codeine 0.1.0__py3-none-any.whl

codeine/translation/data/weights.py

@@ -0,0 +1,232 @@
+"""
+Codon usage counts obtained from the GenScript Codon Frequency Table.
+
+Source:
+https://www.genscript.com/tools/codon-frequency-table
+
+Retrieved: 2026-06-17
+
+Values correspond to the "Number" column.
+"""
+
+ECOLI_WEIGHTS = {'F': {'TTT': 80995, 'TTC': 58774},
+                 'L': {'TTA': 52382,
+                       'TTG': 47500,
+                       'CTT': 43449,
+                       'CTC': 37347,
+                       'CTA': 15409,
+                       'CTG': 177210},
+                 'Y': {'TAT': 63937, 'TAC': 44631},
+                 '*': {'TAA': 7356, 'TAG': 989, 'TGA': 3623},
+                 'H': {'CAT': 45879, 'CAC': 34078},
+                 'Q': {'CAA': 53394, 'CAG': 104171},
+                 'I': {'ATT': 109072, 'ATC': 86796, 'ATA': 24984},
+                 'M': {'ATG': 96695},
+                 'N': {'AAT': 75436, 'AAC': 78443},
+                 'K': {'AAA': 129137, 'AAG': 45459},
+                 'V': {'GTT': 72584, 'GTC': 52439, 'GTA': 42420, 'GTG': 89265},
+                 'D': {'GAT': 119939, 'GAC': 70394},
+                 'E': {'GAA': 143353, 'GAG': 68609},
+                 'S': {'TCT': 38027,
+                       'TCC': 33430,
+                       'TCA': 32715,
+                       'TCG': 31146,
+                       'AGT': 36097,
+                       'AGC': 55551},
+                 'C': {'TGT': 19138, 'TGC': 22188},
+                 'W': {'TGG': 50991},
+                 'P': {'CCT': 27340, 'CCC': 19666, 'CCA': 31534, 'CCG': 76644},
+                 'R': {'CGT': 73197,
+                       'CGC': 72212,
+                       'CGA': 13844,
+                       'CGG': 21552,
+                       'AGA': 13152,
+                       'AGG': 7607},
+                 'T': {'ACT': 37842, 'ACC': 80547, 'ACA': 33910, 'ACG': 50269},
+                 'A': {'GCT': 62479, 'GCC': 88721, 'GCA': 77547, 'GCG': 110308},
+                 'G': {'GGT': 93325, 'GGC': 99390, 'GGA': 34799, 'GGG': 41277}}
+
+YEAST_WEIGHTS = {'F': {'TTT': 147662, 'TTC': 103110},
+                 'L': {'TTA': 149466,
+                       'TTG': 153307,
+                       'CTT': 68959,
+                       'CTC': 30501,
+                       'CTA': 75775,
+                       'CTG': 59027},
+                 'Y': {'TAT': 106420, 'TAC': 83100},
+                 '*': {'TAA': 5596, 'TAG': 2681, 'TGA': 3516},
+                 'H': {'CAT': 77724, 'CAC': 44082},
+                 'Q': {'CAA': 155751, 'CAG': 68932},
+                 'I': {'ATT': 171272, 'ATC': 96735, 'ATA': 100930},
+                 'M': {'ATG': 118274},
+                 'N': {'AAT': 204015, 'AAC': 141103},
+                 'K': {'AAA': 239186, 'AAG': 174250},
+                 'V': {'GTT': 124665, 'GTC': 65664, 'GTA': 66649, 'GTG': 60286},
+                 'D': {'GAT': 214363, 'GAC': 114918},
+                 'E': {'GAA': 260082, 'GAG': 108411},
+                 'S': {'TCT': 133502,
+                       'TCC': 80612,
+                       'TCA': 106266,
+                       'TCG': 48524,
+                       'AGT': 80293,
+                       'AGC': 54825},
+                 'C': {'TGT': 45222, 'TGC': 26520},
+                 'W': {'TGG': 58416},
+                 'P': {'CCT': 77061, 'CCC': 38414, 'CCA': 103062, 'CCG': 29916},
+                 'R': {'CGT': 36693,
+                       'CGC': 14645,
+                       'CGA': 17111,
