diff --git a/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/VcfWithVcf.scala b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/VcfWithVcf.scala
index 0f507ed21e13b6767b70c422fb3d5c71cb2dccc3..afde5054be9d1b679f95deb5cd7248f556e5ad12 100644
--- a/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/VcfWithVcf.scala
+++ b/public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/VcfWithVcf.scala
@@ -17,14 +17,14 @@ package nl.lumc.sasc.biopet.extensions.tools
import java.io.File
-import nl.lumc.sasc.biopet.core.ToolCommandFunction
+import nl.lumc.sasc.biopet.core.{ Reference, ToolCommandFunction }
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
/**
* Biopet extension for tool VcfWithVcf
*/
-class VcfWithVcf(val root: Configurable) extends ToolCommandFunction {
+class VcfWithVcf(val root: Configurable) extends ToolCommandFunction with Reference {
def toolObject = nl.lumc.sasc.biopet.tools.VcfWithVcf
@Input(doc = "Input vcf file", shortName = "input", required = true)
@@ -39,12 +39,16 @@ class VcfWithVcf(val root: Configurable) extends ToolCommandFunction {
@Output(doc = "Output vcf file index", shortName = "output", required = true)
private var outputIndex: File = _
+ @Input
+ var reference: File = _
+
var fields: List[(String, String, Option[String])] = List()
override def defaultCoreMemory = 2.0
override def beforeGraph() {
super.beforeGraph()
+ if (reference == null) reference = referenceFasta()
if (output.getName.endsWith(".gz")) outputIndex = new File(output.getAbsolutePath + ".tbi")
if (output.getName.endsWith(".vcf")) outputIndex = new File(output.getAbsolutePath + ".idx")
if (fields.isEmpty) throw new IllegalArgumentException("No fields found for VcfWithVcf")
@@ -54,5 +58,6 @@ class VcfWithVcf(val root: Configurable) extends ToolCommandFunction {
required("-I", input) +
required("-o", output) +
required("-s", secondaryVcf) +
+ required("-R", reference) +
repeat("-f", fields.map(x => x._1 + ":" + x._2 + ":" + x._3.getOrElse("none")))
}
diff --git a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala
index 2b764ec9c2c7d75b12dc0248eddca338957e2ee7..fc72b6abc4f9e099d021a265834d96f0eb5be7af 100644
--- a/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala
+++ b/public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala
@@ -18,6 +18,7 @@ package nl.lumc.sasc.biopet.tools
import java.io.File
import java.util
+import htsjdk.samtools.reference.FastaSequenceFile
import htsjdk.variant.variantcontext.{ VariantContext, VariantContextBuilder }
import htsjdk.variant.variantcontext.writer.{ AsyncVariantContextWriter, VariantContextWriterBuilder }
import htsjdk.variant.vcf._
@@ -36,6 +37,7 @@ object VcfWithVcf extends ToolCommand {
case class Args(inputFile: File = null,
outputFile: File = null,
+ referenceFasta: File = null,
secondaryVcf: File = null,
fields: List[Fields] = Nil,
matchAllele: Boolean = true) extends AbstractArgs
@@ -54,6 +56,9 @@ object VcfWithVcf extends ToolCommand {
opt[File]('s', "secondaryVcf") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(secondaryVcf = x)
}
+ opt[File]('R', "reference") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
+ c.copy(referenceFasta = x)
+ }
opt[String]('f', "field") unbounded () valueName "<field> or <input_field:output_field> or <input_field:output_field:method>" action { (x, c) =>
val values = x.split(":")
if (values.size > 2) c.copy(fields = Fields(values(0), values(1), FieldMethod.withName(values(2))) :: c.fields)
@@ -74,16 +79,30 @@ object VcfWithVcf extends ToolCommand {
logger.info("Init phase")
val argsParser = new OptParser
- val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
+ val commandArgs: Args = argsParser.parse(args, Args()) getOrElse(throw new IllegalArgumentException)
val reader = new VCFFileReader(commandArgs.inputFile)
val secondaryReader = new VCFFileReader(commandArgs.secondaryVcf)
+ val referenceDict = new FastaSequenceFile(commandArgs.referenceFasta, true).getSequenceDictionary
+
val header = reader.getFileHeader
+ val vcfDict = header.getSequenceDictionary match {
+ case r if r != null =>
+ r.assertSameDictionary(referenceDict)
+ r
+ case _ => referenceDict
+ }
val secondHeader = secondaryReader.getFileHeader
+
+ secondHeader.getSequenceDictionary match {
+ case r if r != null => r.assertSameDictionary(referenceDict)
+ case _ =>
+ }
+
val writer = new AsyncVariantContextWriter(new VariantContextWriterBuilder().
setOutputFile(commandArgs.outputFile).
