GTF attribute values can contain spaces

yhoogstrate · Apr 3, 2024 · 305a724 · 305a724
1 parent 7a79fc2
commit 305a724
Show file tree

Hide file tree

Showing 4 changed files with 7 additions and 1 deletion.
diff --git a/bin/fuma-gencode-gtf-to-bed b/bin/fuma-gencode-gtf-to-bed
@@ -26,7 +26,10 @@ def attribute_to_dict(line):
 		# The last 'field' is empty, as GTF lines are ; terminated
 		if not entry:
 			continue
-		key, value = entry.split()
+		# value can contain spaces
+		key, *value = entry.split()
+		# Put spaces back into value
+		value = ' '.join(value)
 		data[key] = value.replace('"','')
 	return data
 

diff --git a/tests/data/gencode_hg19.subset.bed b/tests/data/gencode_hg19.subset.bed
@@ -5,6 +5,7 @@ chr1	30266	31109	ENSG00000243485.2
 chr1	30365	30503	ENSG00000243485.2
 chr1	34553	36081	ENSG00000237613.2
 chr1	35244	36073	ENSG00000237613.2
+chr1	685678	686673	ENSG00000284662
 chr1	69090	70008	ENSG00000186092.4
 chr1	89294	120932	ENSG00000238009.2
 chr1	92229	129217	ENSG00000238009.2
diff --git a/tests/data/gencode_hg19.subset.gtf b/tests/data/gencode_hg19.subset.gtf
@@ -26,3 +26,4 @@ chr1	HAVANA	exon	110953	111357	.	-	.	gene_id "ENSG00000238009.2"; transcript_id
 chr1	HAVANA	exon	133374	133566	.	-	.	gene_id "ENSG00000238009.2"; transcript_id "ENST00000453576.2"; gene_type "lincRNA"; gene_status "NOVEL"; gene_name "RP11-34P13.7"; transcript_type "lincRNA"; transcript_status "KNOWN"; transcript_name "RP11-34P13.7-004"; exon_number 1;  exon_id "ENSE00001737600.2";  level 2; havana_gene "OTTHUMG00000001096.2"; havana_transcript "OTTHUMT00000003689.1";
 chr1	HAVANA	exon	129081	129223	.	-	.	gene_id "ENSG00000238009.2"; transcript_id "ENST00000453576.2"; gene_type "lincRNA"; gene_status "NOVEL"; gene_name "RP11-34P13.7"; transcript_type "lincRNA"; transcript_status "KNOWN"; transcript_name "RP11-34P13.7-004"; exon_number 2;  exon_id "ENSE00001827073.1";  level 2; havana_gene "OTTHUMG00000001096.2"; havana_transcript "OTTHUMT00000003689.1";
 chr1	HAVANA	gene	11869	14409	.	+	.	gene_id "ENSG00000223972.5"; gene_type "transcribed_unprocessed_pseudogene"; gene_name "DDX11L1"; level 2; hgnc_id "HGNC:37102"; havana_gene "OTTHUMG00000000961.2";
+chr1	ensembl_havana	transcript	685679	686673	.	-	.	gene_id "ENSG00000284662"; gene_version "1"; transcript_id "ENST00000332831"; transcript_version "4"; gene_name "OR4F16"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "OR4F16-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS41221"; tag "basic"; transcript_support_level "NA (assigned to previous version 3)";
diff --git a/tests/data/gencode_hg19.subset.sorted.bed b/tests/data/gencode_hg19.subset.sorted.bed
@@ -8,3 +8,4 @@ chr1	89294	120932	ENSG00000238009.2
 chr1	92229	129217	ENSG00000238009.2
 chr1	110952	129173	ENSG00000238009.2
 chr1	129080	133566	ENSG00000238009.2
+chr1	685678	686673	ENSG00000284662