跳转至

Records

multimolecule.io.records.InvalidStructureFile

Bases: ValueError

Raised when an input structure file is malformed.

Source code in multimolecule/io/records.py
Python
33
34
class InvalidStructureFile(ValueError):
    r"""Raised when an input structure file is malformed."""

multimolecule.io.records.RnaSecondaryStructureRecord dataclass

Container for RNA secondary structure data (sequence + dot-bracket).

Source code in multimolecule/io/records.py
Python
37
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
@dataclass
class RnaSecondaryStructureRecord:
    r"""Container for RNA secondary structure data (sequence + dot-bracket)."""

    sequence: str
    dot_bracket: str
    id: str | None = None

    def __post_init__(self) -> None:
        if len(self.sequence) != len(self.dot_bracket):
            raise ValueError("sequence and dot_bracket must have the same length")

    def __len__(self) -> int:
        return len(self.sequence)

    @classmethod
    def read_dbn(cls, path: str | Path) -> RnaSecondaryStructureRecord:
        from .rna_secondary_structure import read_dbn

        return read_dbn(path)

    @classmethod
    def read_bpseq(cls, path: str | Path) -> RnaSecondaryStructureRecord:
        from .rna_secondary_structure import read_bpseq

        return read_bpseq(path)

    @classmethod
    def read_st(cls, path: str | Path) -> RnaSecondaryStructureRecord:
        from .rna_secondary_structure import read_rna_secondary_structure_st

        return read_rna_secondary_structure_st(path)

    def write_dbn(self, path: str | Path) -> Path:
        from .rna_secondary_structure import write_dbn

        return write_dbn(self, path)

    def write_bpseq(self, path: str | Path) -> Path:
        from .rna_secondary_structure import write_bpseq

        return write_bpseq(self, path)

multimolecule.io.records.BpRnaRecord dataclass

Bases: RnaSecondaryStructureRecord

Container for bpRNA .st annotations.

Source code in multimolecule/io/records.py
Python
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
@dataclass(kw_only=True)
class BpRnaRecord(RnaSecondaryStructureRecord):
    r"""Container for bpRNA .st annotations."""

    structure_array: str
    knot_array: str
    structure_types: Dict[str, List[str]]
    page_number: int | None

    @classmethod
    def from_rna_secondary_structure_record(cls, record: RnaSecondaryStructureRecord) -> BpRnaRecord:
        from ..utils.rna.secondary_structure.bprna import BpRnaSecondaryStructureTopology
        from .rna_secondary_structure import _count_bracket_tiers

        pairs = notations.dot_bracket_to_pairs(record.dot_bracket)
        segment_data = BpRnaSecondaryStructureTopology(record.sequence, pairs, dot_bracket=record.dot_bracket)
        page_number = _count_bracket_tiers(record.dot_bracket)
        return cls(
            sequence=record.sequence,
            dot_bracket=record.dot_bracket,
            id=record.id,
            page_number=page_number,
            structure_array=segment_data.structural_annotation,
            knot_array=segment_data.functional_annotation,
            structure_types=segment_data.structure_types,
        )

    @classmethod
    def from_sequence_pairs(
        cls,
        sequence: str,
        pairs: np.ndarray | Sequence[tuple[int, int]],
        *,
        id: str | None = None,
        dot_bracket: str | None = None,
    ) -> BpRnaRecord:
        from ..utils.rna.secondary_structure.bprna import BpRnaSecondaryStructureTopology
        from ..utils.rna.secondary_structure.pairs import normalize_pairs
        from .rna_secondary_structure import _count_bracket_tiers

        pairs = np.asarray(normalize_pairs(pairs), dtype=int)
        if dot_bracket is None:
            dot_bracket = notations.pairs_to_dot_bracket(pairs, length=len(sequence), unsafe=True)
        elif len(dot_bracket) != len(sequence):
            raise ValueError("dot_bracket length must match sequence length")
        page_number = _count_bracket_tiers(dot_bracket)
        segment_data = BpRnaSecondaryStructureTopology(sequence, pairs, dot_bracket=dot_bracket)
        return cls(
            sequence=sequence,
            dot_bracket=dot_bracket,
            id=id,
            page_number=page_number,
            structure_array=segment_data.structural_annotation,
            knot_array=segment_data.functional_annotation,
            structure_types=segment_data.structure_types,
        )

    @classmethod
    def read_st(cls, path: str | Path) -> BpRnaRecord:
        from .rna_secondary_structure import read_st

        return read_st(path)

    def write_st(self, path: str | Path) -> Path:
        from .rna_secondary_structure import write_st

        return write_st(self, path)

multimolecule.io.records.SequenceRecord dataclass

Container for FASTA records.

Source code in multimolecule/io/records.py
Python
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
@dataclass
class SequenceRecord:
    r"""Container for FASTA records."""

    sequence: str
    id: str | None = None
    comment: str | None = None

    def __len__(self) -> int:
        return len(self.sequence)

    @classmethod
    def read_fasta(cls, path: str | Path) -> SequenceRecord:
        from .fasta import read_fasta

        return read_fasta(path)

    @classmethod
    def read_fasta_records(cls, path: str | Path) -> list[SequenceRecord]:
        from .fasta import read_fasta_records

        return read_fasta_records(path)

    def write_fasta(self, path: str | Path) -> Path:
        from .fasta import write_fasta

        return write_fasta(self, path)