src/predict.py [187:257]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - assert seq_tokenizer is not None or struct_tokenizer is not None or args.embedding_type is not None if seq_tokenizer: if subword: seq_to_list = subword.process_line(protein_seq).split(" ") else: seq_to_list = [v for v in protein_seq] cur_seq_len = len(seq_to_list) if cur_seq_len > args.seq_max_length - 2: if args.trunc_type == "left": seq_to_list = seq_to_list[2 - args.seq_max_length:] else: seq_to_list = seq_to_list[:args.seq_max_length - 2] seq = " ".join(seq_to_list) inputs = seq_tokenizer.encode_plus( seq, None, add_special_tokens=True, max_length=args.seq_max_length, truncation=True ) # input_ids: token index list # token_type_ids: token type index list input_ids, token_type_ids = inputs["input_ids"], inputs["token_type_ids"] real_token_len = len(input_ids) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. attention_mask = [1 if mask_padding_with_zero else 0] * len(input_ids) # Zero-pad up to the sequence length. padding_length = args.seq_max_length - len(input_ids) attention_mask_padding_length = padding_length if pad_on_left: input_ids = ([pad_token] * padding_length) + input_ids attention_mask = ([0 if mask_padding_with_zero else 1] * attention_mask_padding_length) + attention_mask token_type_ids = ([pad_token_segment_id] * padding_length) + token_type_ids else: input_ids = input_ids + ([pad_token] * padding_length) attention_mask = attention_mask + ([0 if mask_padding_with_zero else 1] * attention_mask_padding_length) token_type_ids = token_type_ids + ([pad_token_segment_id] * padding_length) assert len(input_ids) == args.seq_max_length, "Error with input length {} vs {}".format(len(input_ids), args.seq_max_length) assert len(attention_mask) == args.seq_max_length, "Error with input length {} vs {}".format(len(attention_mask), args.seq_max_length) assert len(token_type_ids) == args.seq_max_length, "Error with input length {} vs {}".format(len(token_type_ids), args.seq_max_length) else: input_ids = None attention_mask = None token_type_ids = None real_token_len = None if struct_tokenizer: # for structure cur_seq_len = len(protein_seq) seq_list = [ch for ch in protein_seq] if cur_seq_len > args.struct_max_length: if args.trunc_type == "left": seq_list = seq_list[-args.struct_max_length:] else: seq_list = seq_list[:args.struct_max_length] seq = " ".join(seq_list) inputs = struct_tokenizer.encode_plus( seq, None, add_special_tokens=False, max_length=args.struct_max_length, truncation=True, return_token_type_ids=False, ) struct_input_ids = inputs["input_ids"] real_struct_node_size = len(struct_input_ids) padding_length = args.struct_max_length - real_struct_node_size if real_struct_node_size < args.struct_max_length else 0 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - src/predict_many_samples.py [183:253]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - assert seq_tokenizer is not None or struct_tokenizer is not None or args.embedding_type is not None if seq_tokenizer: if subword: seq_to_list = subword.process_line(protein_seq).split(" ") else: seq_to_list = [v for v in protein_seq] cur_seq_len = len(seq_to_list) if cur_seq_len > args.seq_max_length - 2: if args.trunc_type == "left": seq_to_list = seq_to_list[2 - args.seq_max_length:] else: seq_to_list = seq_to_list[:args.seq_max_length - 2] seq = " ".join(seq_to_list) inputs = seq_tokenizer.encode_plus( seq, None, add_special_tokens=True, max_length=args.seq_max_length, truncation=True ) # input_ids: token index list # token_type_ids: token type index list input_ids, token_type_ids = inputs["input_ids"], inputs["token_type_ids"] real_token_len = len(input_ids) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. attention_mask = [1 if mask_padding_with_zero else 0] * len(input_ids) # Zero-pad up to the sequence length. padding_length = args.seq_max_length - len(input_ids) attention_mask_padding_length = padding_length if pad_on_left: input_ids = ([pad_token] * padding_length) + input_ids attention_mask = ([0 if mask_padding_with_zero else 1] * attention_mask_padding_length) + attention_mask token_type_ids = ([pad_token_segment_id] * padding_length) + token_type_ids else: input_ids = input_ids + ([pad_token] * padding_length) attention_mask = attention_mask + ([0 if mask_padding_with_zero else 1] * attention_mask_padding_length) token_type_ids = token_type_ids + ([pad_token_segment_id] * padding_length) assert len(input_ids) == args.seq_max_length, "Error with input length {} vs {}".format(len(input_ids), args.seq_max_length) assert len(attention_mask) == args.seq_max_length, "Error with input length {} vs {}".format(len(attention_mask), args.seq_max_length) assert len(token_type_ids) == args.seq_max_length, "Error with input length {} vs {}".format(len(token_type_ids), args.seq_max_length) else: input_ids = None attention_mask = None token_type_ids = None real_token_len = None if struct_tokenizer: # for structure cur_seq_len = len(protein_seq) seq_list = [ch for ch in protein_seq] if cur_seq_len > args.struct_max_length: if args.trunc_type == "left": seq_list = seq_list[-args.struct_max_length:] else: seq_list = seq_list[:args.struct_max_length] seq = " ".join(seq_list) inputs = struct_tokenizer.encode_plus( seq, None, add_special_tokens=False, max_length=args.struct_max_length, truncation=True, return_token_type_ids=False, ) struct_input_ids = inputs["input_ids"] real_struct_node_size = len(struct_input_ids) padding_length = args.struct_max_length - real_struct_node_size if real_struct_node_size < args.struct_max_length else 0 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -