fix (gtf): check added when converting a genomic location to gene coo…

…rdinate to ensure they overlap

CHANGELOG.md

@@ -22,6 +22,10 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 - Fixed callVariant that peptide annotation not created correctly with SEC
 
+## Changed
+
+- A check added when converting a genomic location to gene coordinate to ensure they overlap.
+
 ## [1.4.6-rc1] - 2025-02-24
 
 ### Fixed

moPepGen/gtf/GenomicAnnotation.py

@@ -179,6 +179,12 @@ def coordinate_gene_to_transcript(self, index:int, gene:str,
     def coordinate_genomic_to_gene(self, index:int, gene:str) -> int:
         """ Get the gene coordinate from genomic coordinate. """
         gene_location = self.genes[gene].location
+        if not gene_location.start <= index < gene_location.end:
+            loc = f"{self.genes[gene].chrom}:{gene_location.start}-{gene_location.end}"
+            raise ValueError(
+                f"The position does not overlap with the gene. index: {index}, "
+                f"gene: {gene}, {loc}"
+            )
         if gene_location.strand == 1:
             return index - gene_location.start
         if gene_location.strand == -1:

test/files/circRNA/CIRCexplorer3_circularRNA_known.txt

@@ -1,3 +1,3 @@
 chr22	0	464	circular_RNA/1	0	+	0	0	0,0,0	2	323,82	0,323	1	circRNA	RIBC2	ENST00000614167.2	1,2	chr22:0-130787|chr22:131505-160911	1	1	1
-chr22	4980	5177	circular_RNA/1	0	-	4980	4980	0,0,0	2	78,42	0,98	1	circRNA	LZTR1	ENST00000642151.1	1,2	chr22:427119-435769|chr22:437511-472574	1	1	1
+chr22	4980	5120	circular_RNA/1	0	-	4980	4980	0,0,0	2	78,42	0,98	1	circRNA	LZTR1	ENST00000642151.1	1,2	chr22:427119-435769|chr22:437511-472574	1	1	1
 chr22	5058	5078	circular_RNA/2	0	-	5058	5058	0,0,0	1	20	0	2	ciRNA	LZTR1	ENST00000642151.1	1	chr22:868685-870710|chr22:884086-888846	1	1	1

test/files/circRNA/CIRCexplorer_circularRNA_known.txt

@@ -1,3 +1,3 @@
 chr22	0	464	circular_RNA/1	0	+	0	0	0,0,0	2	323,82	0,323	1	circRNA	RIBC2	ENST00000614167.2	1,2	chr22:0-130787|chr22:131505-160911
-chr22	4980	5177	circular_RNA/1	0	-	4980	4980	0,0,0	2	78,42	0,98	1	circRNA	LZTR1	ENST00000642151.1	1,2	chr22:427119-435769|chr22:437511-472574
+chr22	4980	5120	circular_RNA/1	0	-	4980	4980	0,0,0	2	78,42	0,98	1	circRNA	LZTR1	ENST00000642151.1	1,2	chr22:427119-435769|chr22:437511-472574
 chr22	5058	5078	circular_RNA/2	0	-	5058	5058	0,0,0	1	20	0	2	ciRNA	LZTR1	ENST00000642151.1	1	chr22:868685-870710|chr22:884086-888846

test/unit/test_gtf.py

@@ -445,6 +445,13 @@ def test_coordinate_convert(self):
         x = anno.coordinate_gene_to_transcript(19, gene_id, tx_id)
         self.assertEqual(x, 10)
 
+        anno = create_genomic_annotation(ANNOTATION_DATA)
+        gene_id = ANNOTATION_ATTRS[0]['gene_id']
+        tx_id = ANNOTATION_DATA['genes'][0]['transcripts'][0]
+        with self.assertRaises(ValueError):
+            ## This gene is 0-40, so 50 is out of the gene.
+            anno.coordinate_gene_to_transcript(50, gene_id, tx_id)
+
     def test_coordinate_convert_tx_exon_start(self):
         """ Convert coodinate from transcript to genomic when the index is the
         start of an exon"""

test/unit/test_vep_parser.py

@@ -325,7 +325,7 @@ def test_vep_to_variant_record_case11(self):
 
         vep_record = VEPParser.VEPRecord(
             uploaded_variation='rs55971985',
-            location='chr1:38-50',
+            location='chr1:38-40',
             allele='-',
             gene='ENSG0001',
             feature='ENST0001.1',
@@ -437,7 +437,7 @@ def test_vep_to_variant_record_case15(self):
 
         vep_record = VEPParser.VEPRecord(
             uploaded_variation='rs55971985',
-            location='chr1:2-7',
+            location='chr1:6-7',
             allele='-',
             gene='ENSG0001',
             feature='ENST0001.1',