 1505
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (272:284)
 - src/baselines/xgb.py (258:270)

duplicated block id: 1506
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1556:1568)
 - src/SSFN/modeling_bert.py (1757:1769)

duplicated block id: 1507
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/baselines/dnn.py (418:431)

duplicated block id: 1508
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/deep_baselines/virseeker.py (200:213)

duplicated block id: 1509
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (234:246)
 - src/baselines/xgb.py (224:236)

duplicated block id: 1510
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (215:227)
 - src/baselines/xgb.py (207:219)

duplicated block id: 1511
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (689:701)
 - src/trainer.py (296:308)

duplicated block id: 1512
size: 13 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (213:228)
 - src/plot/plot_map_pie_fig4_2.py (247:262)

duplicated block id: 1513
size: 13 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (133:145)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (149:161)

duplicated block id: 1514
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (406:420)
 - src/deep_baselines/run.py (482:496)

duplicated block id: 1515
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1570:1588)
 - src/SSFN/modeling_bert.py (1857:1879)

duplicated block id: 1516
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1570:1588)
 - src/SSFN/modeling_bert.py (1771:1787)

duplicated block id: 1517
size: 13 cleaned lines of code
in 2 files:
 - src/geo_map/parse_loc_lat_lon_from_attr.py (40:52)
 - src/geo_map/standardization_lat_lon_info.py (36:48)

duplicated block id: 1518
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (441:455)
 - src/deep_baselines/run.py (482:496)

duplicated block id: 1519
size: 13 cleaned lines of code
in 2 files:
 - src/app/app.py (329:341)
 - src/predict.py (327:339)

duplicated block id: 1520
size: 13 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (525:539)
 - src/baselines/lgbm.py (441:455)

duplicated block id: 1521
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1490:1504)
 - src/SSFN/modeling_bert.py (1576:1590)

duplicated block id: 1522
size: 13 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (157:169)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (149:161)

duplicated block id: 1523
size: 13 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (423:436)
 - src/deep_baselines/virtifier.py (222:235)

duplicated block id: 1524
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/standardization_lat_lon_info.py (3:17)

duplicated block id: 1525
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1526
size: 12 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1527
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1528
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1529
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1530
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1531
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:17)

duplicated block id: 1532
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1533
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/predict.py (3:17)

duplicated block id: 1534
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1535
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:17)

duplicated block id: 1536
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/evaluater.py (3:17)

duplicated block id: 1537
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/predictor.py (3:17)

duplicated block id: 1538
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/utils.py (3:17)

duplicated block id: 1539
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:17)

duplicated block id: 1540
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1541
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1542
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:15)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1543
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:17)

duplicated block id: 1544
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1545
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:17)

duplicated block id: 1546
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (173:184)
 - src/baselines/xgb.py (190:201)

duplicated block id: 1547
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1548
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1439:1450)
 - src/SSFN/modeling_bert.py (1758:1769)

duplicated block id: 1549
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (177:188)
 - src/baselines/lgbm.py (196:207)

duplicated block id: 1550
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1551
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/trainer.py (3:17)

duplicated block id: 1552
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1553
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (196:207)
 - src/baselines/xgb.py (173:184)

duplicated block id: 1554
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1555
size: 12 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1556
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/plot/plot_map_pie_fig4_2.py (3:17)

duplicated block id: 1557
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1558
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:17)

duplicated block id: 1559
size: 12 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1560
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/plot/plot_map_pie_fig4_2.py (3:17)

duplicated block id: 1561
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/plot/plot_map_pie_fig4_2.py (3:17)

duplicated block id: 1562
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/plot/plot_map_pie_fig4_2.py (3:17)

duplicated block id: 1563
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/get_biosample_from_entrez.py (3:17)

duplicated block id: 1564
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/plot/plot_map_pie_fig4_1.py (3:17)

duplicated block id: 1565
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/predictor.py (3:17)

duplicated block id: 1566
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1567
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1568
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:17)

duplicated block id: 1569
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1570
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/deep_baselines/predict_deep_baselines.py (1:15)

duplicated block id: 1571
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1572
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/predictor.py (3:17)

duplicated block id: 1573
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1574
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1575
size: 12 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1576
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/protein_structure/embedding_from_esmfold.py (3:17)

duplicated block id: 1577
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1578
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1579
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/predictor.py (3:17)

duplicated block id: 1580
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1581
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/utils.py (3:17)

duplicated block id: 1582
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1583
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/protein_structure/predict_structure.py (3:17)

duplicated block id: 1584
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:15)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1585
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1586
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1587
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/standardization_lat_lon_info.py (3:17)

duplicated block id: 1588
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/predict.py (3:17)

duplicated block id: 1589
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/protein_structure/embedding_from_esmfold.py (3:17)

duplicated block id: 1590
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (368:380)
 - src/predict.py (725:737)

duplicated block id: 1591
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1592
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1593
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1594
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:17)

duplicated block id: 1595
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/result_process/process_predict_result.py (3:17)

duplicated block id: 1596
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1597
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/trainer.py (3:17)

duplicated block id: 1598
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/run.py (3:17)

duplicated block id: 1599
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1600
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:17)

duplicated block id: 1601
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/result_process/process_predict_result.py (3:17)

duplicated block id: 1602
size: 12 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1603
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/protein_structure/predict_structure.py (3:17)

duplicated block id: 1604
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/get_biosample_from_entrez.py (3:17)

duplicated block id: 1605
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1606
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/get_biosample_from_manual.py (3:17)

duplicated block id: 1607
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1608
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/plot/plot_map_pie_fig4_1.py (3:17)

duplicated block id: 1609
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1610
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1611
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:17)

duplicated block id: 1612
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1613
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/predict.py (3:17)

duplicated block id: 1614
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (438:452)
 - src/baselines/lgbm.py (337:351)

duplicated block id: 1615
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1616
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1617
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/result_process/process_predict_result.py (3:17)

duplicated block id: 1618
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1619
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1620
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:17)

duplicated block id: 1621
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1622
size: 12 cleaned lines of code
in 2 files:
 - src/predictor.py (208:219)
 - src/predictor.py (224:235)

duplicated block id: 1623
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/get_biosample_from_entrez.py (3:17)

duplicated block id: 1624
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/get_biosample_from_update.py (3:17)

duplicated block id: 1625
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1626
size: 12 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1627
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1628
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1629
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1630
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/protein_structure/structure_from_esm_v1.py (3:17)

duplicated block id: 1631
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1632
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/run.py (3:17)

duplicated block id: 1633
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1634
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1635
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/predict_many_samples.py (3:17)

duplicated block id: 1636
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/result_process/process_predict_result.py (3:17)

duplicated block id: 1637
size: 12 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1638
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1639
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1640
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/predict_one_sample.py (3:17)

duplicated block id: 1641
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/result_process/process_predict_result.py (3:17)

duplicated block id: 1642
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/predict_many_samples.py (3:17)

duplicated block id: 1643
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/download_biosample_page.py (3:17)

duplicated block id: 1644
size: 12 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1645
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1439:1450)
 - src/SSFN/modeling_bert.py (1557:1568)

duplicated block id: 1646
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:17)

duplicated block id: 1647
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:17)

duplicated block id: 1648
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1649
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/get_biosample_from_manual.py (3:17)

duplicated block id: 1650
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/download_biosample_page.py (3:17)

duplicated block id: 1651
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1652
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/predict.py (3:17)

duplicated block id: 1653
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/protein_structure/embedding_from_esmfold.py (3:17)

duplicated block id: 1654
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1655
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1439:1450)
 - src/SSFN/modeling_bert.py (1657:1668)

duplicated block id: 1656
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:17)

duplicated block id: 1657
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1658
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/standardization_lat_lon_info.py (3:17)

duplicated block id: 1659
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1660
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:17)

duplicated block id: 1661
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1492:1504)
 - src/SSFN/modeling_bert.py (1689:1701)

duplicated block id: 1662
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1663
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1664
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/predict_one_sample.py (3:17)

duplicated block id: 1665
size: 12 cleaned lines of code
in 2 files:
 - src/predict.py (417:430)
 - src/predict_many_samples.py (434:447)

duplicated block id: 1666
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1667
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/get_biosample_from_manual.py (3:17)

duplicated block id: 1668
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1669
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1670
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/protein_structure/structure_from_esm_v1.py (3:17)

duplicated block id: 1671
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/download_biosample_page.py (3:17)

duplicated block id: 1672
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/get_biosample_from_manual.py (3:17)

duplicated block id: 1673
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1674
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1675
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/utils.py (3:17)

duplicated block id: 1676
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/predict_one_sample.py (3:17)

duplicated block id: 1677
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1678
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/download_biosample_page.py (3:17)

duplicated block id: 1679
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:17)

duplicated block id: 1680
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1681
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (177:188)
 - src/baselines/xgb.py (190:201)

duplicated block id: 1682
size: 12 cleaned lines of code
in 2 files:
 - src/predict.py (417:430)
 - src/predict_one_sample.py (437:450)

duplicated block id: 1683
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1684
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/get_biosample_from_update.py (3:17)

duplicated block id: 1685
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:17)

duplicated block id: 1686
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/predict_one_sample.py (3:17)

duplicated block id: 1687
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1688
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:17)

duplicated block id: 1689
size: 12 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1690
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1691
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1692
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:17)

duplicated block id: 1693
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1694
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/get_biosample_from_manual.py (3:17)

duplicated block id: 1695
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1139:1151)
 - src/SSFN/modeling_bert.py (1490:1502)

duplicated block id: 1696
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1697
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/extract_attr_from_biosample_page.py (3:17)

duplicated block id: 1698
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1699
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/trainer.py (3:17)

duplicated block id: 1700
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1701
size: 12 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1702
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/get_biosample_from_manual.py (3:17)

duplicated block id: 1703
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/plot/plot_map_pie_fig4_1.py (3:17)

duplicated block id: 1704
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1208:1219)
 - src/SSFN/modeling_bert.py (1348:1359)

duplicated block id: 1705
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/evaluater.py (3:17)

duplicated block id: 1706
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (468:479)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (513:524)

duplicated block id: 1707
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/predictor.py (3:17)

duplicated block id: 1708
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/run.py (3:17)

duplicated block id: 1709
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1710
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/get_biosample_from_entrez.py (3:17)

duplicated block id: 1711
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/utils.py (3:17)

duplicated block id: 1712
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/predict_many_samples.py (3:17)

