add trailing no-count records to sd and rd (#8045)

broadinstitute · Oct 6, 2022 · 9e03432 · 9e03432
1 parent c54ab58
commit 9e03432
Show file tree

Hide file tree

Showing 6 changed files with 49 additions and 253 deletions.
diff --git a/src/main/java/org/broadinstitute/hellbender/tools/walkers/sv/CollectSVEvidence.java b/src/main/java/org/broadinstitute/hellbender/tools/walkers/sv/CollectSVEvidence.java
@@ -802,9 +802,11 @@ static void walkReadMatches( final GATKRead read,
         }
 
         public void close() {
-            while ( !siteDepthQueue.isEmpty() ) {
-                writer.write(siteDepthQueue.removeFirst());
-            }
+            do {
+                while ( !siteDepthQueue.isEmpty() ) {
+                    writer.write(siteDepthQueue.removeFirst());
+                }
+            } while ( readNextLocus() );
             writer.close();
         }
 
@@ -990,6 +992,11 @@ void close() {
             if ( depthEvidence != null ) {
                 writer.write(depthEvidence);
                 countCounter.addCount(depthEvidence.getCounts()[0]);
+                final int[] emptyCount = new int[1];
+                while ( intervalIterator.hasNext() ) {
+                    writer.write(new DepthEvidence(intervalIterator.next(), emptyCount));
+                    countCounter.addCount(0);
+                }
             }
             writer.close();
         }

diff --git a/...java/org/broadinstitute/hellbender/tools/walkers/sv/CollectSVEvidenceIntegrationTest.java b/...java/org/broadinstitute/hellbender/tools/walkers/sv/CollectSVEvidenceIntegrationTest.java
@@ -14,7 +14,6 @@
 public class CollectSVEvidenceIntegrationTest extends CommandLineProgramTest {
 
     public static final String pesrTestDir = toolsTestDir + "walkers/sv/pesr";
-    public static final String tinyVCF = largeFileTestDir + "CEUTrio.HiSeq.WGS.b37.NA12878.20.21.tiny.vcf";
 
     @Test
     public void testPECollection() throws Exception {
@@ -38,7 +37,7 @@ public void testSRCollection() throws Exception {
     @Test
     public void testSDCollection() throws Exception {
         final IntegrationTestSpec spec = new IntegrationTestSpec(
-                "-I " + NA12878_20_21_WGS_bam + " --sample-name NA12878 -F " + tinyVCF + " -SD %s",
+                "-I " + NA12878_20_21_WGS_bam + " --sample-name NA12878 -F " + pesrTestDir + "/snpSites.vcf -SD %s",
                 Collections.singletonList(pesrTestDir + "/NA12878" + SiteDepthCodec.FORMAT_SUFFIX + ".gz"));
         spec.setOutputFileExtension(SiteDepthCodec.FORMAT_SUFFIX + ".gz");
         spec.executeTest("SD collection", this);