+                       'CGG': 9872,
+                       'AGA': 120587,
+                       'AGG': 52322},
+                 'T': {'ACT': 114746, 'ACC': 71204, 'ACA': 100680, 'ACG': 44995},
+                 'A': {'GCT': 119402, 'GCC': 71065, 'GCA': 91502, 'GCG': 34754},
+                 'G': {'GGT': 135417, 'GGC': 54977, 'GGA': 61825, 'GGG': 33885}}
+
+HUMAN_WEIGHTS = {'F': {'TTT': 336562, 'TTC': 406571},
+                 'L': {'TTA': 143715,
+                       'TTG': 249879,
+                       'CTT': 253795,
+                       'CTC': 386182,
+                       'CTA': 138154,
+                       'CTG': 800774},
+                 'Y': {'TAT': 239268, 'TAC': 310695},
+                 '*': {'TAA': 14322, 'TAG': 10915, 'TGA': 25383},
+                 'H': {'CAT': 207826, 'CAC': 297048},
+                 'Q': {'CAA': 234785, 'CAG': 688316},
+                 'I': {'ATT': 313225, 'ATC': 426570, 'ATA': 140652},
+                 'M': {'ATG': 443795},
+                 'N': {'AAT': 331714, 'AAC': 387148},
+                 'K': {'AAA': 476554, 'AAG': 654280},
+                 'V': {'GTT': 216818, 'GTC': 290874, 'GTA': 139156, 'GTG': 575438},
+                 'D': {'GAT': 443369, 'GAC': 517579},
+                 'E': {'GAA': 577846, 'GAG': 810842},
+                 'S': {'TCT': 291040,
+                       'TCC': 346943,
+                       'TCA': 233110,
+                       'TCG': 89429,
+                       'AGT': 237404,
+                       'AGC': 385113},
+                 'C': {'TGT': 197293, 'TGC': 243685},
+                 'W': {'TGG': 255512},
+                 'P': {'CCT': 343793, 'CCC': 397790, 'CCA': 331944, 'CCG': 139414},
+                 'R': {'CGT': 93458,
+                       'CGC': 217130,
+                       'CGA': 126113,
+                       'CGG': 235938,
+                       'AGA': 228151,
+                       'AGG': 227281},
+                 'T': {'ACT': 255582, 'ACC': 382050, 'ACA': 294223, 'ACG': 123533},
+                 'A': {'GCT': 370873, 'GCC': 567930, 'GCA': 317338, 'GCG': 150708},
+                 'G': {'GGT': 215544, 'GGC': 453917, 'GGA': 325243, 'GGG': 326879}}
+
+MOUSE_WEIGHTS = {'F': {'TTT': 244935, 'TTC': 319002},
+                 'L': {'TTA': 92974,
+                       'TTG': 189840,
+                       'CTT': 188236,
+                       'CTC': 290198,
+                       'CTA': 114707,
+                       'CTG': 571592},
+                 'S': {'TCT': 228046,
+                       'TCC': 258787,
+                       'TCA': 165371,
+                       'TCG': 61116,
+                       'AGT': 176056,
+                       'AGC': 279098},
+                 'Y': {'TAT': 175198, 'TAC': 236579},
+                 '*': {'TAA': 8861, 'TAG': 7491, 'TGA': 17004},
+                 'C': {'TGT': 158573, 'TGC': 173509},
+                 'W': {'TGG': 177261},
+                 'P': {'CCT': 261478, 'CCC': 262874, 'CCA': 244064, 'CCG': 89477},
+                 'H': {'CAT': 145279, 'CAC': 217261},
+                 'Q': {'CAA': 163794, 'CAG': 486041},
+                 'R': {'CGT': 66962,
+                       'CGC': 136330,
+                       'CGA': 94626,
+                       'CGG': 147905,
+                       'AGA': 163062,
+                       'AGG': 167166},
+                 'I': {'ATT': 223528, 'ATC': 332072, 'ATA': 103441},
+                 'M': {'ATG': 330431},
+                 'T': {'ACT': 194120, 'ACC': 274588, 'ACA': 227958, 'ACG': 82653},