duplicated block id: 1713
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1714
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/predict.py (3:17)

duplicated block id: 1715
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1716
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1717
size: 12 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1718
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:17)

duplicated block id: 1719
size: 12 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1720
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/protein_structure/embedding_from_esmfold.py (3:17)

duplicated block id: 1721
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/standardization_lat_lon_info.py (3:17)

duplicated block id: 1722
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1723
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/predict.py (3:17)

duplicated block id: 1724
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/trainer.py (3:17)

duplicated block id: 1725
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:17)

duplicated block id: 1726
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1727
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:17)

duplicated block id: 1728
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1729
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1730
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1731
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1732
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/plot/plot_map_pie_fig4_1.py (3:17)

duplicated block id: 1733
size: 12 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1734
size: 12 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1735
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/get_biosample_from_update.py (3:17)

duplicated block id: 1736
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/get_biosample_from_entrez.py (3:17)

duplicated block id: 1737
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1738
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/plot/plot_map_pie_fig4_1.py (3:17)

duplicated block id: 1739
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1740
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:15)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1741
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1742
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1743
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1744
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/evaluater.py (3:17)

duplicated block id: 1745
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1746
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:17)

duplicated block id: 1747
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1748
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/predict_many_samples.py (3:17)

duplicated block id: 1749
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/evaluater.py (3:17)

duplicated block id: 1750
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/protein_structure/predict_structure.py (3:17)

duplicated block id: 1751
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:17)

duplicated block id: 1752
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1753
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/plot/plot_map_pie_fig4_1.py (3:17)

duplicated block id: 1754
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1755
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1756
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1757
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1758
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/run.py (3:17)

duplicated block id: 1759
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1760
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1761
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1762
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/utils.py (3:17)

duplicated block id: 1763
size: 12 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1764
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/protein_structure/predict_structure.py (3:17)

duplicated block id: 1765
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/trainer.py (3:17)

duplicated block id: 1766
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/get_biosample_from_entrez.py (3:17)

duplicated block id: 1767
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/run.py (3:17)

duplicated block id: 1768
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/standardization_lat_lon_info.py (3:17)

duplicated block id: 1769
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/standardization_lat_lon_info.py (3:17)

duplicated block id: 1770
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/predictor.py (3:17)

duplicated block id: 1771
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1772
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/tf_records_generator.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1773
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1774
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1775
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:17)

duplicated block id: 1776
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:17)

duplicated block id: 1777
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/protein_structure/structure_from_esm_v1.py (3:17)

duplicated block id: 1778
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:17)
 - src/deep_baselines/virhunter.py (3:17)

duplicated block id: 1779
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/download_biosample_page.py (3:17)

duplicated block id: 1780
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/predict_many_samples.py (3:17)

duplicated block id: 1781
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (353:369)
 - src/data_loader.py (423:439)

duplicated block id: 1782
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/get_biosample_from_update.py (3:17)

duplicated block id: 1783
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:17)

duplicated block id: 1784
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/protein_structure/structure_from_esm_v1.py (3:17)

duplicated block id: 1785
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1786
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/predict_one_sample.py (3:17)

duplicated block id: 1787
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:17)

duplicated block id: 1788
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_1.py (3:17)

duplicated block id: 1789
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:17)

duplicated block id: 1790
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:17)

duplicated block id: 1791
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/protein_structure/structure_from_esm_v1.py (3:17)

duplicated block id: 1792
size: 12 cleaned lines of code
in 2 files:
 - src/app/app.py (418:431)
 - src/predict.py (417:430)

duplicated block id: 1793
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1794
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:17)

duplicated block id: 1795
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/predict_many_samples.py (3:17)

duplicated block id: 1796
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/evaluater.py (3:17)

duplicated block id: 1797
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/protein_structure/structure_from_esm_v1.py (3:17)

duplicated block id: 1798
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:17)

duplicated block id: 1799
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1800
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1801
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:17)

duplicated block id: 1802
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/geo_map/self_testing_nearest_station_antarctica.py (3:17)

duplicated block id: 1803
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:17)

duplicated block id: 1804
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1805
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1806
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1807
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/protein_structure/embedding_from_esmfold.py (3:17)

duplicated block id: 1808
size: 12 cleaned lines of code
in 2 files:
 - src/common/metrics.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1809
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/structure_file_reader.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1810
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/protein_structure/embedding_from_esmfold.py (3:17)

duplicated block id: 1811
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:15)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1812
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/trainer.py (3:17)

duplicated block id: 1813
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/result_process/process_predict_result.py (3:17)

duplicated block id: 1814
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (438:452)
 - src/baselines/xgb.py (314:328)

duplicated block id: 1815
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/protein_structure/merge_embedding_pdb_result.py (3:17)

duplicated block id: 1816
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_builder.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1817
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1818
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/plot/plot_map_pie_fig4_2.py (3:17)

duplicated block id: 1819
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/geo_map/download_biosample_page.py (3:17)

duplicated block id: 1820
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/predict_one_sample.py (3:17)

duplicated block id: 1821
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virtifier.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:17)

duplicated block id: 1822
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/plot/plot_map_pie_fig_aff4_2.py (3:17)

duplicated block id: 1823
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (3:17)
 - src/plot/plot_map_pie_fig4_2.py (3:17)

duplicated block id: 1824
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/protein_structure/predict_structure.py (3:17)

duplicated block id: 1825
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/run.py (3:17)

duplicated block id: 1826
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/layers.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1827
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (1:15)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1828
size: 12 cleaned lines of code
in 2 files:
 - src/data_loader.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1829
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/evaluater.py (3:17)

duplicated block id: 1830
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:17)
 - src/deep_baselines/run.py (3:17)

duplicated block id: 1831
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1832
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (3:17)
 - src/protein_structure/predict_structure.py (3:17)

duplicated block id: 1833
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/verify_train_dataset.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1834
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/get_biosample_from_update.py (3:17)

duplicated block id: 1835
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (936:947)
 - src/SSFN/modeling_bert.py (1207:1218)

duplicated block id: 1836
size: 12 cleaned lines of code
in 2 files:
 - src/common/loss.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1837
size: 12 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1838
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/ncbi_id_2_uniprot.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1839
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/statistics.py (3:17)
 - src/utils.py (3:17)

duplicated block id: 1840
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/geo_map/get_biosample_from_update.py (3:17)

duplicated block id: 1841
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1490:1502)
 - src/SSFN/modeling_bert.py (1867:1879)

duplicated block id: 1842
size: 12 cleaned lines of code
in 2 files:
 - src/biotoolbox/contact_map_generator.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1843
size: 12 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (3:17)
 - src/deep_baselines/statistics.py (3:17)

duplicated block id: 1844
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (3:17)
 - src/geo_map/parse_loc_lat_lon_from_attr.py (3:17)

duplicated block id: 1845
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1490:1502)
 - src/SSFN/modeling_bert.py (1775:1787)

duplicated block id: 1846
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1847
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/gcn.py (3:17)
 - src/deep_baselines/virtifier.py (3:17)

duplicated block id: 1848
size: 12 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1849
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (3:17)
 - src/deep_baselines/virseeker.py (3:17)

duplicated block id: 1850
size: 12 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (3:17)
 - src/protein_structure/sampling_verify_embedding_is_ok.py (3:17)

duplicated block id: 1851
size: 12 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (3:17)
 - src/deep_baselines/cheer.py (3:17)

duplicated block id: 1852
size: 11 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1141:1151)
 - src/SSFN/modeling_bert.py (1689:1699)

duplicated block id: 1853
size: 11 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (572:585)
 - src/trainer.py (108:121)

duplicated block id: 1854
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (416:426)
 - src/predict.py (871:881)

duplicated block id: 1855
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (416:426)
 - src/predict.py (841:851)

duplicated block id: 1856
size: 11 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (123:133)
 - src/protein_structure/embedding_from_esmfold.py (136:146)

duplicated block id: 1857
size: 11 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (441:453)
 - src/run.py (803:815)

duplicated block id: 1858
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (173:183)
 - src/deep_baselines/run.py (413:423)

duplicated block id: 1859
size: 11 cleaned lines of code
in 2 files:
 - src/app/app.py (147:157)
 - src/predict.py (158:168)

duplicated block id: 1860
size: 11 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (627:639)
 - src/trainer.py (177:189)

duplicated block id: 1861
size: 11 cleaned lines of code
in 2 files:
 - src/predict.py (767:777)
 - src/predict.py (871:881)

duplicated block id: 1862
size: 11 cleaned lines of code
in 2 files:
 - src/predict.py (767:777)
 - src/predict.py (841:851)

duplicated block id: 1863
size: 11 cleaned lines of code
in 2 files:
 - src/app/app.py (42:54)
 - src/deep_baselines/predict_deep_baselines.py (53:65)

duplicated block id: 1864
size: 11 cleaned lines of code
in 2 files:
 - src/predict.py (158:168)
 - src/predict_many_samples.py (157:167)

duplicated block id: 1865
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (584:596)
 - src/trainer.py (177:189)

duplicated block id: 1866
size: 11 cleaned lines of code
in 2 files:
 - src/predict.py (158:168)
 - src/predict_one_sample.py (159:169)

duplicated block id: 1867
size: 11 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (937:947)
 - src/SSFN/modeling_bert.py (1348:1358)

duplicated block id: 1868
size: 11 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (525:537)
 - src/run.py (803:815)

duplicated block id: 1869
size: 11 cleaned lines of code
in 2 files:
 - src/app/app.py (159:169)
 - src/predict.py (170:180)

duplicated block id: 1870
size: 11 cleaned lines of code
in 2 files:
 - src/data_loader.py (765:775)
 - src/predict.py (354:364)

duplicated block id: 1871
size: 11 cleaned lines of code
in 2 files:
 - src/data_loader.py (765:775)
 - src/predict_one_sample.py (372:382)

duplicated block id: 1872
size: 11 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (144:154)
 - src/protein_structure/structure_from_esm_v1.py (227:237)

duplicated block id: 1873
size: 11 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (288:304)
 - src/baselines/xgb.py (274:290)

duplicated block id: 1874
size: 11 cleaned lines of code
in 2 files:
 - src/data_loader.py (765:775)
 - src/predict_many_samples.py (369:379)

duplicated block id: 1875
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (482:494)
 - src/run.py (803:815)

duplicated block id: 1876
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (490:500)
 - src/predict.py (767:777)

