Support for conversion from tags using localized alleles (e.g. LPL, LAD)

pd3 · pd3 · commit 466ceaebdd98 · 2024-04-03T16:13:43.000+01:00
diff --git a/NEWS b/NEWS
@@ -68,6 +68,11 @@ Changes affecting specific commands:
       printing "Requested allele outside valid range". This is now fixed by taking into account
       the actual number of ALT alleles.
 
+* bcftools +tag2tag
+
+    - Support for conversion from tags using localized alleles (e.g. LPL, LAD) to the family of
+      standard tags (PL, AD)
+
 * bcftools +trio-dnm2
 
     - Extend --strictly-novel to exclude cases where the non-Mendelian allele
diff --git a/doc/bcftools.txt b/doc/bcftools.txt
@@ -2861,7 +2861,8 @@ By default, appropriate system directories are searched for installed plugins.
     <http://samtools.github.io/bcftools/howtos/plugin.split-vep.html> for more.
 
 *tag2tag*::
-    Convert between similar tags, such as GL,PL,GP or QR,QA,QS.
+    Convert between similar tags, such as GL,PL,GP or QR,QA,QS or tags with localized alleles e.g. LPL,LAD.
+    See <http://samtools.github.io/bcftools/howtos/plugin.tag2tag.html> for more.
 
