biofiles 0.0.8__py3-none-any.whl → 0.0.9__py3-none-any.whl

biofiles/feature.py

@@ -1,10 +1,17 @@
 from collections import deque
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Iterator, TextIO, Type, TypeVar
+from typing import Iterator, TextIO, Type, TypeVar, cast
 
 from biofiles.common import Reader, Strand
-from biofiles.types.feature import Feature, Gene, ThreePrimeUTR, Exon, UTR, Transcript
+from biofiles.types.feature import (
+    Feature,
+    Gene,
+    ThreePrimeUTR,
+    Exon,
+    UTR,
+    Transcript,
+)
 
 
 @dataclass
@@ -60,6 +67,12 @@ class Features:
             self.by_id[id_] = feature
 
 
+FeatureT = TypeVar("FeatureT", bound=Feature)
+GeneT = TypeVar("GeneT", bound=Gene)
+TranscriptT = TypeVar("TranscriptT", bound=Transcript)
+UTRT = TypeVar("UTRT", bound=UTR)
+
+
 class FeatureReader(Reader):
     def __init__(
         self, input_: TextIO | Path | str, /, streaming_window: int | None = 1000
@@ -107,10 +120,10 @@ class FeatureReader(Reader):
 
     def _finalize_draft(self, draft: FeatureDraft, result: Features) -> Feature:
         match draft.type_.lower():
-            case "gene":
-                feature = self._finalize_gene(draft, result)
-            case "transcript":
-                feature = self._finalize_transcript(draft, result)
+            case "gene" | "ncrna_gene":
+                feature = self._finalize_gene(draft, result, Gene)
+            case "transcript" | "mrna" | "lnc_rna":
+                feature = self._finalize_transcript(draft, result, Transcript)
             case "exon":
                 feature = self._finalize_exon(draft, result)
             case "three_prime_utr":
@@ -124,19 +137,23 @@ class FeatureReader(Reader):
             object.__setattr__(feature.parent, "children", new_children)
         return feature
 
-    def _finalize_gene(self, draft: FeatureDraft, result: Features) -> Feature:
+    def _finalize_gene(
+        self, draft: FeatureDraft, result: Features, type_: Type[GeneT]
+    ) -> Feature:
         feature = self._finalize_other(draft, result)
         name = draft.pick_attribute("gene_name", "Name")
         biotype = draft.pick_attribute("gene_biotype", "biotype", "gene_type")
         if name is None or biotype is None:
             return feature
-        return Gene(**feature.__dict__, name=name, biotype=biotype, transcripts=())
+        return type_(**feature.__dict__, name=name, biotype=biotype, transcripts=())
 
-    def _finalize_transcript(self, draft: FeatureDraft, result: Features) -> Feature:
+    def _finalize_transcript(
+        self, draft: FeatureDraft, result: Features, type_: Type[TranscriptT]
+    ) -> Feature:
         feature = self._finalize_other(draft, result)
         if not (gene := self._find_ancestor_of_type(feature, Gene)):
             return feature
-        transcript = Transcript(**feature.__dict__, gene=gene, exons=())
+        transcript = type_(**feature.__dict__, gene=gene, exons=())
         object.__setattr__(gene, "transcripts", gene.transcripts + (transcript,))
         return transcript
 
@@ -148,25 +165,21 @@ class FeatureReader(Reader):
         object.__setattr__(transcript, "exons", transcript.exons + (exon,))
         return exon
 
-    UTRT = TypeVar("UTRT", bound=UTR)
-
     def _finalize_utr(
         self, draft: FeatureDraft, result: Features, type_: Type[UTRT]
-    ) -> Feature | UTRT:
+    ) -> Feature:
         feature = self._finalize_other(draft, result)
         if not (transcript := self._find_ancestor_of_type(feature, Transcript)):
             return feature
         return type_(**feature.__dict__, gene=transcript.gene, transcript=transcript)
 
-    FeatureT = TypeVar("FeatureT", bound=Feature)
-
     def _find_ancestor_of_type(
         self, feature: Feature, t: Type[FeatureT]
     ) -> FeatureT | None:
         ancestor = feature.parent
         while ancestor and not isinstance(ancestor, t):
             ancestor = ancestor.parent
-        return ancestor
+        return cast(FeatureT | None, ancestor)
 
     def _finalize_other(self, draft: FeatureDraft, result: Features) -> Feature:
         parent_id = self._extract_parent_id(draft)

biofiles/gff.py

@@ -148,7 +148,7 @@ if __name__ == "__main__":
             parsed_utrs = 0
             for feature in r:
                 total_features += 1
-                annotated_genes += feature.type_ == "gene"
+                annotated_genes += "gene" in feature.type_.lower()
                 annotated_exons += feature.type_ == "exon"
                 annotated_utrs += "utr" in feature.type_.lower()
                 parsed_genes += isinstance(feature, Gene)

biofiles/gtf.py

@@ -31,7 +31,7 @@ if __name__ == "__main__":
             parsed_utrs = 0
             for feature in r:
                 total_features += 1
-                annotated_genes += feature.type_ == "gene"
+                annotated_genes += "gene" in feature.type_.lower()
                 annotated_exons += feature.type_ == "exon"
                 annotated_utrs += "utr" in feature.type_.lower()
                 parsed_genes += isinstance(feature, Gene)

biofiles/repeatmasker.py

@@ -1,6 +1,6 @@
 import sys
 from collections import Counter
-from typing import Iterator
+from typing import Iterator, cast, Literal
 
 from biofiles.common import Reader
 from biofiles.types.repeat import Repeat
@@ -42,7 +42,7 @@ class RepeatMaskerReader(Reader):
             seq_start = int(seq_start_str)
             seq_end = int(seq_end_str)
             seq_left = int(seq_left_str[1:-1])
-            strand = {"+": "+", "C": "-"}[strand_str]
+            strand = cast(Literal["+", "-"], {"+": "+", "C": "-"}[strand_str])
 
             if "/" in repeat_class_family:
                 repeat_class, repeat_family = repeat_class_family.split("/", 1)

biofiles/types/feature.py

@@ -26,7 +26,7 @@ class Feature:
     attributes: dict[str, str]
 
     id: str | None
-    parent: "GFFFeature | None"
+    parent: "Feature | None"
     children: tuple["Feature", ...]
 