duplicated block id: 1877
size: 11 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1190:1205)
 - src/SSFN/modeling_bert.py (1328:1343)

duplicated block id: 1878
size: 11 cleaned lines of code
in 2 files:
 - src/predict.py (170:180)
 - src/predict_one_sample.py (171:181)

duplicated block id: 1879
size: 11 cleaned lines of code
in 2 files:
 - src/app/app.py (353:363)
 - src/data_loader.py (765:775)

duplicated block id: 1880
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (518:528)
 - src/predict.py (767:777)

duplicated block id: 1881
size: 11 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1689:1699)
 - src/SSFN/modeling_bert.py (1869:1879)

duplicated block id: 1882
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (416:426)
 - src/deep_baselines/predict_deep_baselines.py (518:528)

duplicated block id: 1883
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (416:426)
 - src/deep_baselines/predict_deep_baselines.py (490:500)

duplicated block id: 1884
size: 11 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1689:1699)
 - src/SSFN/modeling_bert.py (1777:1787)

duplicated block id: 1885
size: 11 cleaned lines of code
in 2 files:
 - src/predict.py (170:180)
 - src/predict_many_samples.py (169:179)

duplicated block id: 1886
size: 11 cleaned lines of code
in 2 files:
 - src/evaluater.py (48:58)
 - src/predictor.py (49:59)

duplicated block id: 1887
size: 11 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (406:418)
 - src/run.py (803:815)

duplicated block id: 1888
size: 11 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (529:542)
 - src/trainer.py (108:121)

duplicated block id: 1889
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:356)
 - src/SSFN/modeling_bert.py (1778:1787)

duplicated block id: 1890
size: 10 cleaned lines of code
in 2 files:
 - src/common/metrics.py (110:119)
 - src/common/metrics.py (257:266)

duplicated block id: 1891
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:356)
 - src/SSFN/modeling_bert.py (1870:1879)

duplicated block id: 1892
size: 10 cleaned lines of code
in 2 files:
 - src/common/metrics.py (158:167)
 - src/common/metrics.py (305:314)

duplicated block id: 1893
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (394:403)
 - src/deep_baselines/run.py (467:476)

duplicated block id: 1894
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:356)
 - src/SSFN/modeling_bert.py (1579:1588)

duplicated block id: 1895
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:356)
 - src/SSFN/modeling_bert.py (1493:1502)

duplicated block id: 1896
size: 10 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (140:149)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (155:164)

duplicated block id: 1897
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (513:522)
 - src/baselines/dnn.py (533:542)

duplicated block id: 1898
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1207:1216)
 - src/SSFN/modeling_bert.py (1655:1664)

duplicated block id: 1899
size: 10 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (783:793)
 - src/evaluater.py (157:167)

duplicated block id: 1900
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:356)
 - src/SSFN/modeling_bert.py (1690:1699)

duplicated block id: 1901
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:356)
 - src/SSFN/modeling_bert.py (1142:1151)

duplicated block id: 1902
size: 10 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (232:241)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (185:194)

duplicated block id: 1903
size: 10 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (243:257)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (217:231)

duplicated block id: 1904
size: 10 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (253:262)
 - src/plot/plot_map_pie_fig_aff4_2.py (253:262)

duplicated block id: 1905
size: 10 cleaned lines of code
in 2 files:
 - src/predict.py (464:473)
 - src/predict.py (493:502)

duplicated block id: 1906
size: 10 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (195:204)
 - src/plot/plot_map_pie_fig_aff4_2.py (194:203)

duplicated block id: 1907
size: 10 cleaned lines of code
in 2 files:
 - src/data_preprocess/subword.py (88:97)
 - src/data_preprocess/subword.py (104:113)

duplicated block id: 1908
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (510:519)
 - src/baselines/xgb.py (394:403)

duplicated block id: 1909
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (429:438)
 - src/deep_baselines/run.py (467:476)

duplicated block id: 1910
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (301:310)
 - src/SSFN/modeling_bert.py (435:444)

duplicated block id: 1911
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (301:310)
 - src/SSFN/modeling_bert.py (503:512)

duplicated block id: 1912
size: 10 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (140:149)
 - src/data_preprocess/subword.py (104:113)

duplicated block id: 1913
size: 10 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (470:479)
 - src/deep_baselines/run.py (490:499)

duplicated block id: 1914
size: 10 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (219:228)
 - src/plot/plot_map_pie_fig_aff4_2.py (253:262)

duplicated block id: 1915
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (24:51)
 - src/baselines/xgb.py (24:50)

duplicated block id: 1916
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (824:834)
 - src/evaluater.py (157:167)

duplicated block id: 1917
size: 10 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (155:164)
 - src/data_preprocess/subword.py (88:97)

duplicated block id: 1918
size: 10 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (64:75)
 - src/deep_baselines/cheer.py (249:260)

duplicated block id: 1919
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (121:131)
 - src/SSFN/pooling.py (165:175)

duplicated block id: 1920
size: 10 cleaned lines of code
in 2 files:
 - src/predict.py (435:444)
 - src/predict.py (493:502)

duplicated block id: 1921
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (435:444)
 - src/SSFN/modeling_bert.py (503:512)

duplicated block id: 1922
size: 10 cleaned lines of code
in 2 files:
 - src/predict.py (435:444)
 - src/predict.py (464:473)

duplicated block id: 1923
size: 10 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (936:945)
 - src/SSFN/modeling_bert.py (1655:1664)

duplicated block id: 1924
size: 10 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (51:62)
 - src/protein_structure/structure_from_esm_v1.py (51:63)

duplicated block id: 1925
size: 10 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (765:774)
 - src/predict_one_sample.py (749:758)

duplicated block id: 1926
size: 10 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (52:61)
 - src/deep_baselines/cheer.py (384:393)

duplicated block id: 1927
size: 10 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (52:61)
 - src/deep_baselines/cheer.py (238:247)

duplicated block id: 1928
size: 10 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (510:519)
 - src/baselines/lgbm.py (429:438)

duplicated block id: 1929
size: 9 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (442:450)
 - src/predict_one_sample.py (509:517)

duplicated block id: 1930
size: 9 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (442:450)
 - src/predict_one_sample.py (477:485)

duplicated block id: 1931
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (426:434)
 - src/app/app.py (458:466)

duplicated block id: 1932
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (490:498)
 - src/predict_many_samples.py (442:450)

duplicated block id: 1933
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1107:1147)
 - src/SSFN/modeling_bert.py (1364:1379)

duplicated block id: 1934
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (426:434)
 - src/app/app.py (490:498)

duplicated block id: 1935
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (556:564)
 - src/deep_baselines/virseeker.py (221:229)

duplicated block id: 1936
size: 9 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (506:514)
 - src/predict_one_sample.py (445:453)

duplicated block id: 1937
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (776:784)
 - src/deep_baselines/run.py (864:872)

duplicated block id: 1938
size: 9 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (474:482)
 - src/predict_one_sample.py (445:453)

duplicated block id: 1939
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1364:1379)
 - src/SSFN/modeling_bert.py (1570:1584)

duplicated block id: 1940
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1348:1356)
 - src/SSFN/modeling_bert.py (1842:1850)

duplicated block id: 1941
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (807:817)
 - src/evaluater.py (196:206)

duplicated block id: 1942
size: 9 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (48:56)
 - src/plot/plot_map_pie_fig_aff4_1.py (39:47)

duplicated block id: 1943
size: 9 cleaned lines of code
in 2 files:
 - src/predict.py (425:433)
 - src/predict.py (483:491)

duplicated block id: 1944
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1364:1379)
 - src/SSFN/modeling_bert.py (1771:1783)

duplicated block id: 1945
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1364:1379)
 - src/SSFN/modeling_bert.py (1857:1875)

duplicated block id: 1946
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1348:1356)
 - src/SSFN/modeling_bert.py (1556:1564)

duplicated block id: 1947
size: 9 cleaned lines of code
in 2 files:
 - src/predict.py (454:462)
 - src/predict.py (483:491)

duplicated block id: 1948
size: 9 cleaned lines of code
in 2 files:
 - src/predict.py (425:433)
 - src/predict.py (454:462)

duplicated block id: 1949
size: 9 cleaned lines of code
in 2 files:
 - src/data_loader.py (524:532)
 - src/data_loader.py (976:984)

duplicated block id: 1950
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1348:1356)
 - src/SSFN/modeling_bert.py (1757:1765)

duplicated block id: 1951
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1348:1356)
 - src/SSFN/modeling_bert.py (1656:1664)

duplicated block id: 1952
size: 9 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (301:310)
 - src/plot/plot_map_pie_fig4_2.py (316:324)

duplicated block id: 1953
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (867:876)
 - src/predictor.py (55:64)

duplicated block id: 1954
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (70:78)
 - src/deep_baselines/virtifier.py (74:82)

duplicated block id: 1955
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (937:945)
 - src/SSFN/modeling_bert.py (1842:1850)

duplicated block id: 1956
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1656:1664)
 - src/SSFN/modeling_bert.py (1842:1850)

duplicated block id: 1957
size: 9 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (445:453)
 - src/predict_one_sample.py (509:517)

duplicated block id: 1958
size: 9 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (445:453)
 - src/predict_one_sample.py (477:485)

duplicated block id: 1959
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (937:945)
 - src/SSFN/modeling_bert.py (1556:1564)

duplicated block id: 1960
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (458:466)
 - src/predict_many_samples.py (442:450)

duplicated block id: 1961
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (937:945)
 - src/SSFN/modeling_bert.py (1757:1765)

duplicated block id: 1962
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1254:1262)
 - src/SSFN/modeling_bert.py (1373:1381)

duplicated block id: 1963
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (358:368)
 - src/run.py (593:603)

duplicated block id: 1964
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (490:498)
 - src/predict_one_sample.py (445:453)

duplicated block id: 1965
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (849:861)
 - src/baselines/lgbm.py (647:658)

duplicated block id: 1966
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1101)
 - src/SSFN/modeling_bert.py (1758:1766)

duplicated block id: 1967
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (871:880)
 - src/predictor.py (163:172)

duplicated block id: 1968
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (24:46)
 - src/deep_baselines/virseeker.py (24:46)

duplicated block id: 1969
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (647:658)
 - src/deep_baselines/run.py (808:820)

duplicated block id: 1970
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1622:1635)
 - src/SSFN/modeling_bert.py (1804:1817)