 *trio-dnm2*::
     screen variants for possible de-novo mutations in trios
diff --git a/plugins/tag2tag.c b/plugins/tag2tag.c
diff --git a/test/tag2tag.LPL.1.1.vcf b/test/tag2tag.LPL.1.1.vcf
@@ -0,0 +1,15 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=LAD,Number=.,Type=Integer,Description="Localized field: Allelic Depths">
+##FORMAT=<ID=LPL,Number=.,Type=Integer,Description="Local normalized, Phred-scaled likelihoods for genotypes as in original gVCF (without allele reordering)">
+##FORMAT=<ID=LAA,Number=.,Type=Integer,Description="Mapping of alt allele index from original gVCF to msVCF, comma-separated, 1-based (each value is the allele index in the msVCF)">
+##contig=<ID=chr,length=123456>
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Phred-scaled genotype likelihoods">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	smpl1	smpl2
+chr	1	.	A	C,G	.	.	.	GT:LAD:LPL:LAA:AD:PL	0/0:31:0:.:31,.,.:0,.,.,.,.,.	0/1:17,16:86,0,57:1:17,16,.:86,0,57,.,.,.
+chr	2	.	G	A,T	.	.	.	GT:LAD:LPL:LAA:AD:PL	0/2:13,12:82,0,55:2:13,.,12:82,.,.,0,.,55	0/0:34:0:.:34,.,.:0,.,.,.,.,.
+chr	3	.	T	G	.	.	.	GT:LAD:LPL:LAA:AD:PL	0/0:29:0:.:29,.:0,.,.	0/1:13,8:81,0,53:1:13,8:81,0,53
+chr	4	.	A	C	.	.	.	GT:LAD:LPL:LAA:AD:PL	1/1:0,27:88,61,0:1:0,27:88,61,0	0/1:18,19:85,0,52:1:18,19:85,0,52
+chr	5	.	T	TA,TAA,TAAA,TAAAA,TAAAAA,TAAAAAA,TAAAAAAA	.	.	.	GT:LAD:LPL:LAA:AD:PL	5/2:0,8,13:305,339,82,220,0,61:5,2:0,.,13,.,.,8,.,.:305,.,.,220,.,61,.,.,0,.,.,.,.,.,.,339,.,.,.,.,82,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.	2/2:0,25:90,56,0:2:0,.,25,.,.,.,.,.:90,.,.,56,.,0,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.
diff --git a/test/tag2tag.LPL.1.2.vcf b/test/tag2tag.LPL.1.2.vcf
@@ -0,0 +1,12 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##contig=<ID=chr,length=123456>
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Phred-scaled genotype likelihoods">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	smpl1	smpl2
+chr	1	.	A	C,G	.	.	.	GT:AD:PL	0/0:31,.,.:0,.,.,.,.,.	0/1:17,16,.:86,0,57,.,.,.
+chr	2	.	G	A,T	.	.	.	GT:AD:PL	0/2:13,.,12:82,.,.,0,.,55	0/0:34,.,.:0,.,.,.,.,.
+chr	3	.	T	G	.	.	.	GT:AD:PL	0/0:29,.:0,.,.	0/1:13,8:81,0,53
+chr	4	.	A	C	.	.	.	GT:AD:PL	1/1:0,27:88,61,0	0/1:18,19:85,0,52
+chr	5	.	T	TA,TAA,TAAA,TAAAA,TAAAAA,TAAAAAA,TAAAAAAA	.	.	.	GT:AD:PL	5/2:0,.,13,.,.,8,.,.:305,.,.,220,.,61,.,.,0,.,.,.,.,.,.,339,.,.,.,.,82,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.	2/2:0,.,25,.,.,.,.,.:90,.,.,56,.,0,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.
diff --git a/test/tag2tag.LPL.1.3.vcf b/test/tag2tag.LPL.1.3.vcf
@@ -0,0 +1,15 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=LAD,Number=.,Type=Integer,Description="Localized field: Allelic Depths">
+##FORMAT=<ID=LPL,Number=.,Type=Integer,Description="Local normalized, Phred-scaled likelihoods for genotypes as in original gVCF (without allele reordering)">
+##FORMAT=<ID=LAA,Number=.,Type=Integer,Description="Mapping of alt allele index from original gVCF to msVCF, comma-separated, 1-based (each value is the allele index in the msVCF)">
+##contig=<ID=chr,length=123456>
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Phred-scaled genotype likelihoods">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	smpl1	smpl2
+chr	1	.	A	C,G	.	.	.	GT:AD:PL	0/0:31,0,0:0,255,255,255,255,255	0/1:17,16,0:86,0,57,255,255,255
+chr	2	.	G	A,T	.	.	.	GT:AD:PL	0/2:13,0,12:82,255,255,0,255,55	0/0:34,0,0:0,255,255,255,255,255
+chr	3	.	T	G	.	.	.	GT:AD:PL	0/0:29,0:0,255,255	0/1:13,8:81,0,53
+chr	4	.	A	C	.	.	.	GT:AD:PL	1/1:0,27:88,61,0	0/1:18,19:85,0,52
+chr	5	.	T	TA,TAA,TAAA,TAAAA,TAAAAA,TAAAAAA,TAAAAAAA	.	.	.	GT:LAD:LPL:LAA	5/2:0,8,13:305,339,82,220,0,61:5,2	2/2:0,25:90,56,0:2
diff --git a/test/tag2tag.LPL.1.vcf b/test/tag2tag.LPL.1.vcf
@@ -0,0 +1,12 @@
+##fileformat=VCFv4.2
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=LAD,Number=.,Type=Integer,Description="Localized field: Allelic Depths">
+##FORMAT=<ID=LPL,Number=.,Type=Integer,Description="Local normalized, Phred-scaled likelihoods for genotypes as in original gVCF (without allele reordering)">
+##FORMAT=<ID=LAA,Number=.,Type=Integer,Description="Mapping of alt allele index from original gVCF to msVCF, comma-separated, 1-based (each value is the allele index in the msVCF)">
+##contig=<ID=chr,length=123456>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	smpl1	smpl2
+chr	1	.	A	C,G	.	.	.	GT:LAD:LPL:LAA	0/0:31:0:.	0/1:17,16:86,0,57:1
+chr	2	.	G	A,T	.	.	.	GT:LAD:LPL:LAA	0/2:13,12:82,0,55:2	0/0:34:0:.
+chr	3	.	T	G	.	.	.	GT:LAD:LPL:LAA	0/0:29:0:.	0/1:13,8:81,0,53:1
+chr	4	.	A	C	.	.	.	GT:LAD:LPL:LAA	1/1:0,27:88,61,0:1	0/1:18,19:85,0,52:1
+chr	5	.	T	TA,TAA,TAAA,TAAAA,TAAAAA,TAAAAAA,TAAAAAAA	.	.	.	GT:LAD:LPL:LAA	5/2:0,8,13:305,339,82,220,0,61:5,2	2/2:0,25:90,56,0:2
diff --git a/test/test.pl b/test/test.pl
@@ -608,6 +608,9 @@
 run_test(\&test_vcf_plugin,$opts,in=>'view.GL',out=>'view.PL.vcf',cmd=>'+tag2tag --no-version',args=>'-- -r --gl-to-pl');
 run_test(\&test_vcf_plugin,$opts,in=>'view.GL',out=>'view.GL-GP.vcf',cmd=>'+tag2tag --no-version',args=>'-- --gl-to-gp');
 run_test(\&test_vcf_plugin,$opts,in=>'view.GP',out=>'view.GT.vcf',cmd=>'+tag2tag --no-version',args=>'-- -r --gp-to-gt -t 0.2');
+run_test(\&test_vcf_plugin,$opts,in=>'tag2tag.LPL.1',out=>'tag2tag.LPL.1.1.vcf',cmd=>'+tag2tag --no-version',args=>'-- --LXX-to-XX');
+run_test(\&test_vcf_plugin,$opts,in=>'tag2tag.LPL.1',out=>'tag2tag.LPL.1.2.vcf',cmd=>'+tag2tag --no-version',args=>'-- --LXX-to-XX -r');
+run_test(\&test_vcf_plugin,$opts,in=>'tag2tag.LPL.1',out=>'tag2tag.LPL.1.3.vcf',cmd=>'+tag2tag --no-version',args=>'-- --LXX-to-XX -r -d AD:0,PL:255 -s 3');
 run_test(\&test_vcf_plugin,$opts,in=>'query.variantkey',out=>'query.add-variantkey.vcf',cmd=>'+add-variantkey',args=>'');
 run_test(\&test_vcf_plugin,$opts,in=>'query.variantkey',out=>'variantkey-hex.out',cmd=>'+variantkey-hex',args=>'test/');
 run_test(\&test_vcf_plugin,$opts,in=>'query.nucleotide',out=>'query.allele-length.tsv',cmd=>'+allele-length',args=>'');