- setReferenceDictionary(header.getSequenceDictionary).
+ setReferenceDictionary(vcfDict).
build)
for (x <- commandArgs.fields) {
diff --git a/public/biopet-tools/src/test/resources/VEP_oneline.vcf b/public/biopet-tools/src/test/resources/VEP_oneline.vcf
index e5cd64bcb5ff107f53fb6c22fd1634be4c969e54..e93681cd277b7b7db096a5128792dd466d893137 100644
--- a/public/biopet-tools/src/test/resources/VEP_oneline.vcf
+++ b/public/biopet-tools/src/test/resources/VEP_oneline.vcf
@@ -73,90 +73,7 @@
##FILTER=<ID=IndexIsVariant,Description="Index call is a variant">
##FILTER=<ID=InArtificialChrom,Description="Variant found in an artificial chromosome">
##FILTER=<ID=IsIntergenic,Description="Variant found in intergenic region">
-##contig=<ID=chrM,length=16571>
-##contig=<ID=chr1,length=249250621>
-##contig=<ID=chr2,length=243199373>
-##contig=<ID=chr3,length=198022430>
-##contig=<ID=chr4,length=191154276>
-##contig=<ID=chr5,length=180915260>
-##contig=<ID=chr6,length=171115067>
-##contig=<ID=chr7,length=159138663>
-##contig=<ID=chr8,length=146364022>
-##contig=<ID=chr9,length=141213431>
-##contig=<ID=chr10,length=135534747>
-##contig=<ID=chr11,length=135006516>
-##contig=<ID=chr12,length=133851895>
-##contig=<ID=chr13,length=115169878>
-##contig=<ID=chr14,length=107349540>
-##contig=<ID=chr15,length=102531392>
-##contig=<ID=chr16,length=90354753>
-##contig=<ID=chr17,length=81195210>
-##contig=<ID=chr18,length=78077248>
-##contig=<ID=chr19,length=59128983>
-##contig=<ID=chr20,length=63025520>
-##contig=<ID=chr21,length=48129895>
-##contig=<ID=chr22,length=51304566>
-##contig=<ID=chrX,length=155270560>
-##contig=<ID=chrY,length=59373566>
-##contig=<ID=chr1_gl000191_random,length=106433>
-##contig=<ID=chr1_gl000192_random,length=547496>
-##contig=<ID=chr4_gl000193_random,length=189789>
-##contig=<ID=chr4_gl000194_random,length=191469>
-##contig=<ID=chr7_gl000195_random,length=182896>
-##contig=<ID=chr8_gl000196_random,length=38914>
-##contig=<ID=chr8_gl000197_random,length=37175>
-##contig=<ID=chr9_gl000198_random,length=90085>
-##contig=<ID=chr9_gl000199_random,length=169874>
-##contig=<ID=chr9_gl000200_random,length=187035>
-##contig=<ID=chr9_gl000201_random,length=36148>
-##contig=<ID=chr11_gl000202_random,length=40103>
-##contig=<ID=chr17_gl000203_random,length=37498>
-##contig=<ID=chr17_gl000204_random,length=81310>
-##contig=<ID=chr17_gl000205_random,length=174588>
-##contig=<ID=chr17_gl000206_random,length=41001>
-##contig=<ID=chr18_gl000207_random,length=4262>
-##contig=<ID=chr19_gl000208_random,length=92689>
-##contig=<ID=chr19_gl000209_random,length=159169>
-##contig=<ID=chr21_gl000210_random,length=27682>
-##contig=<ID=chrUn_gl000211,length=166566>
-##contig=<ID=chrUn_gl000212,length=186858>
-##contig=<ID=chrUn_gl000213,length=164239>
-##contig=<ID=chrUn_gl000214,length=137718>
-##contig=<ID=chrUn_gl000215,length=172545>
-##contig=<ID=chrUn_gl000216,length=172294>
-##contig=<ID=chrUn_gl000217,length=172149>
-##contig=<ID=chrUn_gl000218,length=161147>
-##contig=<ID=chrUn_gl000219,length=179198>
-##contig=<ID=chrUn_gl000220,length=161802>
-##contig=<ID=chrUn_gl000221,length=155397>
-##contig=<ID=chrUn_gl000222,length=186861>
-##contig=<ID=chrUn_gl000223,length=180455>
-##contig=<ID=chrUn_gl000224,length=179693>