duplicated block id: 1971
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1101)
 - src/SSFN/modeling_bert.py (1557:1565)

duplicated block id: 1972
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (556:564)
 - src/deep_baselines/virtifier.py (243:251)

duplicated block id: 1973
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1101)
 - src/SSFN/modeling_bert.py (1657:1665)

duplicated block id: 1974
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (426:434)
 - src/predict_one_sample.py (509:517)

duplicated block id: 1975
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (426:434)
 - src/predict_one_sample.py (477:485)

duplicated block id: 1976
size: 9 cleaned lines of code
in 2 files:
 - src/utils.py (139:147)
 - src/utils.py (161:169)

duplicated block id: 1977
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (848:858)
 - src/evaluater.py (196:206)

duplicated block id: 1978
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1757:1765)
 - src/SSFN/modeling_bert.py (1842:1850)

duplicated block id: 1979
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (64:73)
 - src/deep_baselines/cheer.py (395:404)

duplicated block id: 1980
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (24:48)
 - src/deep_baselines/virtifier.py (24:46)

duplicated block id: 1981
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (556:564)
 - src/deep_baselines/virhunter.py (210:218)

duplicated block id: 1982
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1208:1216)
 - src/SSFN/modeling_bert.py (1842:1850)

duplicated block id: 1983
size: 9 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:411)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:457)

duplicated block id: 1984
size: 9 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (301:310)
 - src/plot/plot_map_pie_fig_aff4_2.py (332:340)

duplicated block id: 1985
size: 9 cleaned lines of code
in 2 files:
 - src/predictor.py (67:75)
 - src/predictor.py (83:91)

duplicated block id: 1986
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1208:1216)
 - src/SSFN/modeling_bert.py (1757:1765)

duplicated block id: 1987
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1556:1564)
 - src/SSFN/modeling_bert.py (1842:1850)

duplicated block id: 1988
size: 9 cleaned lines of code
in 2 files:
 - src/evaluater.py (66:74)
 - src/evaluater.py (79:87)

duplicated block id: 1989
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1208:1216)
 - src/SSFN/modeling_bert.py (1556:1564)

duplicated block id: 1990
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (24:46)
 - src/deep_baselines/virtifier.py (24:46)

duplicated block id: 1991
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (911:920)
 - src/predictor.py (163:172)

duplicated block id: 1992
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1539:1550)
 - src/SSFN/modeling_bert.py (1740:1751)

duplicated block id: 1993
size: 9 cleaned lines of code
in 2 files:
 - src/data_loader.py (507:515)
 - src/data_loader.py (957:965)

duplicated block id: 1994
size: 9 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:411)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:502)

duplicated block id: 1995
size: 9 cleaned lines of code
in 2 files:
 - src/trainer.py (70:78)
 - src/trainer.py (86:94)

duplicated block id: 1996
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (826:835)
 - src/predictor.py (55:64)

duplicated block id: 1997
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (426:434)
 - src/predict_many_samples.py (506:514)

duplicated block id: 1998
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (458:466)
 - src/predict_one_sample.py (445:453)

duplicated block id: 1999
size: 9 cleaned lines of code
in 2 files:
 - src/app/app.py (426:434)
 - src/predict_many_samples.py (474:482)

duplicated block id: 2000
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/cheer.py (24:46)
 - src/deep_baselines/virhunter.py (24:48)

duplicated block id: 2001
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (956:966)
 - src/predictor.py (264:274)

duplicated block id: 2002
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (916:926)
 - src/predictor.py (264:274)

duplicated block id: 2003
size: 9 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1101)
 - src/SSFN/modeling_bert.py (1439:1447)

duplicated block id: 2004
size: 9 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (24:41)
 - src/data_preprocess/tf_records_generator.py (24:40)

duplicated block id: 2005
size: 9 cleaned lines of code
in 2 files:
 - src/predictor.py (186:194)
 - src/predictor.py (221:229)

duplicated block id: 2006
size: 9 cleaned lines of code
in 2 files:
 - src/data_loader.py (389:397)
 - src/data_loader.py (462:470)

duplicated block id: 2007
size: 9 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (442:450)
 - src/predict_many_samples.py (506:514)

duplicated block id: 2008
size: 9 cleaned lines of code
in 2 files:
 - src/deep_baselines/virhunter.py (24:48)
 - src/deep_baselines/virseeker.py (24:46)

duplicated block id: 2009
size: 9 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (442:450)
 - src/predict_many_samples.py (474:482)

duplicated block id: 2010
size: 9 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (459:467)
 - src/deep_baselines/run.py (373:381)

duplicated block id: 2011
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (818:825)
 - src/baselines/dnn.py (905:912)

duplicated block id: 2012
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (544:556)
 - src/trainer.py (127:139)

duplicated block id: 2013
size: 8 cleaned lines of code
in 2 files:
 - src/predict.py (450:459)
 - src/predict_one_sample.py (473:482)

duplicated block id: 2014
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (488:495)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (504:511)

duplicated block id: 2015
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (235:244)
 - src/predict.py (446:455)

duplicated block id: 2016
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1439:1446)
 - src/SSFN/modeling_bert.py (1843:1850)

duplicated block id: 2017
size: 8 cleaned lines of code
in 2 files:
 - src/app/app.py (418:427)
 - src/deep_baselines/predict_deep_baselines.py (211:220)

duplicated block id: 2018
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (608:616)
 - src/evaluater.py (197:206)

duplicated block id: 2019
size: 8 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (53:60)
 - src/common/multi_label_metrics.py (116:123)

duplicated block id: 2020
size: 8 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (68:75)
 - src/plot/plot_map_pie_fig_aff4_2.py (136:143)

duplicated block id: 2021
size: 8 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (69:76)
 - src/plot/plot_map_pie_fig4_2.py (139:146)

duplicated block id: 2022
size: 8 cleaned lines of code
in 2 files:
 - src/app/app.py (454:463)
 - src/predict.py (450:459)

duplicated block id: 2023
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (849:858)
 - src/baselines/xgb.py (608:616)

duplicated block id: 2024
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (231:238)
 - src/SSFN/pooling.py (316:323)

duplicated block id: 2025
size: 8 cleaned lines of code
in 2 files:
 - src/predict.py (479:488)
 - src/predict_one_sample.py (505:514)

duplicated block id: 2026
size: 8 cleaned lines of code
in 2 files:
 - src/predict.py (450:459)
 - src/predict_many_samples.py (470:479)

duplicated block id: 2027
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (23:40)
 - src/data_preprocess/tf_records_generator.py (23:38)

duplicated block id: 2028
size: 8 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (122:129)
 - src/protein_structure/structure_from_esm_v1.py (218:225)

duplicated block id: 2029
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (732:739)
 - src/deep_baselines/run.py (823:830)

duplicated block id: 2030
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (395:402)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (443:450)

duplicated block id: 2031
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1100)
 - src/SSFN/modeling_bert.py (1843:1850)

duplicated block id: 2032
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1349:1356)
 - src/SSFN/modeling_bert.py (1439:1446)

duplicated block id: 2033
size: 8 cleaned lines of code
in 2 files:
 - src/app/app.py (266:274)
 - src/data_loader.py (642:650)

duplicated block id: 2034
size: 8 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (69:76)
 - src/plot/plot_map_pie_fig_aff4_2.py (136:143)

duplicated block id: 2035
size: 8 cleaned lines of code
in 2 files:
 - src/predict.py (479:488)
 - src/predict_many_samples.py (502:511)

duplicated block id: 2036
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (864:871)
 - src/deep_baselines/run.py (732:739)

duplicated block id: 2037
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (432:439)
 - src/baselines/lgbm.py (449:456)

duplicated block id: 2038
size: 8 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (139:146)
 - src/plot/plot_map_pie_fig_aff4_2.py (68:75)

duplicated block id: 2039
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (608:616)
 - src/deep_baselines/run.py (808:817)

duplicated block id: 2040
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1371:1379)
 - src/SSFN/modeling_bert.py (1490:1498)

duplicated block id: 2041
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (211:220)
 - src/predict_one_sample.py (437:446)

duplicated block id: 2042
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/pooling.py (141:150)
 - src/SSFN/pooling.py (185:195)

duplicated block id: 2043
size: 8 cleaned lines of code
in 2 files:
 - src/data_loader.py (642:650)
 - src/predict_one_sample.py (285:293)

duplicated block id: 2044
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (587:599)
 - src/trainer.py (127:139)

duplicated block id: 2045
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (444:451)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (488:495)

duplicated block id: 2046
size: 8 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (116:123)
 - src/common/multi_label_metrics.py (199:206)

duplicated block id: 2047
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (444:451)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (504:511)

duplicated block id: 2048
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (211:220)
 - src/predict_many_samples.py (434:443)

duplicated block id: 2049
size: 8 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (53:60)
 - src/common/multi_label_metrics.py (199:206)

duplicated block id: 2050
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1100)
 - src/SSFN/modeling_bert.py (1209:1216)

duplicated block id: 2051
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (92:100)
 - src/predict_many_samples.py (94:102)

duplicated block id: 2052
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (429:436)
 - src/run.py (785:792)

duplicated block id: 2053
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (211:220)
 - src/predict.py (417:426)

duplicated block id: 2054
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (425:432)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (516:523)

duplicated block id: 2055
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (297:304)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (342:349)

duplicated block id: 2056
size: 8 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (425:432)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (471:478)

duplicated block id: 2057
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (774:781)
 - src/baselines/dnn.py (864:871)

duplicated block id: 2058
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (444:453)
 - src/predict.py (797:806)

duplicated block id: 2059
size: 8 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (115:122)
 - src/common/multi_label_metrics.py (333:341)

duplicated block id: 2060
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (445:455)
 - src/deep_baselines/run.py (361:371)

duplicated block id: 2061
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1093:1100)
 - src/SSFN/modeling_bert.py (1349:1356)

duplicated block id: 2062
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (938:945)
 - src/SSFN/modeling_bert.py (1093:1100)

duplicated block id: 2063
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (259:268)
 - src/predict.py (475:484)

duplicated block id: 2064
size: 8 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (179:188)
 - src/plot/plot_map_pie_fig_aff4_2.py (179:187)

duplicated block id: 2065
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (774:781)
 - src/deep_baselines/run.py (823:830)

duplicated block id: 2066
size: 8 cleaned lines of code
in 2 files:
 - src/app/app.py (84:92)
 - src/deep_baselines/predict_deep_baselines.py (92:100)

