Skip to content

Fasta

multimolecule.io.fasta.read_fasta

Python
read_fasta(path: str | Path) -> SequenceRecord

Parse a FASTA file and return the first record.

Source code in multimolecule/io/fasta.py
Python
32
33
34
35
def read_fasta(path: str | Path) -> SequenceRecord:
    r"""Parse a FASTA file and return the first record."""

    return read_fasta_records(path)[0]

multimolecule.io.fasta.read_fasta_records

Python
read_fasta_records(
    path: str | Path,
) -> list[SequenceRecord]

Parse a FASTA file and return all records.

Source code in multimolecule/io/fasta.py
Python
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
def read_fasta_records(path: str | Path) -> list[SequenceRecord]:
    r"""Parse a FASTA file and return all records."""

    path = Path(path)
    records: list[SequenceRecord] = []
    id: str | None = None
    comment: str | None = None
    seq_parts: list[str] = []
    saw_header = False

    def flush_record() -> None:
        nonlocal id, comment, seq_parts, saw_header
        if not saw_header and not seq_parts:
            return
        if saw_header and not seq_parts:
            raise InvalidStructureFile(f"Missing sequence line after defline in {path!s}")
        records.append(SequenceRecord(sequence="".join(seq_parts), id=id, comment=comment))
        id = None
        comment = None
        seq_parts = []
        saw_header = False

    with path.open() as fh:
        for line in fh:
            stripped = line.strip()
            if not stripped:
                continue
            if stripped.startswith("#") or stripped.startswith(";"):
                continue
            if stripped.startswith(">"):
                flush_record()
                saw_header = True
                header = stripped[1:].strip()
                if header:
                    parts = header.split(None, 1)
                    id = parts[0]
                    comment = parts[1].strip() if len(parts) > 1 else None
                continue
            seq_parts.append(stripped)

    flush_record()
    if not records:
        raise InvalidStructureFile(f"No FASTA records found in {path!s}")
    return records

multimolecule.io.fasta.write_fasta

Python
write_fasta(
    record: SequenceRecord, path: str | Path
) -> Path

Write a FASTA file for a single record.

Source code in multimolecule/io/fasta.py
Python
84
85
86
87
88
89
def write_fasta(record: SequenceRecord, path: str | Path) -> Path:
    r"""Write a FASTA file for a single record."""

    if not isinstance(record, SequenceRecord):
        raise TypeError("record must be a SequenceRecord")
    return write_fasta_records([record], path)

multimolecule.io.fasta.write_fasta_records

Python
write_fasta_records(
    records: Sequence[SequenceRecord], path: str | Path
) -> Path

Write a FASTA file for one or more records.

Source code in multimolecule/io/fasta.py
Python
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
def write_fasta_records(records: Sequence[SequenceRecord], path: str | Path) -> Path:
    r"""Write a FASTA file for one or more records."""

    path = Path(path)
    if not records:
        raise ValueError("records must contain at least one SequenceRecord")
    with path.open("w") as fh:
        for index, record in enumerate(records):
            if not isinstance(record, SequenceRecord):
                raise TypeError("records must contain only SequenceRecord instances")
            name = record.id
            if name is None:
                name = path.stem if len(records) == 1 else f"{path.stem}_{index + 1}"
            comment = record.comment or ""
            fh.write(f">{name}{' ' + comment if comment else ''}\n")
            fh.write(f"{record.sequence}\n")
    return path