dockformer/data/parsers.py

# Copyright 2021 AlQuraishi Laboratory
# Copyright 2021 DeepMind Technologies Limited
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Functions for parsing various file formats."""
import collections
import dataclasses
import itertools
import re
import string
from typing import Dict, Iterable, List, Optional, Sequence, Tuple, Set


def parse_fasta(fasta_string: str) -> Tuple[Sequence[str], Sequence[str]]:
    """Parses FASTA string and returns list of strings with amino-acid sequences.

    Arguments:
        fasta_string: The string contents of a FASTA file.

    Returns:
        A tuple of two lists:
        * A list of sequences.
        * A list of sequence descriptions taken from the comment lines. In the
            same order as the sequences.
    """
    sequences = []
    descriptions = []
    index = -1
    for line in fasta_string.splitlines():
        line = line.strip()
        if line.startswith(">"):
            index += 1
            descriptions.append(line[1:])  # Remove the '>' at the beginning.
            sequences.append("")
            continue
        elif line.startswith("#"):
            continue
        elif not line:
            continue  # Skip blank lines.
        sequences[index] += line

    return sequences, descriptions