duplicated block id: 2067
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (647:655)
 - src/evaluater.py (197:206)

duplicated block id: 2068
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (397:404)
 - src/baselines/xgb.py (414:421)

duplicated block id: 2069
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (938:945)
 - src/SSFN/modeling_bert.py (1439:1446)

duplicated block id: 2070
size: 8 cleaned lines of code
in 2 files:
 - src/common/metrics.py (386:393)
 - src/common/multi_label_metrics.py (458:465)

duplicated block id: 2071
size: 8 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1209:1216)
 - src/SSFN/modeling_bert.py (1439:1446)

duplicated block id: 2072
size: 8 cleaned lines of code
in 2 files:
 - src/app/app.py (486:495)
 - src/predict.py (479:488)

duplicated block id: 2073
size: 8 cleaned lines of code
in 2 files:
 - src/data_loader.py (885:892)
 - src/data_loader.py (1433:1440)

duplicated block id: 2074
size: 8 cleaned lines of code
in 2 files:
 - src/data_loader.py (885:892)
 - src/data_loader.py (1408:1415)

duplicated block id: 2075
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (66:76)
 - src/baselines/xgb.py (58:69)

duplicated block id: 2076
size: 8 cleaned lines of code
in 2 files:
 - src/data_loader.py (642:650)
 - src/predict.py (276:284)

duplicated block id: 2077
size: 8 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (394:401)
 - src/run.py (785:792)

duplicated block id: 2078
size: 8 cleaned lines of code
in 2 files:
 - src/data_loader.py (642:650)
 - src/predict_many_samples.py (282:290)

duplicated block id: 2079
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (92:100)
 - src/predict.py (93:101)

duplicated block id: 2080
size: 8 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (143:150)
 - src/deep_baselines/run.py (272:279)

duplicated block id: 2081
size: 7 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (329:335)
 - src/plot/plot_map_pie_fig_aff4_2.py (346:352)

duplicated block id: 2082
size: 7 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (99:105)
 - src/result_process/process_predict_result.py (105:111)

duplicated block id: 2083
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (222:228)
 - src/predict.py (430:436)

duplicated block id: 2084
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1719:1730)
 - src/SSFN/modeling_bert.py (1806:1817)

duplicated block id: 2085
size: 7 cleaned lines of code
in 2 files:
 - src/common/metrics.py (363:369)
 - src/common/multi_label_metrics.py (482:488)

duplicated block id: 2086
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (24:38)
 - src/deep_baselines/run.py (24:50)

duplicated block id: 2087
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (518:524)
 - src/predict_many_samples.py (545:552)

duplicated block id: 2088
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (410:416)
 - src/predict_one_sample.py (447:453)

duplicated block id: 2089
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (492:498)
 - src/predict_many_samples.py (410:416)

duplicated block id: 2090
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (533:539)
 - src/baselines/xgb.py (397:403)

duplicated block id: 2091
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (518:524)
 - src/predict_one_sample.py (543:550)

duplicated block id: 2092
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (410:416)
 - src/predict_one_sample.py (479:485)

duplicated block id: 2093
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (219:225)
 - src/deep_baselines/predict_deep_baselines.py (267:273)

duplicated block id: 2094
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (410:416)
 - src/predict_one_sample.py (511:517)

duplicated block id: 2095
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (513:519)
 - src/baselines/xgb.py (414:420)

duplicated block id: 2096
size: 7 cleaned lines of code
in 2 files:
 - src/utils.py (110:116)
 - src/utils.py (153:159)

duplicated block id: 2097
size: 7 cleaned lines of code
in 2 files:
 - src/utils.py (110:116)
 - src/utils.py (131:137)

duplicated block id: 2098
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (24:35)
 - src/deep_baselines/run.py (24:50)

duplicated block id: 2099
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (122:130)
 - src/data_loader.py (172:180)

duplicated block id: 2100
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (24:49)
 - src/protein_structure/embedding_from_esmfold.py (24:38)

duplicated block id: 2101
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (24:50)
 - src/protein_structure/merge_embedding_pdb_result.py (24:32)

duplicated block id: 2102
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (1106:1112)
 - src/predict.py (318:324)

duplicated block id: 2103
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (449:455)
 - src/deep_baselines/run.py (470:476)

duplicated block id: 2104
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (1123:1129)
 - src/predict_one_sample.py (358:364)

duplicated block id: 2105
size: 7 cleaned lines of code
in 2 files:
 - src/utils.py (131:137)
 - src/utils.py (153:159)

duplicated block id: 2106
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (476:482)
 - src/predict_one_sample.py (413:419)

duplicated block id: 2107
size: 7 cleaned lines of code
in 2 files:
 - src/evaluater.py (24:42)
 - src/predictor.py (24:43)

duplicated block id: 2108
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (24:35)
 - src/baselines/predict.py (24:38)

duplicated block id: 2109
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (432:438)
 - src/deep_baselines/run.py (490:496)

duplicated block id: 2110
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (513:519)
 - src/deep_baselines/run.py (490:496)

duplicated block id: 2111
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (414:420)
 - src/deep_baselines/run.py (470:476)

duplicated block id: 2112
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:66)
 - src/protein_structure/structure_from_esm_v1.py (246:252)

duplicated block id: 2113
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (339:345)
 - src/data_loader.py (1123:1129)

duplicated block id: 2114
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (24:49)
 - src/trainer.py (24:50)

duplicated block id: 2115
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (390:396)
 - src/data_loader.py (473:479)

duplicated block id: 2116
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (301:307)
 - src/SSFN/modeling_bert.py (581:587)

duplicated block id: 2117
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (492:498)
 - src/predict_one_sample.py (413:419)

duplicated block id: 2118
size: 7 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (413:419)
 - src/predict_one_sample.py (479:485)

duplicated block id: 2119
size: 7 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (413:419)
 - src/predict_one_sample.py (511:517)

duplicated block id: 2120
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (222:228)
 - src/deep_baselines/run.py (234:240)

duplicated block id: 2121
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (463:469)
 - src/data_loader.py (473:479)

duplicated block id: 2122
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (93:100)
 - src/predict_one_sample.py (97:104)

duplicated block id: 2123
size: 7 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (155:162)
 - src/plot/plot_map_pie_fig_aff4_2.py (154:161)

duplicated block id: 2124
size: 7 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (278:284)
 - src/result_process/process_predict_result.py (105:111)

duplicated block id: 2125
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (561:567)
 - src/plot/plot_map_pie_fig4_1.py (99:105)

duplicated block id: 2126
size: 7 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (413:419)
 - src/predict_one_sample.py (447:453)

duplicated block id: 2127
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1254:1260)
 - src/SSFN/modeling_bert.py (1492:1498)

duplicated block id: 2128
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1624:1635)
 - src/SSFN/modeling_bert.py (1719:1730)

duplicated block id: 2129
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (389:397)
 - src/predict.py (395:403)

duplicated block id: 2130
size: 7 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (76:82)
 - src/geo_map/get_biosample_from_manual.py (51:57)

duplicated block id: 2131
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1520:1531)
 - src/SSFN/modeling_bert.py (1624:1635)

duplicated block id: 2132
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (219:225)
 - src/deep_baselines/predict_deep_baselines.py (243:249)

duplicated block id: 2133
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1520:1531)
 - src/SSFN/modeling_bert.py (1719:1730)

duplicated block id: 2134
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (24:50)
 - src/protein_structure/embedding_from_esmfold.py (24:38)

duplicated block id: 2135
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1141:1147)
 - src/SSFN/modeling_bert.py (1254:1260)

duplicated block id: 2136
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (508:514)
 - src/predict_one_sample.py (413:419)

duplicated block id: 2137
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (270:276)
 - src/predict.py (488:494)

duplicated block id: 2138
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (243:249)
 - src/deep_baselines/predict_deep_baselines.py (267:273)

duplicated block id: 2139
size: 7 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (24:38)
 - src/protein_structure/merge_embedding_pdb_result.py (24:32)

duplicated block id: 2140
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (444:450)
 - src/predict_one_sample.py (413:419)

duplicated block id: 2141
size: 7 cleaned lines of code
in 2 files:
 - src/common/metrics.py (411:417)
 - src/common/multi_label_metrics.py (482:488)

duplicated block id: 2142
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (687:693)
 - src/predict_many_samples.py (355:361)

duplicated block id: 2143
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (687:693)
 - src/predict_one_sample.py (358:364)

duplicated block id: 2144
size: 7 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (24:48)
 - src/trainer.py (24:50)

duplicated block id: 2145
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1520:1531)
 - src/SSFN/modeling_bert.py (1806:1817)

duplicated block id: 2146
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (1123:1129)
 - src/predict_many_samples.py (355:361)

duplicated block id: 2147
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1254:1260)
 - src/SSFN/modeling_bert.py (1689:1695)

duplicated block id: 2148
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (428:434)
 - src/predict_one_sample.py (413:419)

duplicated block id: 2149
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (24:39)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (24:40)

duplicated block id: 2150
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (642:649)
 - src/predictor.py (265:272)

duplicated block id: 2151
size: 7 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (76:82)
 - src/geo_map/get_biosample_from_update.py (52:58)

duplicated block id: 2152
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (24:49)
 - src/protein_structure/merge_embedding_pdb_result.py (24:32)

duplicated block id: 2153
size: 7 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (90:96)
 - src/geo_map/get_biosample_from_update.py (92:98)

duplicated block id: 2154
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1254:1260)
 - src/SSFN/modeling_bert.py (1869:1875)

duplicated block id: 2155
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (533:539)
 - src/baselines/lgbm.py (432:438)

duplicated block id: 2156
size: 7 cleaned lines of code
in 2 files:
 - src/common/metrics.py (334:340)
 - src/common/multi_label_metrics.py (453:459)

duplicated block id: 2157
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1254:1260)
 - src/SSFN/modeling_bert.py (1777:1783)

duplicated block id: 2158
size: 7 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (199:205)
 - src/common/multi_label_metrics.py (334:341)

duplicated block id: 2159
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (680:687)
 - src/predictor.py (265:272)

duplicated block id: 2160
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (460:466)
 - src/predict_many_samples.py (410:416)

duplicated block id: 2161
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (251:257)
 - src/deep_baselines/predict_deep_baselines.py (275:281)

duplicated block id: 2162
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (669:675)
 - src/predict_many_samples.py (337:343)

