Stop printing protein sequence with start_lost events

Remove an unnecessary assert. Fixes samtools#1025 (comment)
davmlaw · Jun 6, 2019 · bb5eedf · bb5eedf
1 parent 2db4c0b
commit bb5eedf
Show file tree

Hide file tree

Showing 10 changed files with 668 additions and 9 deletions.
diff --git a/csq.c b/csq.c
@@ -1826,9 +1826,6 @@ int shifted_del_synonymous(args_t *args, splice_t *splice, uint32_t ex_beg, uint
         int32_t vcf_block_beg = splice->vcf.pos + ref_len - 2*ndel;        // the position of the first base of the ref block that could potentially replace the deletion
         if ( vcf_block_beg < 0 ) return 0;
 
-        if ( !(vcf_block_beg < ex_beg) ) fprintf(stderr,"vcf_pos=%d  ref_len=%d  ndel=%d  ..  vcf_block_beg=%d ?< ex_beg=%d\n",splice->vcf.pos,ref_len,ndel,vcf_block_beg,ex_beg);
-        assert( vcf_block_beg < ex_beg );
-
 #if XDBG
         fprintf(stderr,"vcf_block_beg: %d\n",vcf_block_beg+1);
 #endif
@@ -2185,7 +2182,7 @@ fprintf(stderr,"cds splice_csq: %d [%s][%s] .. beg,end=%d %d, ret=%d, csq=%d\n\n
 #endif
 
     if ( ret==SPLICE_VAR_REF ) return 2;  // not a variant, eg REF=CA ALT=CA
-    if ( ret==SPLICE_OUTSIDE || ret==SPLICE_OVERLAP )  // not a coding csq
+    if ( ret==SPLICE_OUTSIDE || ret==SPLICE_OVERLAP || splice.csq==CSQ_START_LOST )  // not a coding csq
     {
         free(splice.kref.s);
         free(splice.kalt.s);

