biofiles 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

biofiles/feature.py

@@ -1,10 +1,10 @@
 from collections import deque
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Iterator, TextIO
+from typing import Iterator, TextIO, Type, TypeVar
 
 from biofiles.common import Reader, Strand
-from biofiles.types.feature import Feature, Gene, ThreePrimeUTR, Exon
+from biofiles.types.feature import Feature, Gene, ThreePrimeUTR, Exon, UTR, Transcript
 
 
 @dataclass
@@ -67,6 +67,9 @@ class FeatureReader(Reader):
         super().__init__(input_)
         self._streaming_window = streaming_window
 
+    def __iter__(self) -> Iterator[Feature]:
+        raise NotImplementedError
+
     def _finalize_drafts(
         self, drafts: FeatureDrafts, w: int | None
     ) -> Iterator[Feature]:
@@ -106,10 +109,14 @@ class FeatureReader(Reader):
         match draft.type_.lower():
             case "gene":
                 feature = self._finalize_gene(draft, result)
+            case "transcript":
+                feature = self._finalize_transcript(draft, result)
             case "exon":
                 feature = self._finalize_exon(draft, result)
             case "three_prime_utr":
-                feature = self._finalize_three_prime_utr(draft, result)
+                feature = self._finalize_utr(draft, result, ThreePrimeUTR)
+            case "utr":
+                feature = self._finalize_utr(draft, result, UTR)
             case _:
                 feature = self._finalize_other(draft, result)
         if feature.parent:
@@ -123,33 +130,43 @@ class FeatureReader(Reader):
         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 Gene(**feature.__dict__, name=name, biotype=biotype, transcripts=())
 
-    def _finalize_exon(self, draft: FeatureDraft, result: Features) -> Feature:
+    def _finalize_transcript(self, draft: FeatureDraft, result: Features) -> 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=())
+        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_three_prime_utr(
-        self, draft: FeatureDraft, result: Features
-    ) -> Feature:
+    UTRT = TypeVar("UTRT", bound=UTR)
+
+    def _finalize_utr(
+        self, draft: FeatureDraft, result: Features, type_: Type[UTRT]
+    ) -> Feature | UTRT:
         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)
 
-        gene = feature.parent
-        while gene and not isinstance(gene, Gene):
-            gene = gene.parent
+    FeatureT = TypeVar("FeatureT", bound=Feature)
 
-        if gene is None:
-            return feature
-        return ThreePrimeUTR(**feature.__dict__, gene=gene)
+    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
 
     def _finalize_other(self, draft: FeatureDraft, result: Features) -> Feature:
         parent_id = self._extract_parent_id(draft)
@@ -188,6 +205,8 @@ 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/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"]
 
@@ -122,8 +122,8 @@ class GFF3Writer(Writer):
             feature.sequence_id,
             feature.source,
             feature.type_,
-            str(feature.start_original),
-            str(feature.end_original),
+            str(feature.start_c + 1),
+            str(feature.end_c),
             str(feature.score) if feature.score is not None else ".",
             str(feature.strand) if feature.strand is not None else ".",
             str(feature.phase) if feature.phase is not None else ".",
@@ -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_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/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_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/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)
@@ -14,7 +14,7 @@ class Feature:
 
     start_original: int
     end_original: int
-    # Original, 1-based inclusive values.
+    # Original values as they were present in the file (1-based inclusive for .gff and .gtf).
 
     start_c: int
     end_c: int
@@ -37,16 +37,28 @@ 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
+    # TODO mRNA
 
 
 @dataclass(frozen=True)
-class ThreePrimeUTR(Feature):
+class UTR(Feature):
     gene: Gene
-    # TODO transcript
+    transcript: Transcript
+
+
+@dataclass(frozen=True)
+class ThreePrimeUTR(UTR):
+    pass

{biofiles-0.0.6.dist-info → biofiles-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: biofiles
-Version: 0.0.6
+Version: 0.0.8
 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-0.0.6.dist-info → biofiles-0.0.8.dist-info}/RECORD

@@ -1,16 +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=4eRXmusxTbrDqkwPkMKaa1nYRSSYvt3Y3_-7jC7rkII,6693
-biofiles/gff.py,sha256=TwBasmakNmeS5yikP-E5iMEvB6BXgczGYQKiGa2_LAw,5516
-biofiles/gtf.py,sha256=hWfjQjzwsrXLjCGr9ia6GdHNdYtlwkBrG1ldJYhRD-4,1251
+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=PyxIkbpWLcboY8cGEcJBn6sWv5wIFgOyD9Ey5D2G3JQ,938
+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-0.0.6.dist-info/LICENSE,sha256=CbR8ssdFyViKj25JAlMjIt1_FbiZ1tAC5t-uwUbxqak,1070
-biofiles-0.0.6.dist-info/METADATA,sha256=vbIWtDF_yHm-qV8EKlCiKQzjajnoIZdV0RWZJoS0zh0,3033
-biofiles-0.0.6.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-biofiles-0.0.6.dist-info/top_level.txt,sha256=laFaFv8hpkI4U-Pgs0yBaAJXN2_CJKl7jb-m3-tGfSc,9
-biofiles-0.0.6.dist-info/RECORD,,
+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,,