duplicated block id: 2163
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (957:964)
 - src/baselines/lgbm.py (680:687)

duplicated block id: 2164
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (460:466)
 - src/predict_one_sample.py (413:419)

duplicated block id: 2165
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (395:403)
 - src/predict_one_sample.py (408:416)

duplicated block id: 2166
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (24:35)
 - src/protein_structure/merge_embedding_pdb_result.py (24:32)

duplicated block id: 2167
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (24:42)
 - src/geo_map/self_testing_nearest_station_antarctica.py (24:33)

duplicated block id: 2168
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (561:567)
 - src/result_process/process_predict_result.py (105:111)

duplicated block id: 2169
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/predict_one_sample.py (511:517)

duplicated block id: 2170
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (321:327)
 - src/data_loader.py (1106:1112)

duplicated block id: 2171
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/predict_one_sample.py (479:485)

duplicated block id: 2172
size: 7 cleaned lines of code
in 2 files:
 - src/common/metrics.py (241:247)
 - src/common/metrics.py (288:294)

duplicated block id: 2173
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (227:233)
 - src/deep_baselines/predict_deep_baselines.py (251:257)

duplicated block id: 2174
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (227:233)
 - src/deep_baselines/predict_deep_baselines.py (275:281)

duplicated block id: 2175
size: 7 cleaned lines of code
in 2 files:
 - src/common/metrics.py (177:183)
 - src/common/metrics.py (288:294)

duplicated block id: 2176
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/app/app.py (492:498)

duplicated block id: 2177
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (1198:1204)
 - src/data_loader.py (1300:1306)

duplicated block id: 2178
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/app/app.py (428:434)

duplicated block id: 2179
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (785:791)
 - src/data_loader.py (1323:1329)

duplicated block id: 2180
size: 7 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (246:252)
 - src/predict.py (459:465)

duplicated block id: 2181
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/app/app.py (460:466)

duplicated block id: 2182
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/predict_one_sample.py (447:453)

duplicated block id: 2183
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (400:407)
 - src/SSFN/modeling_bert.py (478:485)

duplicated block id: 2184
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (680:687)
 - src/deep_baselines/run.py (917:924)

duplicated block id: 2185
size: 7 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (53:59)
 - src/common/multi_label_metrics.py (334:341)

duplicated block id: 2186
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (103:111)
 - src/baselines/xgb.py (102:110)

duplicated block id: 2187
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (783:789)
 - src/trainer.py (70:76)

duplicated block id: 2188
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (783:789)
 - src/trainer.py (86:92)

duplicated block id: 2189
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (400:406)
 - src/predict.py (456:462)

duplicated block id: 2190
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (400:406)
 - src/predict.py (427:433)

duplicated block id: 2191
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (396:402)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (504:510)

duplicated block id: 2192
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1254:1260)
 - src/SSFN/modeling_bert.py (1578:1584)

duplicated block id: 2193
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (428:434)
 - src/predict_many_samples.py (410:416)

duplicated block id: 2194
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (396:402)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (488:494)

duplicated block id: 2195
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (24:35)
 - src/baselines/dnn.py (24:49)

duplicated block id: 2196
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (400:406)
 - src/predict.py (485:491)

duplicated block id: 2197
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (339:345)
 - src/data_loader.py (687:693)

duplicated block id: 2198
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (614:620)
 - src/predict_many_samples.py (647:653)

duplicated block id: 2199
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (669:675)
 - src/predict_one_sample.py (340:346)

duplicated block id: 2200
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (435:441)
 - src/SSFN/modeling_bert.py (581:587)

duplicated block id: 2201
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (24:38)
 - src/protein_structure/embedding_from_esmfold.py (24:38)

duplicated block id: 2202
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (321:327)
 - src/data_loader.py (669:675)

duplicated block id: 2203
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (503:509)
 - src/SSFN/modeling_bert.py (581:587)

duplicated block id: 2204
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (669:675)
 - src/predict.py (318:324)

duplicated block id: 2205
size: 7 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (136:142)
 - src/protein_structure/structure_from_esm_v1.py (219:225)

duplicated block id: 2206
size: 7 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (99:105)
 - src/protein_structure/structure_from_esm_v1.py (278:284)

duplicated block id: 2207
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (614:620)
 - src/predict_one_sample.py (639:645)

duplicated block id: 2208
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/predict.py (24:38)
 - src/protein_structure/merge_embedding_pdb_result.py (24:32)

duplicated block id: 2209
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/predict_many_samples.py (476:482)

duplicated block id: 2210
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/predict_many_samples.py (508:514)

duplicated block id: 2211
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (513:519)
 - src/baselines/lgbm.py (449:455)

duplicated block id: 2212
size: 7 cleaned lines of code
in 2 files:
 - src/app/app.py (394:400)
 - src/predict_many_samples.py (444:450)

duplicated block id: 2213
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (410:416)
 - src/predict_many_samples.py (444:450)

duplicated block id: 2214
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (957:964)
 - src/baselines/xgb.py (642:649)

duplicated block id: 2215
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (533:539)
 - src/deep_baselines/run.py (470:476)

duplicated block id: 2216
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (24:35)
 - src/protein_structure/embedding_from_esmfold.py (24:38)

duplicated block id: 2217
size: 7 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1373:1379)
 - src/SSFN/modeling_bert.py (1689:1695)

duplicated block id: 2218
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (642:649)
 - src/deep_baselines/run.py (917:924)

duplicated block id: 2219
size: 7 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (561:567)
 - src/protein_structure/structure_from_esm_v1.py (278:284)

duplicated block id: 2220
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (432:438)
 - src/baselines/xgb.py (414:420)

duplicated block id: 2221
size: 7 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (157:163)
 - src/protein_structure/structure_from_esm_v1.py (232:238)

duplicated block id: 2222
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (24:43)
 - src/geo_map/self_testing_nearest_station_antarctica.py (24:33)

duplicated block id: 2223
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (449:455)
 - src/baselines/xgb.py (397:403)

duplicated block id: 2224
size: 7 cleaned lines of code
in 2 files:
 - src/predict.py (395:403)
 - src/predict_many_samples.py (405:413)

duplicated block id: 2225
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (24:49)
 - src/baselines/predict.py (24:38)

duplicated block id: 2226
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (1106:1112)
 - src/predict_one_sample.py (340:346)

duplicated block id: 2227
size: 7 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (397:403)
 - src/deep_baselines/run.py (490:496)

duplicated block id: 2228
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (410:416)
 - src/predict_many_samples.py (508:514)

duplicated block id: 2229
size: 7 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (410:416)
 - src/predict_many_samples.py (476:482)

duplicated block id: 2230
size: 7 cleaned lines of code
in 2 files:
 - src/data_loader.py (1106:1112)
 - src/predict_many_samples.py (337:343)

duplicated block id: 2231
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2232
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2233
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2234
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)

duplicated block id: 2235
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2236
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2237
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2238
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2239
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (549:554)
 - src/run.py (103:108)

duplicated block id: 2240
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2241
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2242
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2243
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (49:54)
 - src/plot/plot_map_pie_fig_aff4_1.py (40:45)

duplicated block id: 2244
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (383:388)
 - src/run.py (742:748)

duplicated block id: 2245
size: 6 cleaned lines of code
in 2 files:
 - src/common/metrics.py (102:107)
 - src/common/metrics.py (151:156)

duplicated block id: 2246
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2247
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2248
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2249
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2250
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (334:339)
 - src/predict_many_samples.py (334:339)

duplicated block id: 2251
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2252
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2253
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (260:267)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (244:250)

duplicated block id: 2254
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2255
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (591:596)
 - src/baselines/xgb.py (621:626)

duplicated block id: 2256
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (558:565)
 - src/deep_baselines/run.py (552:559)

duplicated block id: 2257
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2258
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2259
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (336:341)
 - src/predict_many_samples.py (334:339)

duplicated block id: 2260
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (204:209)
 - src/predict_many_samples.py (424:429)

duplicated block id: 2261
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (404:409)
 - src/app/app.py (439:444)

duplicated block id: 2262
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2263
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2264
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2265
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2266
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (337:343)
 - src/deep_baselines/run.py (352:358)

duplicated block id: 2267
size: 6 cleaned lines of code
in 2 files:
 - src/predictor.py (83:88)
 - src/trainer.py (86:91)

duplicated block id: 2268
size: 6 cleaned lines of code
in 2 files:
 - src/predictor.py (83:88)
 - src/trainer.py (70:75)

duplicated block id: 2269
size: 6 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:352)
 - src/SSFN/modeling_bert.py (1374:1379)

duplicated block id: 2270
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2271
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2272
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2273
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2274
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2275
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (214:219)
 - src/data_loader.py (291:296)

duplicated block id: 2276
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (315:320)
 - src/predict.py (334:339)

duplicated block id: 2277
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2278
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (404:409)
 - src/predict_many_samples.py (455:460)

duplicated block id: 2279
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2280
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2281
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (214:219)
 - src/data_loader.py (259:264)

duplicated block id: 2282
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2283
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2284
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2285
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2286
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2287
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2288
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (564:569)
 - src/run.py (119:124)

duplicated block id: 2289
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2290
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2291
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (404:409)
 - src/predict_one_sample.py (458:463)

duplicated block id: 2292
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/predict_structure.py (97:102)
 - src/protein_structure/predict_structure.py (176:181)

duplicated block id: 2293
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2294
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2295
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2296
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2297
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (558:565)
 - src/baselines/dnn.py (595:602)

duplicated block id: 2298
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2299
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2300
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (318:323)
 - src/predict_one_sample.py (355:360)

duplicated block id: 2301
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2302
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2303
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (148:153)
 - src/plot/plot_map_pie_fig4_2.py (198:203)

duplicated block id: 2304
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2305
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (168:173)
 - src/plot/plot_map_pie_fig_aff4_2.py (197:202)

duplicated block id: 2306
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (425:430)
 - src/predict_one_sample.py (477:482)

duplicated block id: 2307
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (425:430)
 - src/predict_one_sample.py (509:514)

duplicated block id: 2308
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (334:339)
 - src/predict_many_samples.py (352:357)

duplicated block id: 2309
size: 6 cleaned lines of code
in 2 files:
 - src/predictor.py (189:194)
 - src/predictor.py (208:213)

duplicated block id: 2310
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2311
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2312
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2313
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2314
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (24:36)
 - src/data_preprocess/tf_records_generator.py (24:34)