diff --git a/test/csq/ENST00000230048/ENST00000230048.fa b/test/csq/ENST00000230048/ENST00000230048.fa
diff --git a/test/csq/ENST00000230048/ENST00000230048.fa.fai b/test/csq/ENST00000230048/ENST00000230048.fa.fai
@@ -0,0 +1 @@
+6	38016	23	60	61
diff --git a/test/csq/ENST00000230048/ENST00000230048.gff b/test/csq/ENST00000230048/ENST00000230048.gff
@@ -0,0 +1,8 @@
+6	ensembl_havana	gene	-15	38015	.	+	.	ID=gene:ENSG00000112304;Name=ACOT13;biotype=protein_coding;description=acyl-CoA thioesterase 13 [Source:HGNC Symbol%3BAcc:20999];gene_id=ENSG00000112304;logic_name=ensembl_havana_gene;version=6
+6	ensembl_havana	transcript	21	37996	.	+	.	ID=transcript:ENST00000230048;Parent=gene:ENSG00000112304;Name=ACOT13-001;biotype=protein_coding;ccdsid=CCDS4558.1;havana_transcript=OTTHUMT00000040010;havana_version=2;tag=basic;transcript_id=ENST00000230048;version=4
+6	ensembl_havana	exon	21	294	.	+	.	Parent=transcript:ENST00000230048;Name=ENSE00001174688;constitutive=0;ensembl_end_phase=0;ensembl_phase=-1;exon_id=ENSE00001174688;rank=1;version=3
+6	ensembl_havana	CDS	214	294	.	+	0	ID=CDS:ENSP00000230048;Parent=transcript:ENST00000230048;protein_id=ENSP00000230048
+6	ensembl_havana	exon	30833	31017	.	+	.	Parent=transcript:ENST00000230048;Name=ENSE00003657839;constitutive=0;ensembl_end_phase=2;ensembl_phase=0;exon_id=ENSE00003657839;rank=2;version=1
+6	ensembl_havana	CDS	30833	31017	.	+	0	ID=CDS:ENSP00000230048;Parent=transcript:ENST00000230048;protein_id=ENSP00000230048
+6	ensembl_havana	CDS	34409	34565	.	+	1	ID=CDS:ENSP00000230048;Parent=transcript:ENST00000230048;protein_id=ENSP00000230048
+6	ensembl_havana	exon	34409	37996	.	+	.	Parent=transcript:ENST00000230048;Name=ENSE00003680711;constitutive=0;ensembl_end_phase=-1;ensembl_phase=2;exon_id=ENSE00003680711;rank=3;version=2
diff --git a/test/csq/ENST00000230048/ascii-art.txt b/test/csq/ENST00000230048/ascii-art.txt
@@ -0,0 +1,8 @@
+
+6:214 AT  A
+
+....eeeeeee
+CACGATGACCA
+CACGA-GACCA
+
+
diff --git a/test/csq/ENST00000230048/start-del.txt b/test/csq/ENST00000230048/start-del.txt
@@ -0,0 +1,3 @@
+214	AT	A	start_lost|ACOT13|ENST00000230048|protein_coding|+
+214	AT	A	start_lost|ACOT13|ENST00000230048|protein_coding|+
+
diff --git a/test/csq/ENST00000230048/start-del.vcf b/test/csq/ENST00000230048/start-del.vcf
@@ -0,0 +1,7 @@
+##fileformat=VCFv4.2
+##contig=<ID=6,length=249250621>
+##INFO=<ID=type,Number=.,Type=String,Description="">
+##INFO=<ID=EXP,Number=1,Type=String,Description="Expected consequence">
+##INFO=<ID=EXPL,Number=1,Type=String,Description="Expected consequence with bt/csq -l">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO
+6	214	.	AT	A	.	.	type=ENST00000230048:24667492-AT-A;EXP=start_lost|ACOT13|ENST00000230048|protein_coding|+
diff --git a/test/csq/ENST00000318249/start-lost.txt b/test/csq/ENST00000318249/start-lost.txt
@@ -1,3 +1,3 @@
-4959	GA	G	frameshift&start_lost|NBPF3|ENST00000318249|protein_coding|+|1M>1?|4959GA>G
-4959	GA	G	frameshift&start_lost|NBPF3|ENST00000318249|protein_coding|+|1M>1?|4959GA>G
+4959	GA	G	start_lost|NBPF3|ENST00000318249|protein_coding|+
+4959	GA	G	start_lost|NBPF3|ENST00000318249|protein_coding|+
 
diff --git a/test/csq/ENST00000318249/start-lost.txt-l b/test/csq/ENST00000318249/start-lost.txt-l
@@ -1,3 +1,3 @@
-4959	GA	G	frameshift&start_lost|NBPF3|ENST00000318249|protein_coding|+|1M>1?|4959GA>G
-4959	GA	G	frameshift&start_lost|NBPF3|ENST00000318249|protein_coding|+|1M>1?|4959GA>G
+4959	GA	G	start_lost|NBPF3|ENST00000318249|protein_coding|+
+4959	GA	G	start_lost|NBPF3|ENST00000318249|protein_coding|+
 
diff --git a/test/csq/ENST00000318249/start-lost.vcf b/test/csq/ENST00000318249/start-lost.vcf
@@ -3,4 +3,4 @@
 ##INFO=<ID=type,Number=.,Type=String,Description="">
 ##INFO=<ID=EXP,Number=1,Type=String,Description="Expected consequence">
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO
-1	4959	.	GA	G	.	.	EXP=frameshift&start_lost|NBPF3|ENST00000318249|protein_coding|+|1M>1?|4959GA>G;type=ENST00000318249:21771579-GA-G
+1	4959	.	GA	G	.	.	EXP=start_lost|NBPF3|ENST00000318249|protein_coding|+;type=ENST00000318249:21771579-GA-G
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		214 AT A start_lost\|ACOT13\|ENST00000230048\|protein_coding\|+
		214 AT A start_lost\|ACOT13\|ENST00000230048\|protein_coding\|+