+                 'N': {'AAT': 221760, 'AAC': 296083},
+                 'K': {'AAA': 305128, 'AAG': 482643},
+                 'V': {'GTT': 152706, 'GTC': 224465, 'GTA': 105532, 'GTG': 416428},
+                 'A': {'GCT': 288132, 'GCC': 378142, 'GCA': 226309, 'GCG': 94463},
+                 'D': {'GAT': 301359, 'GAC': 380355},
+                 'E': {'GAA': 379216, 'GAG': 563999},
+                 'G': {'GGT': 164971, 'GGC': 312846, 'GGA': 241435, 'GGG': 220474}}
+
+ARABIDOPSIS_WEIGHTS = {'F': {'TTT': 534456, 'TTC': 505253},
+                       'L': {'TTA': 308336,
+                             'TTG': 508909,
+                             'CTT': 589767,
+                             'CTC': 391502,
+                             'CTA': 240784,
+                             'CTG': 240472},
+                       'S': {'TCT': 610403,
+                             'TCC': 270545,
+                             'TCA': 440264,
+                             'TCG': 223500,
+                             'AGT': 339903,
+                             'AGC': 273815},
+                       'Y': {'TAT': 359583, 'TAC': 337738},
+                       '*': {'TAA': 22128, 'TAG': 12250, 'TGA': 26304},
+                       'C': {'TGT': 254179, 'TGC': 171924},
+                       'W': {'TGG': 304101},
+                       'P': {'CCT': 455638, 'CCC': 129838, 'CCA': 393957, 'CCG': 207684},
+                       'H': {'CAT': 334012, 'CAC': 211635},
+                       'Q': {'CAA': 470475, 'CAG': 371091},
+                       'R': {'CGT': 220192,
+                             'CGC': 91869,
+                             'CGA': 152537,
+                             'CGG': 117195,
+                             'AGA': 457927,
+                             'AGG': 266406},
+                       'I': {'ATT': 528593, 'ATC': 452968, 'ATA': 305594},
+                       'M': {'ATG': 594807},
+                       'T': {'ACT': 431031, 'ACC': 252577, 'ACA': 381774, 'ACG': 186589},
+                       'N': {'AAT': 543539, 'AAC': 508277},
+                       'K': {'AAA': 749448, 'AAG': 798966},
+                       'V': {'GTT': 668037, 'GTC': 312848, 'GTA': 242644, 'GTG': 423929},
+                       'A': {'GCT': 697575, 'GCC': 253877, 'GCA': 427842, 'GCG': 217886},
+                       'D': {'GAT': 895566, 'GAC': 420193},
+                       'E': {'GAA': 836077, 'GAG': 786970},
+                       'G': {'GGT': 546544, 'GGC': 223041, 'GGA': 592219, 'GGG': 249165}}
+
+DROSOPHILA_WEIGHTS = {'F': {'TTT': 241160, 'TTC': 402987},
+                      'L': {'TTA': 80654,
+                            'TTG': 294929,
+                            'CTT': 164079,
+                            'CTC': 255170,
+                            'CTA': 150674,
+                            'CTG': 709057},
+                      'S': {'TCT': 127758,
+                            'TCC': 359352,
+                            'TCA': 142775,
+                            'TCG': 307642,
+                            'AGT': 211452,
+                            'AGC': 377750},
+                      'Y': {'TAT': 196987, 'TAC': 338493},
+                      '*': {'TAA': 14550, 'TAG': 11721, 'TGA': 9358},
+                      'C': {'TGT': 98056, 'TGC': 241823},
+                      'W': {'TGG': 181191},
+                      'P': {'CCT': 127584, 'CCC': 331799, 'CCA': 248604, 'CCG': 293998},
+                      'H': {'CAT': 194039, 'CAC': 294555},
