New --ligate-force and --ligate-warn options

for finer control of the `-l, --ligate` behavior in
imperfect overlaps. The new default is to throw an error
when sites present in one chunk but absent in the other
are encountered. To drop such sites and proceed, use
the new `--ligate-warn` option (previously this was the
default). To keep such sites, use the new `--ligate-force`
option.

Resolves #1567

NEWS

@@ -33,6 +33,20 @@
       information carried in the missing and half-missing genotypes
       (e.g. ".", "./." or "./1")
 
+* bcftools concat:
+
+    - new `--ligate-force` and `--ligate-warn` options for finer control
+      of `-l, --ligate` behavior in imperfect overlaps. The new default is
+      to throw an error when sites present in one chunk but absent in the
+      other are encountered. To drop such sites and proceed, use the new
+      `--ligate-warn` option (previously this was the default). To keep such
+      sites, use the new `--ligate-force` option (#1567).
+
+* bcftools +contrast:
+
+    - support for chunking within map/reduce framework allowing to collect
+      NASSOC counts even for empty case/control sample sets (#1566)
+
 * bcftools csq:
 
     - bug fix, compound indels were not recognised in some cases (#1536)

doc/bcftools.txt

@@ -787,7 +787,13 @@ are concatenated without being recompressed, which is very fast..
 *-l, --ligate*::
     Ligate phased VCFs by matching phase at overlapping haplotypes.
     Note that the option is intended for VCFs with perfect overlap, sites
-    in overlapping regions present in one but missing in other are dropped.
+    in overlapping regions present in one but missing in the other are dropped.
+
+*--ligate-force*::
+    Keep all sites and ligate even non-overlapping chunks and chunks with imperfect overlap
+
+*--ligate-warn*::
+    Drop sites in imperfect overlaps
 
 *--no-version*::
     see *<<common_options,Common Options>>*

test/concat.5.1.out

@@ -0,0 +1,10 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##contig=<ID=chr1>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PQ,Number=1,Type=Integer,Description="Phasing Quality (bigger is better)">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phase Set">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	SAMPLE
+chr1	1	.	A	C	.	.	.	GT:PS	0|1:1
+chr1	3	.	G	T	.	.	.	GT:PS	0|1:1
+chr1	4	.	T	A	.	.	.	GT:PS	1|0:1

test/concat.5.2.out

@@ -0,0 +1,11 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##contig=<ID=chr1>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PQ,Number=1,Type=Integer,Description="Phasing Quality (bigger is better)">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phase Set">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	SAMPLE
+chr1	1	.	A	C	.	.	.	GT:PS	0|1:1
+chr1	2	.	C	G	.	.	.	GT:PS	1|0:1
+chr1	3	.	G	T	.	.	.	GT:PQ:PS	0|1:99:1
+chr1	4	.	T	A	.	.	.	GT:PS	1|0:1

test/concat.5.a.vcf

@@ -0,0 +1,5 @@
+##fileformat=VCFv4.2
+##contig=<ID=chr1>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	SAMPLE
+chr1	1	.	A	C	.	.	.	GT	0|1

test/concat.5.b.vcf

@@ -0,0 +1,6 @@
+##fileformat=VCFv4.2
+##contig=<ID=chr1>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	SAMPLE
+chr1	2	.	C	G	.	.	.	GT	1|0
+chr1	3	.	G	T	.	.	.	GT	0|1

test/concat.5.c.vcf

@@ -0,0 +1,6 @@
+##fileformat=VCFv4.2
+##contig=<ID=chr1>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	SAMPLE
+chr1	3	.	G	T	.	.	.	GT	1|0
+chr1	4	.	T	A	.	.	.	GT	0|1

test/test.pl

@@ -601,11 +601,14 @@
 test_vcf_concat($opts,in=>['concat.2.a','concat.2.b'],out=>'concat.2.bcf.out',do_bcf=>1,args=>'-a');
 test_vcf_concat($opts,in=>['concat.2.a','concat.2.b'],out=>'concat.4.vcf.out',do_bcf=>0,args=>'-aD');
 test_vcf_concat($opts,in=>['concat.2.a','concat.2.b'],out=>'concat.4.bcf.out',do_bcf=>1,args=>'-aD');
-test_vcf_concat($opts,in=>['concat.3.a','concat.3.b','concat.3.0','concat.3.c','concat.3.d','concat.3.e','concat.3.f'],out=>'concat.3.vcf.out',do_bcf=>0,args=>'-l');
-test_vcf_concat($opts,in=>['concat.3.a','concat.3.b','concat.3.0','concat.3.c','concat.3.d','concat.3.e','concat.3.f'],out=>'concat.3.bcf.out',do_bcf=>1,args=>'-l');
+test_vcf_concat($opts,in=>['concat.3.a','concat.3.b','concat.3.0','concat.3.c','concat.3.d','concat.3.e','concat.3.f'],out=>'concat.3.vcf.out',do_bcf=>0,args=>'-l --ligate-warn');
+test_vcf_concat($opts,in=>['concat.3.a','concat.3.b','concat.3.0','concat.3.c','concat.3.d','concat.3.e','concat.3.f'],out=>'concat.3.bcf.out',do_bcf=>1,args=>'-l --ligate-warn');
 test_naive_concat($opts,name=>'naive_concat',max_hdr_lines=>10000,max_body_lines=>10000,nfiles=>10);
 test_vcf_concat($opts,in=>['concat.4.a','concat.4.b'],out=>'concat.5.out',do_bcf=>0,args=>'-l');
 test_vcf_concat($opts,in=>['concat.4.a','concat.4.b'],out=>'concat.5.out',do_bcf=>1,args=>'-l');
+test_vcf_concat($opts,in=>['concat.5.a','concat.5.b','concat.5.c'],out=>'concat.5.1.out',do_bcf=>0,args=>'-l --ligate-warn');
+test_vcf_concat($opts,in=>['concat.5.a','concat.5.b','concat.5.c'],out=>'concat.5.1.out',do_bcf=>1,args=>'-l --ligate-warn');
+test_vcf_concat($opts,in=>['concat.5.a','concat.5.b','concat.5.c'],out=>'concat.5.2.out',do_bcf=>1,args=>'-l --ligate-force');
 test_vcf_reheader($opts,in=>'reheader',out=>'reheader.1.out',header=>'reheader.hdr');
 test_vcf_reheader($opts,in=>'reheader',out=>'reheader.2.out',samples=>'reheader.samples');
 test_vcf_reheader($opts,in=>'reheader',out=>'reheader.2.out',samples=>'reheader.samples2');