-##contig=<ID=chrUn_gl000225,length=211173>
-##contig=<ID=chrUn_gl000226,length=15008>
-##contig=<ID=chrUn_gl000227,length=128374>
-##contig=<ID=chrUn_gl000228,length=129120>
-##contig=<ID=chrUn_gl000229,length=19913>
-##contig=<ID=chrUn_gl000230,length=43691>
-##contig=<ID=chrUn_gl000231,length=27386>
-##contig=<ID=chrUn_gl000232,length=40652>
-##contig=<ID=chrUn_gl000233,length=45941>
-##contig=<ID=chrUn_gl000234,length=40531>
-##contig=<ID=chrUn_gl000235,length=34474>
-##contig=<ID=chrUn_gl000236,length=41934>
-##contig=<ID=chrUn_gl000237,length=45867>
-##contig=<ID=chrUn_gl000238,length=39939>
-##contig=<ID=chrUn_gl000239,length=33824>
-##contig=<ID=chrUn_gl000240,length=41933>
-##contig=<ID=chrUn_gl000241,length=42152>
-##contig=<ID=chrUn_gl000242,length=43523>
-##contig=<ID=chrUn_gl000243,length=43341>
-##contig=<ID=chrUn_gl000244,length=39929>
-##contig=<ID=chrUn_gl000245,length=36651>
-##contig=<ID=chrUn_gl000246,length=38154>
-##contig=<ID=chrUn_gl000247,length=36422>
-##contig=<ID=chrUn_gl000248,length=39786>
-##contig=<ID=chrUn_gl000249,length=38502>
+##contig=<ID=chrQ,length=16571>
##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence type as predicted by VEP. Format: Allele|Gene|Feature|Feature_type|Consequence|cDNA_position|CDS_position|Protein_position|Amino_acids|Codons|Existing_variation|AA_MAF|EA_MAF|ALLELE_NUM|DISTANCE|STRAND|CLIN_SIG|SYMBOL|SYMBOL_SOURCE|GMAF|HGVSc|HGVSp|AFR_MAF|AMR_MAF|ASN_MAF|EUR_MAF|PUBMED">
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT Sample_101 Sample_102 Sample_103
-chr1 871042 rs199537431 C CA 1541.12 PASS FG=intron;FD=unknown;GM=NM_152486.2;GL=SAMD11;CP=0.000;CG=-1.630;CN=2294,3274,30362,112930;DSP=107;AC=2;AF=0.333;AN=6;BaseQRankSum=4.068;DB;DP=124;FS=1.322;MLEAC=2;MLEAF=0.333;MQ=60.0;MQ0=0;MQRankSum=-0.197;QD=19.03;RPA=1,2;RU=A;ReadPosRankSum=-0.424;STR;VQSLOD=0.079;culprit=FS;GATKCaller=UG,HC;CSQ=A|ENSESTG00000013623|ENSESTT00000034081|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|ENSESTT00000034081.1:c.306-110_306-109insA||||||,A|CCDS2.2|CCDS2.2|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|CCDS2.2:c.306-110_306-109insA||||||,A|ENSESTG00000013623|ENSESTT00000034116|Transcript|upstream_gene_variant||||||rs199537431|||1|3610|1||||A:0.0078|||||||,A|ENSESTG00000013623|ENSESTT00000034091|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|ENSESTT00000034091.1:c.306-110_306-109insA||||||,A|ENSESTG00000013623|ENSESTT00000034102|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|ENSESTT00000034102.1:c.29-110_29-109insA||||||,A|148398|XM_005244723.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244723.1:c.306-110_306-109insA||||||,A|148398|XM_005244724.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244724.1:c.306-110_306-109insA||||||,A|148398|XM_005244725.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244725.1:c.306-110_306-109insA||||||,A|148398|NM_152486.2|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|NM_152486.2:c.306-110_306-109insA||||||,A|148398|XM_005244727.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244727.1:c.306-110_306-109insA||||||,A|148398|XM_005244726.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244726.1:c.306-110_306-109insA|||||| GT:AD:DP:GQ:PL 0/1:24,21:45:99:838,0,889 0/1:17,19:36:99:744,0,603 0/0:42,0:43:99:0,126,1717