+                      'Q': {'CAA': 287398, 'CAG': 674575},
+                      'R': {'CGT': 161800,
+                            'CGC': 334733,
+                            'CGA': 155637,
+                            'CGG': 151728,
+                            'AGA': 93738,
+                            'AGG': 115430},
+                      'I': {'ATT': 302063, 'ATC': 421851, 'ATA': 171610},
+                      'M': {'ATG': 431822},
+                      'T': {'ACT': 175261, 'ACC': 393516, 'ACA': 201178, 'ACG': 267095},
+                      'N': {'AAT': 385441, 'AAC': 483430},
+                      'K': {'AAA': 304266, 'AAG': 729428},
+                      'V': {'GTT': 200189, 'GTC': 254974, 'GTA': 116035, 'GTG': 514471},
+                      'A': {'GCT': 265295, 'GCC': 620889, 'GCA': 234549, 'GCG': 259119},
+                      'D': {'GAT': 504880, 'GAC': 454677},
+                      'E': {'GAA': 383850, 'GAG': 789807},
+                      'G': {'GGT': 243460, 'GGC': 492283, 'GGA': 326983, 'GGG': 85472}}

codeine/translation/tables.py

@@ -0,0 +1,200 @@
+import json
+import re
+
+from pathlib import Path
+from typing import Any, Dict
+
+from codeine.utils.dict import FrozenDict
+
+
+class TranslationTable:
+    """
+    Translation table. Here we use the NCBI translation table IDs
+    (see https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi)
+    Uses DNA by default, but can switch to RNA by setting ``rna=True``.
+    """
+
+    def __init__(self, table_id: int = 1, rna: bool = False) -> None:
+        """
+        Parameters
+        ----------
+        table_id
+            Which translation table to use. Default is 1, which is the standard genetic code.
+        rna
+            Whether to use RNA. Default is no (False), i.e. use DNA.
+        """
+        self._locked = False
+
+        self.table_id = table_id
+        self.rna = rna
+
+        tables = self._load_tables()
+
+        try:
+            table = tables[str(table_id)]
+        except KeyError:
+            raise ValueError(f'Unknown NCBI translation table ID: {table_id}.')
+
+        self.name = table['name']
+        self.names = tuple(table.get('names', (self.name,)))
+
+        self.stop_codons = tuple(
+            self.normalise_sequence(codon)
+            for codon in table['stop_codons']
+        )
+
+        dna_to_aa = table['codon_to_aa']
+
+        aa_to_dna = {}
+        for codon, aa in dna_to_aa.items():
+            aa_to_dna.setdefault(aa, []).append(codon)
+
+        codons_to_aa = {
+            self.normalise_sequence(codon): aa
+            for codon, aa in dna_to_aa.items()
+        }
+
+        aa_to_codons = {
+            aa: tuple(
+                self.normalise_sequence(codon)
+                for codon in codons
+            )
+            for aa, codons in aa_to_dna.items()
+        }
+
+        self.codons_to_aa = FrozenDict(codons_to_aa)
+        self.aa_to_codons = FrozenDict(aa_to_codons)
+
+        self._locked = True
+
+    @classmethod
+    def custom(
+            cls,
+            codons_to_aa: Dict[str, str],
+            name: str = 'Custom',
+            rna: bool = False,
+    ) -> 'TranslationTable':
+        """
+        Create a custom translation table.
+
+        This is useful for synthetic, partial, experimental, or externally
+        defined translation tables, or for tables that have been discovered
+        but not yet added to Codeine. Codons are normalised to DNA or RNA
+        according to the ``rna`` argument.