duplicated block id: 2315
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2316
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2317
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)

duplicated block id: 2318
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2319
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2320
size: 6 cleaned lines of code
in 2 files:
 - src/common/multi_label_metrics.py (34:39)
 - src/common/multi_label_metrics.py (98:103)

duplicated block id: 2321
size: 6 cleaned lines of code
in 2 files:
 - src/SSFN/model.py (347:352)
 - src/SSFN/modeling_bert.py (1255:1260)

duplicated block id: 2322
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (315:320)
 - src/predict_one_sample.py (355:360)

duplicated block id: 2323
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (38:51)
 - src/deep_baselines/run.py (40:64)

duplicated block id: 2324
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (426:431)
 - src/predict.py (454:459)

duplicated block id: 2325
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (61:69)
 - src/baselines/xgb.py (61:69)

duplicated block id: 2326
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (454:459)
 - src/predict_one_sample.py (509:514)

duplicated block id: 2327
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (483:488)
 - src/predict_many_samples.py (442:447)

duplicated block id: 2328
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2329
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2330
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2331
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (483:488)
 - src/predict_many_samples.py (474:479)

duplicated block id: 2332
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (464:469)
 - src/predict_many_samples.py (484:489)

duplicated block id: 2333
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2334
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (464:469)
 - src/predict_many_samples.py (516:521)

duplicated block id: 2335
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2336
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (830:835)
 - src/deep_baselines/run.py (877:882)

duplicated block id: 2337
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (468:473)
 - src/predict.py (435:440)

duplicated block id: 2338
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2339
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2340
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2341
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_1.py (40:45)
 - src/plot/plot_map_pie_fig_aff4_2.py (48:53)

duplicated block id: 2342
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (454:459)
 - src/predict_one_sample.py (445:450)

duplicated block id: 2343
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2344
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (735:741)
 - src/trainer.py (352:358)

duplicated block id: 2345
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (468:473)
 - src/predict.py (464:469)

duplicated block id: 2346
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (426:431)
 - src/predict.py (483:488)

duplicated block id: 2347
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (468:473)
 - src/predict.py (493:498)

duplicated block id: 2348
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2349
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2350
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)

duplicated block id: 2351
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (86:91)
 - src/geo_map/get_biosample_from_update.py (42:47)

duplicated block id: 2352
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)

duplicated block id: 2353
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2354
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (296:301)
 - src/predict_many_samples.py (301:306)

duplicated block id: 2355
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2356
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2357
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2358
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2359
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2360
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (24:41)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (24:36)

duplicated block id: 2361
size: 6 cleaned lines of code
in 2 files:
 - src/common/metrics.py (261:266)
 - src/common/metrics.py (309:314)

duplicated block id: 2362
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2363
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2364
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (604:609)
 - src/deep_baselines/run.py (867:872)

duplicated block id: 2365
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2366
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2367
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (483:488)
 - src/predict_one_sample.py (477:482)

duplicated block id: 2368
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2369
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (604:609)
 - src/deep_baselines/run.py (779:784)

duplicated block id: 2370
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2371
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2372
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2373
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2374
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2375
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (445:452)
 - src/run.py (596:603)

duplicated block id: 2376
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2377
size: 6 cleaned lines of code
in 2 files:
 - src/predictor.py (67:72)
 - src/trainer.py (70:75)

duplicated block id: 2378
size: 6 cleaned lines of code
in 2 files:
 - src/predictor.py (67:72)
 - src/trainer.py (86:91)

duplicated block id: 2379
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2380
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2381
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2382
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (321:328)
 - src/deep_baselines/run.py (361:368)

duplicated block id: 2383
size: 6 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (590:595)
 - src/run.py (96:101)

duplicated block id: 2384
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2385
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2386
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2387
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2388
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2389
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2390
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2391
size: 6 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (304:309)
 - src/predict_one_sample.py (315:320)

duplicated block id: 2392
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2393
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (266:272)
 - src/data_loader.py (1081:1086)

duplicated block id: 2394
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2395
size: 6 cleaned lines of code
in 2 files:
 - src/trainer.py (286:291)
 - src/trainer.py (310:315)

duplicated block id: 2396
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2397
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)

duplicated block id: 2398
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (590:597)
 - src/run.py (96:101)

duplicated block id: 2399
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2400
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2401
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2402
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)

duplicated block id: 2403
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2404
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (666:671)
 - src/data_loader.py (684:689)

duplicated block id: 2405
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2406
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2407
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2408
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2409
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2410
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2411
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (301:306)
 - src/predict_many_samples.py (312:317)

duplicated block id: 2412
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (1081:1086)
 - src/predict_many_samples.py (282:288)

duplicated block id: 2413
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2414
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2415
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2416
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2417
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (296:301)
 - src/predict_one_sample.py (304:309)

duplicated block id: 2418
size: 6 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1265:1271)
 - src/SSFN/modeling_bert.py (1382:1388)

duplicated block id: 2419
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (336:341)
 - src/predict_one_sample.py (337:342)

duplicated block id: 2420
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (336:341)
 - src/predict.py (315:320)

duplicated block id: 2421
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2422
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2423
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2424
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2425
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (318:323)
 - src/predict.py (334:339)

duplicated block id: 2426
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2427
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2428
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (483:488)
 - src/predict_one_sample.py (445:450)

duplicated block id: 2429
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (318:323)
 - src/predict_many_samples.py (352:357)

duplicated block id: 2430
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2431
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2432
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2433
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)

duplicated block id: 2434
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (49:54)
 - src/plot/plot_map_pie_fig4_2.py (49:54)

duplicated block id: 2435
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)

duplicated block id: 2436
size: 6 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (612:617)
 - src/run.py (119:124)

duplicated block id: 2437
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2438
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (917:922)
 - src/deep_baselines/run.py (789:794)

duplicated block id: 2439
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (454:459)
 - src/predict_many_samples.py (442:447)

duplicated block id: 2440
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2441
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2442
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (32:48)
 - src/predictor.py (31:43)

duplicated block id: 2443
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (301:306)
 - src/predict_one_sample.py (315:320)

duplicated block id: 2444
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2445
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (500:505)
 - src/predict.py (435:440)

duplicated block id: 2446
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (500:505)
 - src/predict.py (464:469)

duplicated block id: 2447
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2448
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2449
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2450
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (285:290)
 - src/app/app.py (296:301)

duplicated block id: 2451
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2452
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2453
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2454
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2455
size: 6 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (597:602)
 - src/run.py (103:108)

duplicated block id: 2456
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2457
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (285:290)
 - src/predict_many_samples.py (312:317)

duplicated block id: 2458
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2459
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2460
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)

duplicated block id: 2461
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (830:835)
 - src/baselines/dnn.py (917:922)

duplicated block id: 2462
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2463
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2464
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2465
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2466
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2467
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (500:505)
 - src/predict.py (493:498)

duplicated block id: 2468
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2469
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)

duplicated block id: 2470
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (439:444)
 - src/predict_one_sample.py (423:428)

duplicated block id: 2471
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2472
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2473
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2474
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2475
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2476
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2477
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)

duplicated block id: 2478
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2479
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2480
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2481
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (684:689)
 - src/data_loader.py (1103:1108)

duplicated block id: 2482
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2483
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (285:290)
 - src/predict_one_sample.py (315:320)

duplicated block id: 2484
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2485
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (312:317)
 - src/predict_one_sample.py (304:309)

duplicated block id: 2486
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (454:459)
 - src/predict_many_samples.py (506:511)

duplicated block id: 2487
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2488
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2489
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2490
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2491
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (455:460)
 - src/predict_one_sample.py (423:428)

duplicated block id: 2492
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2493
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2494
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (599:604)
 - src/run.py (103:108)

duplicated block id: 2495
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2496
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2497
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (693:699)
 - src/trainer.py (352:358)

duplicated block id: 2498
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2499
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2500
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2501
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (490:495)
 - src/predict.py (425:430)

duplicated block id: 2502
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (490:495)
 - src/predict.py (454:459)

duplicated block id: 2503
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2504
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2505
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2506
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)

duplicated block id: 2507
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)

duplicated block id: 2508
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (1103:1108)
 - src/data_loader.py (1120:1125)

duplicated block id: 2509
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)

duplicated block id: 2510
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2511
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (314:320)
 - src/deep_baselines/run.py (352:358)

duplicated block id: 2512
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (515:522)
 - src/deep_baselines/run.py (552:559)

duplicated block id: 2513
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2514
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (458:463)
 - src/predict.py (425:430)

duplicated block id: 2515
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2516
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2517
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2518
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2519
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2520
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2521
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (168:173)
 - src/plot/plot_map_pie_fig4_2.py (198:203)

duplicated block id: 2522
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (246:251)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2523
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)

duplicated block id: 2524
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2525
size: 6 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1046:1051)
 - src/SSFN/modeling_bert.py (1263:1268)

duplicated block id: 2526
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2527
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (24:41)
 - src/data_preprocess/tf_records_generator.py (24:34)

duplicated block id: 2528
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2529
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2530
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2531
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2532
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/structure_from_esm_v1.py (246:251)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2533
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2534
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2535
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2536
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2537
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (287:298)
 - src/plot/plot_map_pie_fig_aff4_2.py (321:329)

duplicated block id: 2538
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2539
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2540
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2541
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (614:619)
 - src/run.py (119:124)

duplicated block id: 2542
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2543
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2544
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2545
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2546
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2547
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2548
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2549
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2550
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (438:444)
 - src/deep_baselines/run.py (352:358)

duplicated block id: 2551
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2552
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2553
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2554
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (287:292)
 - src/plot/plot_map_pie_fig_aff4_2.py (298:303)

duplicated block id: 2555
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2556
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (425:430)
 - src/predict_many_samples.py (506:511)

duplicated block id: 2557
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2558
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2559
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2560
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (269:275)
 - src/plot/plot_map_pie_fig_aff4_2.py (279:285)

duplicated block id: 2561
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2562
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2563
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (49:54)
 - src/plot/plot_map_pie_fig_aff4_2.py (48:53)

duplicated block id: 2564
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (425:430)
 - src/predict_many_samples.py (474:479)

duplicated block id: 2565
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (37:50)
 - src/deep_baselines/run.py (40:64)

duplicated block id: 2566
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2567
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (435:440)
 - src/predict_one_sample.py (519:524)

duplicated block id: 2568
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2569
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (435:440)
 - src/predict_one_sample.py (487:492)