 
@@ -50,7 +50,6 @@ class Transcript(Feature):
 class Exon(Feature):
     gene: Gene
     transcript: Transcript
-    # TODO mRNA
 
 
 @dataclass(frozen=True)

{biofiles-0.0.8.dist-info → biofiles-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: biofiles
-Version: 0.0.8
+Version: 0.0.9
 Summary: Pure-Python, zero-dependency collection of bioinformatics-related file readers and writers
 Author-email: Tigran Saluev <tigran@saluev.com>
 Maintainer-email: Tigran Saluev <tigran@saluev.com>

biofiles-0.0.9.dist-info/RECORD

@@ -0,0 +1,16 @@
+biofiles/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+biofiles/common.py,sha256=Yi0i85FpD2wR3vqL645LTUAE6TybGDxxZQsUmEGHqu4,1126
+biofiles/fasta.py,sha256=ctIt5I_fcZx-xQN921zpmlZS7e9_ICf-3_i6mTs5qbs,2135
+biofiles/feature.py,sha256=tUTn16xV1e0qpgkZ1ZwQ4LJJGil5mgQJBJ9s1yFDgiI,8068
+biofiles/gff.py,sha256=6xmwnuU1CsFibIHzbggYJajzQC4KGsGAfWMxyYFFChw,5798
+biofiles/gtf.py,sha256=kAt_5ifb0f8cCR-kycnQhkyo78xOynqTUUGqgOP8tjA,1543
+biofiles/repeatmasker.py,sha256=txOYdw15ru88pUczsk0pDFzgGpplLu23CB8Ppz-MczY,3119
+biofiles/types/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+biofiles/types/feature.py,sha256=3Ar45WRgiaDSh5iQt24Emtk6_57G01q5nHJ1GNIJ19Y,1190
+biofiles/types/repeat.py,sha256=63SqzAwEGIDIGP9pxC85RUdwXbbSm0S5WNL3lSiWlmc,641
+biofiles/types/sequence.py,sha256=EOw_oKuMR0THpCYJqVE__27z7qrRqcdIPrRWTL4OFMw,152
+biofiles-0.0.9.dist-info/LICENSE,sha256=CbR8ssdFyViKj25JAlMjIt1_FbiZ1tAC5t-uwUbxqak,1070
+biofiles-0.0.9.dist-info/METADATA,sha256=gLu3ufoag4tZllgq9xCDZe_kA24RXuI4TqQdAI_QIKw,3033
+biofiles-0.0.9.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+biofiles-0.0.9.dist-info/top_level.txt,sha256=laFaFv8hpkI4U-Pgs0yBaAJXN2_CJKl7jb-m3-tGfSc,9
+biofiles-0.0.9.dist-info/RECORD,,

biofiles-0.0.8.dist-info/RECORD

@@ -1,16 +0,0 @@
-biofiles/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-biofiles/common.py,sha256=Yi0i85FpD2wR3vqL645LTUAE6TybGDxxZQsUmEGHqu4,1126
-biofiles/fasta.py,sha256=ctIt5I_fcZx-xQN921zpmlZS7e9_ICf-3_i6mTs5qbs,2135
-biofiles/feature.py,sha256=oZKNkZrCJjg4-AutGy3rri0gq-FRyo7vLwUzYG1EY7g,7809
-biofiles/gff.py,sha256=LIbHGkpSTo-iMeatt2opPFlpNs8tHyv9XHPIVwzh3m8,5790
-biofiles/gtf.py,sha256=eQsnpTjDaxrBeQ8uHzXy6C6sj8OvenFv9zwkFlytQYM,1535
-biofiles/repeatmasker.py,sha256=DqD1z1hUfCP4-qnfjF-oMF-ZpW_6XhOf_nzA8VHhQbw,3079
-biofiles/types/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-biofiles/types/feature.py,sha256=N6IIip7YqtSib5w_VLX1cBVwja8iWfa5AJncsKBs1PU,1209
-biofiles/types/repeat.py,sha256=63SqzAwEGIDIGP9pxC85RUdwXbbSm0S5WNL3lSiWlmc,641
-biofiles/types/sequence.py,sha256=EOw_oKuMR0THpCYJqVE__27z7qrRqcdIPrRWTL4OFMw,152
-biofiles-0.0.8.dist-info/LICENSE,sha256=CbR8ssdFyViKj25JAlMjIt1_FbiZ1tAC5t-uwUbxqak,1070
-biofiles-0.0.8.dist-info/METADATA,sha256=B0rgF4FGa2lgMehk6LdOEhHB2jddaoc76fteG3p4dp0,3033
-biofiles-0.0.8.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-biofiles-0.0.8.dist-info/top_level.txt,sha256=laFaFv8hpkI4U-Pgs0yBaAJXN2_CJKl7jb-m3-tGfSc,9
-biofiles-0.0.8.dist-info/RECORD,,