+
+        Parameters
+        ----------
+        codons_to_aa
+            Mapping from codons to amino-acid symbols.
+        name
+            Name of the custom translation table. Default is ``'Custom'``.
+        rna
+            Whether the table should use RNA codons.
+
+        Returns
+        -------
+        TranslationTable
+            A custom translation table.
+        """
+        obj = cls.__new__(cls)
+        obj._locked = False
+
+        obj.table_id = None
+        obj.rna = rna
+        obj.name = name
+        obj.names = (name,)
+
+        normalised = {
+            obj.normalise_sequence(codon): aa
+            for codon, aa in codons_to_aa.items()
+        }
+
+        if any(len(codon) != 3 for codon in normalised):
+            raise ValueError('All codons must have length 3.')
+
+        if any(len(aa) != 1 for aa in normalised.values()):
+            raise ValueError('Amino-acid symbols must be single characters.')
+
+        aa_to_codons = {}
+        for codon, aa in normalised.items():
+            aa_to_codons.setdefault(aa, []).append(codon)
+
+        obj.stop_codons = tuple(codon for codon, aa in normalised.items() if aa == '*')
+
+        obj.codons_to_aa = FrozenDict(normalised)
+        obj.aa_to_codons = FrozenDict({aa: tuple(codons) for aa, codons in aa_to_codons.items()})
+
+        obj._locked = True
+        return obj
+
+    def __setattr__(self, name: str, value: Any) -> None:
+        if getattr(self, '_locked', False) and name != '_locked':
+            raise AttributeError(f'{type(self).__name__} is immutable')
+        object.__setattr__(self, name, value)
+
+    def __repr__(self) -> str:
+        molecule = 'RNA' if self.rna else 'DNA'
+
+        lines = [
+            'TranslationTable',
+            f'Table ID: {self.table_id} ({self.name})',
+            f'Molecule type: {molecule}',
+            '',
+            'Table:',
+        ]
+
+        for aa in sorted(self.aa_to_codons):
+            codons = ' '.join(self.aa_to_codons[aa])
+            lines.append(f'    {aa}: {codons}')
+
+        return '\n'.join(lines)
+
+    def __getitem__(self, codon: str) -> str:
+        try:
+            codon = self.normalise_sequence(codon)
+            return self.codons_to_aa[codon]
+
+        except (AttributeError, TypeError, ValueError, KeyError) as e:
+            raise KeyError(f'Invalid codon: {codon}.') from e
+
+    def normalise_sequence(self, seq: str) -> str:
+        """
+        Format a sequence in the format specified by this codon table, i.e. convert to
+        RNA/DNA and cast to upper case.
+
+        Parameters
+        ----------
+        codon
+            The inputted codon.
+
+        Returns
+        -------
+        The normalised codon.
+        """
+        seq = seq.upper().replace(' ', '')
+        seq = seq.replace('T', 'U') if self.rna else seq.replace('U', 'T')
+        regex = r'^[ACGU]*$' if self.rna else r'^[ACGT]*$'
+        if not re.match(regex, seq):
+            raise ValueError('Sequence to normalise must be a nucleotide sequence.')
+        else:
+            return seq
+
+    def translate(self, seq: str) -> str:
+        """
+        Translate a DNA/RNA coding sequence into its amino-acid sequence.
+        """
+        if len(seq) % 3 != 0:
+            raise ValueError('Sequence length must be a multiple of 3')
+
+        seq = self.normalise_sequence(seq)
+
+        return ''.join(self.codons_to_aa[seq[i:i + 3]] for i in range(0, len(seq), 3))
+
+    @staticmethod
+    def _load_tables() -> dict:
+        """
+        Load tables from stored JSON entries.
+        """
+        path = Path(__file__).parent / 'data' / 'tables.json'
+        with path.open() as f:
+            return json.load(f)