duplicated block id: 2570
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2571
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (321:326)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2572
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (334:339)
 - src/predict_one_sample.py (337:342)

duplicated block id: 2573
size: 6 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1083:1091)
 - src/SSFN/modeling_bert.py (1194:1202)

duplicated block id: 2574
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2575
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2576
size: 6 cleaned lines of code
in 2 files:
 - src/common/metrics.py (162:167)
 - src/common/metrics.py (261:266)

duplicated block id: 2577
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2578
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (23:42)
 - src/plot/plot_map_pie_fig4_2.py (23:41)

duplicated block id: 2579
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2580
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2581
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2582
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2583
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2584
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2585
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2586
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2587
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (1081:1086)
 - src/predict_one_sample.py (285:291)

duplicated block id: 2588
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2589
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2590
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2591
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (595:602)
 - src/deep_baselines/run.py (515:522)

duplicated block id: 2592
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2593
size: 6 cleaned lines of code
in 2 files:
 - src/common/metrics.py (114:119)
 - src/common/metrics.py (309:314)

duplicated block id: 2594
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)

duplicated block id: 2595
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (315:320)
 - src/predict_many_samples.py (352:357)

duplicated block id: 2596
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (458:463)
 - src/predict.py (483:488)

duplicated block id: 2597
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)

duplicated block id: 2598
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (420:425)
 - src/predict_many_samples.py (455:460)

duplicated block id: 2599
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2600
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (344:351)
 - src/deep_baselines/run.py (361:368)

duplicated block id: 2601
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2602
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2603
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (352:357)
 - src/predict_one_sample.py (337:342)

duplicated block id: 2604
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2605
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (439:444)
 - src/predict_many_samples.py (420:425)

duplicated block id: 2606
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2607
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (567:572)
 - src/predict_one_sample.py (675:680)

duplicated block id: 2608
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2609
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2610
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2611
size: 6 cleaned lines of code
in 2 files:
 - src/common/metrics.py (114:119)
 - src/common/metrics.py (162:167)

duplicated block id: 2612
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (464:469)
 - src/predict_one_sample.py (519:524)

duplicated block id: 2613
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2614
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2615
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2616
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/embedding_from_esmfold.py (149:154)
 - src/protein_structure/embedding_from_esmfold.py (157:162)

duplicated block id: 2617
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (666:671)
 - src/data_loader.py (1120:1125)

duplicated block id: 2618
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (88:93)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (69:74)

duplicated block id: 2619
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2620
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (464:469)
 - src/predict_one_sample.py (487:492)

duplicated block id: 2621
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2622
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2623
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2624
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2625
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2626
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (493:498)
 - src/predict_one_sample.py (487:492)

duplicated block id: 2627
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (493:498)
 - src/predict_one_sample.py (519:524)

duplicated block id: 2628
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2629
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2630
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (24:41)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (24:35)

duplicated block id: 2631
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2632
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2633
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2634
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2635
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2636
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/run.py (789:794)
 - src/deep_baselines/run.py (877:882)

duplicated block id: 2637
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2638
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (1081:1086)
 - src/predict.py (276:282)

duplicated block id: 2639
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2640
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2641
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2642
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (435:440)
 - src/predict_many_samples.py (484:489)

duplicated block id: 2643
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (435:440)
 - src/predict_many_samples.py (516:521)

duplicated block id: 2644
size: 6 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (337:342)
 - src/predict_one_sample.py (355:360)

duplicated block id: 2645
size: 6 cleaned lines of code
in 2 files:
 - src/predict_one_sample.py (423:428)
 - src/predict_one_sample.py (458:463)

duplicated block id: 2646
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2647
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2648
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2649
size: 6 cleaned lines of code
in 2 files:
 - src/evaluater.py (32:42)
 - src/predict.py (32:48)

duplicated block id: 2650
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (321:328)
 - src/run.py (596:603)

duplicated block id: 2651
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)

duplicated block id: 2652
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2653
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)

duplicated block id: 2654
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2655
size: 6 cleaned lines of code
in 2 files:
 - src/trainer.py (54:59)
 - src/trainer.py (286:291)

duplicated block id: 2656
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2657
size: 6 cleaned lines of code
in 2 files:
 - src/trainer.py (54:59)
 - src/trainer.py (310:315)

duplicated block id: 2658
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2659
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2660
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (542:547)
 - src/run.py (96:101)

duplicated block id: 2661
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/virseeker.py (193:198)
 - src/deep_baselines/virtifier.py (202:207)

duplicated block id: 2662
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2663
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2664
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2665
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2666
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (148:153)
 - src/plot/plot_map_pie_fig_aff4_2.py (197:202)

duplicated block id: 2667
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (207:212)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2668
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)

duplicated block id: 2669
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2670
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)

duplicated block id: 2671
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)

duplicated block id: 2672
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)

duplicated block id: 2673
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/xgb.py (349:354)
 - src/run.py (742:748)

duplicated block id: 2674
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2675
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (283:288)
 - src/data_loader.py (315:320)

duplicated block id: 2676
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (100:105)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2677
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)

duplicated block id: 2678
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)

duplicated block id: 2679
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (307:312)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2680
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2681
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2682
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2683
size: 6 cleaned lines of code
in 2 files:
 - src/SSFN/modeling_bert.py (1083:1091)
 - src/SSFN/modeling_bert.py (1332:1340)

duplicated block id: 2684
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (198:203)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2685
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2686
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2687
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2688
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_2.py (233:238)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2689
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2690
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (24:36)
 - src/data_preprocess/data_preprocess_into_tfrecords_for_rdrp.py (24:36)

duplicated block id: 2691
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)

duplicated block id: 2692
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (24:41)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (24:36)

duplicated block id: 2693
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (567:572)
 - src/predict_many_samples.py (691:696)

duplicated block id: 2694
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (245:250)
 - src/data_loader.py (283:288)

duplicated block id: 2695
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/merge_embedding_pdb_result.py (106:111)

duplicated block id: 2696
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (783:788)
 - src/predictor.py (67:72)

duplicated block id: 2697
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2698
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (245:250)
 - src/data_loader.py (315:320)

duplicated block id: 2699
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2700
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2701
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2702
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2703
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (24:35)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (24:36)

duplicated block id: 2704
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (783:788)
 - src/predictor.py (83:88)

duplicated block id: 2705
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2706
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/structure_from_esm_v1.py (246:251)

duplicated block id: 2707
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2708
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (562:567)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2709
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/merge_embedding_pdb_result.py (130:135)

duplicated block id: 2710
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (88:93)
 - src/data_preprocess/data_preprocess_for_rdrp_v2.py (106:111)

duplicated block id: 2711
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2712
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2713
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/protein_structure/structure_from_esm_v1.py (279:284)

duplicated block id: 2714
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2715
size: 6 cleaned lines of code
in 2 files:
 - src/data_loader.py (259:264)
 - src/data_loader.py (291:296)

duplicated block id: 2716
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/lgbm.py (344:351)
 - src/run.py (596:603)

duplicated block id: 2717
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/protein_structure/merge_embedding_pdb_result.py (141:146)

duplicated block id: 2718
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/plot/plot_map_pie_fig4_1.py (198:203)

duplicated block id: 2719
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)
 - src/protein_structure/embedding_from_esmfold.py (321:326)

duplicated block id: 2720
size: 6 cleaned lines of code
in 2 files:
 - src/deep_baselines/predict_deep_baselines.py (204:209)
 - src/predict_one_sample.py (427:432)

duplicated block id: 2721
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (43:59)
 - src/baselines/lgbm.py (38:51)

duplicated block id: 2722
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/plot/plot_map_pie_fig4_2.py (233:238)

duplicated block id: 2723
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2724
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2725
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (60:65)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2726
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (383:388)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2727
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (493:498)
 - src/predict_many_samples.py (516:521)

duplicated block id: 2728
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (334:339)
 - src/predict_one_sample.py (355:360)

duplicated block id: 2729
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (316:321)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2730
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (448:453)
 - src/geo_map/standardization_lat_lon_info.py (207:212)

duplicated block id: 2731
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2732
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/geo_map/standardization_lat_lon_info.py (183:188)

duplicated block id: 2733
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (408:413)
 - src/deep_baselines/predict_deep_baselines.py (204:209)

duplicated block id: 2734
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_entrez.py (86:91)
 - src/geo_map/get_biosample_from_manual.py (41:46)

duplicated block id: 2735
size: 6 cleaned lines of code
in 2 files:
 - src/plot/plot_map_pie_fig4_1.py (148:153)
 - src/plot/plot_map_pie_fig4_1.py (168:173)

duplicated block id: 2736
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (73:78)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2737
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (420:425)
 - src/predict_one_sample.py (458:463)

duplicated block id: 2738
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/geo_map/get_biosample_from_manual.py (66:71)

duplicated block id: 2739
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/get_biosample_from_manual.py (66:71)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2740
size: 6 cleaned lines of code
in 2 files:
 - src/protein_structure/merge_embedding_pdb_result.py (74:79)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2741
size: 6 cleaned lines of code
in 2 files:
 - src/predict_many_samples.py (565:570)
 - src/predict_one_sample.py (563:568)

duplicated block id: 2742
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/plot/plot_map_pie_fig4_1.py (100:105)

duplicated block id: 2743
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v1.py (288:293)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2744
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (352:357)
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (493:498)

duplicated block id: 2745
size: 6 cleaned lines of code
in 2 files:
 - src/app/app.py (318:323)
 - src/app/app.py (336:341)

duplicated block id: 2746
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (360:365)
 - src/plot/plot_map_pie_fig_aff4_2.py (231:236)

duplicated block id: 2747
size: 6 cleaned lines of code
in 2 files:
 - src/data_preprocess/data_preprocess_for_rdrp_v3_extend.py (402:407)
 - src/result_process/process_predict_result.py (106:111)

duplicated block id: 2748
size: 6 cleaned lines of code
in 2 files:
 - src/predict.py (493:498)
 - src/predict_many_samples.py (484:489)

duplicated block id: 2749
size: 6 cleaned lines of code
in 2 files:
 - src/baselines/dnn.py (43:59)
 - src/baselines/xgb.py (37:50)

duplicated block id: 2750
size: 6 cleaned lines of code
in 2 files:
 - src/geo_map/standardization_lat_lon_info.py (183:188)
 - src/geo_map/standardization_lat_lon_info.py (207:212)