diff --git a/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/NA12878.rd.txt.gz b/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/NA12878.rd.txt.gz
diff --git a/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/NA12878.sd.txt.gz b/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/NA12878.sd.txt.gz
diff --git a/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/intervals.bed b/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/intervals.bed
@@ -1,250 +1,6 @@
+20	9000000	9001000
+20	9001000	9002000
 20	10000000	10001000
 20	10001000	10002000
-20	10002000	10003000
-20	10003000	10004000
-20	10004000	10005000
-20	10005000	10006000
-20	10006000	10007000
-20	10007000	10008000
-20	10008000	10009000
-20	10009000	10010000
-20	10010000	10011000
-20	10011000	10012000
-20	10012000	10013000
-20	10013000	10014000
-20	10014000	10015000
-20	10015000	10016000
-20	10016000	10017000
-20	10017000	10018000
-20	10018000	10019000
-20	10019000	10020000
-20	10020000	10021000
-20	10021000	10022000
-20	10022000	10023000
-20	10023000	10024000
-20	10024000	10025000
-20	10025000	10026000
-20	10026000	10027000
-20	10027000	10028000
-20	10028000	10029000
-20	10029000	10030000
-20	10030000	10031000
-20	10031000	10032000
-20	10032000	10033000
-20	10033000	10034000
-20	10034000	10035000
-20	10035000	10036000
-20	10036000	10037000
-20	10037000	10038000
-20	10038000	10039000
-20	10039000	10040000
-20	10040000	10041000
-20	10041000	10042000
-20	10042000	10043000
-20	10043000	10044000
-20	10044000	10045000
-20	10045000	10046000
-20	10046000	10047000
-20	10047000	10048000
-20	10048000	10049000
-20	10049000	10050000
-20	10050000	10051000
-20	10051000	10052000
-20	10052000	10053000
-20	10053000	10054000
-20	10054000	10055000
-20	10055000	10056000
-20	10056000	10057000
-20	10057000	10058000
-20	10058000	10059000
-20	10059000	10060000
-20	10060000	10061000
-20	10061000	10062000
-20	10062000	10063000
-20	10063000	10064000
-20	10064000	10065000
-20	10065000	10066000
-20	10066000	10067000
-20	10067000	10068000
-20	10068000	10069000
-20	10069000	10070000
-20	10070000	10071000
-20	10071000	10072000
-20	10072000	10073000
-20	10073000	10074000
-20	10074000	10075000
-20	10075000	10076000
-20	10076000	10077000
-20	10077000	10078000
-20	10078000	10079000
-20	10079000	10080000
-20	10080000	10081000
-20	10081000	10082000
-20	10082000	10083000
-20	10083000	10084000
-20	10084000	10085000
-20	10085000	10086000
-20	10086000	10087000
-20	10087000	10088000
-20	10088000	10089000
-20	10089000	10090000
-20	10090000	10091000
-20	10091000	10092000
-20	10092000	10093000
-20	10093000	10094000
-20	10094000	10095000
-20	10095000	10096000
-20	10096000	10097000
-20	10097000	10098000
-20	10098000	10099000
-20	10099000	10100000
-20	10100000	10101000
-20	10101000	10102000
-20	10102000	10103000
-20	10103000	10104000
-20	10104000	10105000
-20	10105000	10106000
-20	10106000	10107000
-20	10107000	10108000
-20	10108000	10109000
-20	10109000	10110000
-20	10110000	10111000
-20	10111000	10112000
-20	10112000	10113000
-20	10113000	10114000
-20	10114000	10115000
-20	10115000	10116000
-20	10116000	10117000
-20	10117000	10118000
-20	10118000	10119000
-20	10119000	10120000
-20	10120000	10121000
-20	10121000	10122000
-20	10122000	10123000
-20	10123000	10124000
-20	10124000	10125000
-20	10125000	10126000
-20	10126000	10127000
-20	10127000	10128000
-20	10128000	10129000
-20	10129000	10130000
-20	10130000	10131000
-20	10131000	10132000
-20	10132000	10133000
-20	10133000	10134000
-20	10134000	10135000
-20	10135000	10136000
-20	10136000	10137000
-20	10137000	10138000
-20	10138000	10139000
-20	10139000	10140000
-20	10140000	10141000
-20	10141000	10142000
-20	10142000	10143000
-20	10143000	10144000
-20	10144000	10145000
-20	10145000	10146000
-20	10146000	10147000
-20	10147000	10148000
-20	10148000	10149000
-20	10149000	10150000
-20	10150000	10151000
-20	10151000	10152000
-20	10152000	10153000
-20	10153000	10154000
-20	10154000	10155000
