def _parse_hhr_hit()

in src/analysis/parsers.py [0:0]


def _parse_hhr_hit(detailed_lines: Sequence[str]) -> TemplateHit:
  """Parses the detailed HMM HMM comparison section for a single Hit.

  This works on .hhr files generated from both HHBlits and HHSearch.

  Args:
    detailed_lines: A list of lines from a single comparison section between 2
      sequences (which each have their own HMM's)

  Returns:
    A dictionary with the information from that detailed comparison section

  Raises:
    RuntimeError: If a certain line cannot be processed
  """
  # Parse first 2 lines.
  number_of_hit = int(detailed_lines[0].split()[-1])
  name_hit = detailed_lines[1][1:]

  # Parse the summary line.
  pattern = (
      'Probab=(.*)[\t ]*E-value=(.*)[\t ]*Score=(.*)[\t ]*Aligned_cols=(.*)[\t'
      ' ]*Identities=(.*)%[\t ]*Similarity=(.*)[\t ]*Sum_probs=(.*)[\t '
      ']*Template_Neff=(.*)')
  match = re.match(pattern, detailed_lines[2])
  if match is None:
    raise RuntimeError(
        'Could not parse section: %s. Expected this: \n%s to contain summary.' %
        (detailed_lines, detailed_lines[2]))
  (_, _, _, aligned_cols, _, _, sum_probs, _) = [float(x)
                                                 for x in match.groups()]

  # The next section reads the detailed comparisons. These are in a 'human
  # readable' format which has a fixed length. The strategy employed is to
  # assume that each block starts with the query sequence line, and to parse
  # that with a regexp in order to deduce the fixed length used for that block.
  query = ''
  hit_sequence = ''
  indices_query = []
  indices_hit = []
  length_block = None

  for line in detailed_lines[3:]:
    # Parse the query sequence line
    if (line.startswith('Q ') and not line.startswith('Q ss_dssp') and
        not line.startswith('Q ss_pred') and
        not line.startswith('Q Consensus')):
      # Thus the first 17 characters must be 'Q <query_name> ', and we can parse
      # everything after that.
      #              start    sequence       end       total_sequence_length
      patt = r'[\t ]*([0-9]*) ([A-Z-]*)[\t ]*([0-9]*) \([0-9]*\)'
      groups = _get_hhr_line_regex_groups(patt, line[17:])

      # Get the length of the parsed block using the start and finish indices,
      # and ensure it is the same as the actual block length.
      start = int(groups[0]) - 1  # Make index zero based.
      delta_query = groups[1]
      end = int(groups[2])
      num_insertions = len([x for x in delta_query if x == '-'])
      length_block = end - start + num_insertions
      assert length_block == len(delta_query)

      # Update the query sequence and indices list.
      query += delta_query
      _update_hhr_residue_indices_list(delta_query, start, indices_query)

    elif line.startswith('T '):
      # Parse the hit sequence.
      if (not line.startswith('T ss_dssp') and
          not line.startswith('T ss_pred') and
          not line.startswith('T Consensus')):
        # Thus the first 17 characters must be 'T <hit_name> ', and we can
        # parse everything after that.
        #              start    sequence       end     total_sequence_length
        patt = r'[\t ]*([0-9]*) ([A-Z-]*)[\t ]*[0-9]* \([0-9]*\)'
        groups = _get_hhr_line_regex_groups(patt, line[17:])
        start = int(groups[0]) - 1  # Make index zero based.
        delta_hit_sequence = groups[1]
        assert length_block == len(delta_hit_sequence)

        # Update the hit sequence and indices list.
        hit_sequence += delta_hit_sequence
        _update_hhr_residue_indices_list(delta_hit_sequence, start, indices_hit)

  return TemplateHit(
      index=number_of_hit,
      name=name_hit,
      aligned_cols=int(aligned_cols),
      sum_probs=sum_probs,
      query=query,
      hit_sequence=hit_sequence,
      indices_query=indices_query,
      indices_hit=indices_hit,
  )