biofiles 0.0.7__tar.gz → 0.0.9__tar.gz

{biofiles-0.0.7 → biofiles-0.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: biofiles
-Version: 0.0.7
+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-0.0.7 → biofiles-0.0.9}/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
+from typing import Iterator, TextIO, Type, TypeVar, cast
 
 from biofiles.common import Reader, Strand
-from biofiles.types.feature import Feature, Gene, ThreePrimeUTR, Exon, UTR
+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
@@ -107,8 +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 "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":
@@ -122,39 +137,49 @@ 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, exons=())
+        return type_(**feature.__dict__, name=name, biotype=biotype, transcripts=())
 
-    def _finalize_exon(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 = type_(**feature.__dict__, gene=gene, exons=())
+        object.__setattr__(gene, "transcripts", gene.transcripts + (transcript,))
+        return transcript
 
-        gene = feature.parent
-        while gene and not isinstance(gene, Gene):
-            gene = gene.parent
-
-        if gene is None:
+    def _finalize_exon(self, draft: FeatureDraft, result: Features) -> Feature:
+        feature = self._finalize_other(draft, result)
+        if not (transcript := self._find_ancestor_of_type(feature, Transcript)):
             return feature
-        exon = Exon(**feature.__dict__, gene=gene)
-        object.__setattr__(gene, "exons", gene.exons + (exon,))
+        exon = Exon(**feature.__dict__, gene=transcript.gene, transcript=transcript)
+        object.__setattr__(transcript, "exons", transcript.exons + (exon,))
         return exon
 
     def _finalize_utr(
-        self, draft: FeatureDraft, result: Features, type_: Type[UTR]
+        self, draft: FeatureDraft, result: Features, type_: Type[UTRT]
     ) -> Feature:
         feature = self._finalize_other(draft, result)
-
-        gene = feature.parent
-        while gene and not isinstance(gene, Gene):
-            gene = gene.parent
-
-        if gene is None:
+        if not (transcript := self._find_ancestor_of_type(feature, Transcript)):
             return feature
-        return type_(**feature.__dict__, gene=gene)
+        return type_(**feature.__dict__, gene=transcript.gene, transcript=transcript)
+
+    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 cast(FeatureT | None, ancestor)
 
     def _finalize_other(self, draft: FeatureDraft, result: Features) -> Feature:
         parent_id = self._extract_parent_id(draft)
@@ -193,6 +218,8 @@ class FeatureReader(Reader):
             return id_
         if draft.type_ == "transcript" and (id_ := draft.attributes.get("gene_id")):
             return id_
-        if draft.type_ == "exon" and (id_ := draft.attributes.get("transcript_id")):
+        if draft.type_ in ("exon", "UTR", "three_prime_UTR", "five_prime_UTR") and (
+            id_ := draft.attributes.get("transcript_id")
+        ):
             return id_
         return None

{biofiles-0.0.7 → biofiles-0.0.9}/biofiles/gff.py

@@ -4,7 +4,7 @@ from typing import Iterator, cast, TextIO
 
 from biofiles.common import Strand, Writer
 from biofiles.feature import FeatureReader, FeatureDraft, FeatureDrafts
-from biofiles.types.feature import Feature, Gene, Exon
+from biofiles.types.feature import Feature, Gene, Exon, UTR
 
 __all__ = ["GFFReader", "GFF3Writer"]
 
@@ -142,14 +142,21 @@ if __name__ == "__main__":
             total_features = 0
             annotated_genes = 0
             annotated_exons = 0
+            annotated_utrs = 0
             parsed_genes = 0
             parsed_exons = 0
+            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)
                 parsed_exons += isinstance(feature, Exon)
+                parsed_utrs += isinstance(feature, UTR)
         print(
-            f"{path}: {total_features} features, {parsed_genes} genes parsed out of {annotated_genes}, {parsed_exons} exons parsed out of {annotated_exons}"
+            f"{path}: {total_features} features, "
+            f"{parsed_genes} genes parsed out of {annotated_genes}, "
+            f"{parsed_exons} exons parsed out of {annotated_exons}, "
+            f"{parsed_utrs} UTRs parsed out of {annotated_utrs}"
         )

{biofiles-0.0.7 → biofiles-0.0.9}/biofiles/gtf.py

@@ -4,7 +4,7 @@ import sys
 from typing import Iterator
 
 from biofiles.gff import GFFReader
-from biofiles.types.feature import Gene, Exon, Feature
+from biofiles.types.feature import Gene, Exon, Feature, UTR
 
 
 class GTFReader(GFFReader):
@@ -25,14 +25,21 @@ if __name__ == "__main__":
             total_features = 0
             annotated_genes = 0
             annotated_exons = 0
+            annotated_utrs = 0
             parsed_genes = 0
             parsed_exons = 0
+            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)
                 parsed_exons += isinstance(feature, Exon)
+                parsed_utrs += isinstance(feature, UTR)
         print(
-            f"{path}: {total_features} features, {parsed_genes} genes parsed out of {annotated_genes}, {parsed_exons} exons parsed out of {annotated_exons}"
+            f"{path}: {total_features} features, "
+            f"{parsed_genes} genes parsed out of {annotated_genes}, "
+            f"{parsed_exons} exons parsed out of {annotated_exons}, "
+            f"{parsed_utrs} UTRs parsed out of {annotated_utrs}"
         )

{biofiles-0.0.7 → biofiles-0.0.9}/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-0.0.7 → biofiles-0.0.9}/biofiles/types/feature.py

@@ -3,7 +3,7 @@ from dataclasses import dataclass
 from biofiles.common import Strand
 
 
-__all__ = ["Feature", "Gene", "Exon"]
+__all__ = ["Feature", "Gene", "Transcript", "Exon", "UTR", "ThreePrimeUTR"]
 
 
 @dataclass(frozen=True)
@@ -26,7 +26,7 @@ class Feature:
     attributes: dict[str, str]
 
     id: str | None
-    parent: "GFFFeature | None"
+    parent: "Feature | None"
     children: tuple["Feature", ...]
 
 
@@ -37,19 +37,25 @@ class Feature:
 class Gene(Feature):
     name: str
     biotype: str
+    transcripts: tuple["Transcript", ...]
+
+
+@dataclass(frozen=True)
+class Transcript(Feature):
+    gene: Gene
     exons: tuple["Exon", ...]
 
 
 @dataclass(frozen=True)
 class Exon(Feature):
     gene: Gene
-    # TODO transcript, mRNA
+    transcript: Transcript
 
 
 @dataclass(frozen=True)
 class UTR(Feature):
     gene: Gene
-    # TODO transcript
+    transcript: Transcript
 
 
 @dataclass(frozen=True)

{biofiles-0.0.7 → biofiles-0.0.9}/biofiles.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: biofiles
-Version: 0.0.7
+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-0.0.7 → biofiles-0.0.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "biofiles"
-version = "0.0.7"
+version = "0.0.9"
 authors = [
   { name="Tigran Saluev", email="tigran@saluev.com" },
 ]