-20	10155000	10156000
-20	10156000	10157000
-20	10157000	10158000
-20	10158000	10159000
-20	10159000	10160000
-20	10160000	10161000
-20	10161000	10162000
-20	10162000	10163000
-20	10163000	10164000
-20	10164000	10165000
-20	10165000	10166000
-20	10166000	10167000
-20	10167000	10168000
-20	10168000	10169000
-20	10169000	10170000
-20	10170000	10171000
-20	10171000	10172000
-20	10172000	10173000
-20	10173000	10174000
-20	10174000	10175000
-20	10175000	10176000
-20	10176000	10177000
-20	10177000	10178000
-20	10178000	10179000
-20	10179000	10180000
-20	10180000	10181000
-20	10181000	10182000
-20	10182000	10183000
-20	10183000	10184000
-20	10184000	10185000
-20	10185000	10186000
-20	10186000	10187000
-20	10187000	10188000
-20	10188000	10189000
-20	10189000	10190000
-20	10190000	10191000
-20	10191000	10192000
-20	10192000	10193000
-20	10193000	10194000
-20	10194000	10195000
-20	10195000	10196000
-20	10196000	10197000
-20	10197000	10198000
-20	10198000	10199000
-20	10199000	10200000
-20	10200000	10201000
-20	10201000	10202000
-20	10202000	10203000
-20	10203000	10204000
-20	10204000	10205000
-20	10205000	10206000
-20	10206000	10207000
-20	10207000	10208000
-20	10208000	10209000
-20	10209000	10210000
-20	10210000	10211000
-20	10211000	10212000
-20	10212000	10213000
-20	10213000	10214000
-20	10214000	10215000
-20	10215000	10216000
-20	10216000	10217000
-20	10217000	10218000
-20	10218000	10219000
-20	10219000	10220000
-20	10220000	10221000
-20	10221000	10222000
-20	10222000	10223000
-20	10223000	10224000
-20	10224000	10225000
-20	10225000	10226000
-20	10226000	10227000
-20	10227000	10228000
-20	10228000	10229000
-20	10229000	10230000
-20	10230000	10231000
-20	10231000	10232000
-20	10232000	10233000
-20	10233000	10234000
-20	10234000	10235000
-20	10235000	10236000
-20	10236000	10237000
-20	10237000	10238000
-20	10238000	10239000
-20	10239000	10240000
-20	10240000	10241000
-20	10241000	10242000
-20	10242000	10243000
-20	10243000	10244000
-20	10244000	10245000
-20	10245000	10246000
-20	10246000	10247000
-20	10247000	10248000
-20	10248000	10249000
-20	10249000	10250000
+20	10260000	10261000
+20	10261000	10262000
diff --git a/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/snpSites.vcf b/src/test/resources/org/broadinstitute/hellbender/tools/walkers/sv/pesr/snpSites.vcf
@@ -0,0 +1,34 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=LowQual,Description="Low quality">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=A,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA12878
+21	9000001	.	A	G	41.28	.	AC=2;AF=1.00;AN=2;DP=2;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;QD=20.64;SOR=0.693	GT:AD:DP:GQ:PL	1/1:0,2:2:6:53,6,0
+21	9000002	.	A	G	41.28	.	AC=2;AF=1.00;AN=2;DP=2;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=60.00;QD=20.64;SOR=0.693	GT:AD:DP:GQ:PL	1/1:0,2:2:6:53,6,0
+21	10032937	.	C	T	78.28	.	AC=2;AF=1.00;AN=2;DP=2;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=59.50;QD=25.36;SOR=0.693	GT:AD:DP:GQ:PL	1/1:0,2:2:6:90,6,0
+21	10085649	.	A	G	78.28	.	AC=2;AF=1.00;AN=2;DP=2;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=59.50;QD=28.73;SOR=0.693	GT:AD:DP:GQ:PL	1/1:0,2:2:6:90,6,0
+21	10085652	.	C	A	58.60	.	AC=1;AF=0.500;AN=2;BaseQRankSum=1.611;DP=8;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=59.88;MQRankSum=0.319;QD=7.33;ReadPosRankSum=1.242;SOR=0.693	GT:AD:DP:GQ:PL	0/1:6,2:8:66:66,0,722
+21	10085654	.	G	C	58.60	.	AC=1;AF=0.500;AN=2;BaseQRankSum=-2.100;DP=8;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=59.88;MQRankSum=0.319;QD=7.33;ReadPosRankSum=1.242;SOR=0.693	GT:AD:DP:GQ:PL	0/1:6,2:8:66:66,0,722
+21	10260001	.	C	T	78.28	.	AC=2;AF=1.00;AN=2;DP=2;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=59.50;QD=25.36;SOR=0.693	GT:AD:DP:GQ:PL	1/1:0,2:2:6:90,6,0
+21	10260002	.	A	G	78.28	.	AC=2;AF=1.00;AN=2;DP=2;ExcessHet=3.0103;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=59.50;QD=28.73;SOR=0.693	GT:AD:DP:GQ:PL	1/1:0,2:2:6:90,6,0