+chrQ 10000 rs199537431 C CA 1541.12 PASS FG=intron;FD=unknown;GM=NM_152486.2;GL=SAMD11;CP=0.000;CG=-1.630;CN=2294,3274,30362,112930;DSP=107;AC=2;AF=0.333;AN=6;BaseQRankSum=4.068;DB;DP=124;FS=1.322;MLEAC=2;MLEAF=0.333;MQ=60.0;MQ0=0;MQRankSum=-0.197;QD=19.03;RPA=1,2;RU=A;ReadPosRankSum=-0.424;STR;VQSLOD=0.079;culprit=FS;GATKCaller=UG,HC;CSQ=A|ENSESTG00000013623|ENSESTT00000034081|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|ENSESTT00000034081.1:c.306-110_306-109insA||||||,A|CCDS2.2|CCDS2.2|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|CCDS2.2:c.306-110_306-109insA||||||,A|ENSESTG00000013623|ENSESTT00000034116|Transcript|upstream_gene_variant||||||rs199537431|||1|3610|1||||A:0.0078|||||||,A|ENSESTG00000013623|ENSESTT00000034091|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|ENSESTT00000034091.1:c.306-110_306-109insA||||||,A|ENSESTG00000013623|ENSESTT00000034102|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||||A:0.0078|ENSESTT00000034102.1:c.29-110_29-109insA||||||,A|148398|XM_005244723.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244723.1:c.306-110_306-109insA||||||,A|148398|XM_005244724.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244724.1:c.306-110_306-109insA||||||,A|148398|XM_005244725.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244725.1:c.306-110_306-109insA||||||,A|148398|NM_152486.2|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|NM_152486.2:c.306-110_306-109insA||||||,A|148398|XM_005244727.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244727.1:c.306-110_306-109insA||||||,A|148398|XM_005244726.1|Transcript|intron_variant&feature_elongation||||||rs199537431|||1||1||SAMD11||A:0.0078|XM_005244726.1:c.306-110_306-109insA|||||| GT:AD:DP:GQ:PL 0/1:24,21:45:99:838,0,889 0/1:17,19:36:99:744,0,603 0/0:42,0:43:99:0,126,1717
diff --git a/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz b/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz
index 8f0e4cb3292cbb6ac9918f7f13633e21b9f2ed1a..4947c907caf17380cddab39af399ce2762b53f83 100644
Binary files a/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz and b/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz differ
diff --git a/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz.tbi b/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz.tbi
index 1d1bc2ce9351b5f9d267a75fd6f7df3fc34326df..78d4dad2281aaba9589d3f1a8e8571edf1b012dd 100644
Binary files a/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz.tbi and b/public/biopet-tools/src/test/resources/VEP_oneline.vcf.gz.tbi differ
diff --git a/public/biopet-tools/src/test/resources/unvep_online.vcf b/public/biopet-tools/src/test/resources/unvep_online.vcf
new file mode 100644
index 0000000000000000000000000000000000000000..30133271958e7ee68a1264000f6c4a477df80c4f
--- /dev/null
+++ b/public/biopet-tools/src/test/resources/unvep_online.vcf
@@ -0,0 +1,78 @@
+##fileformat=VCFv4.1
+##reference=file:///data/DIV5/KG/references/gatk_bundle_2.5/hg19_nohap/ucsc.hg19_nohap.fasta
+##INFO=<ID=DN,Number=1,Type=Integer,Description="inDbSNP">
+##INFO=<ID=DT,Number=0,Type=Flag,Description="in1000Genomes">
+##INFO=<ID=DA,Number=1,Type=String,Description="allelesDBSNP">
+##INFO=<ID=FG,Number=.,Type=String,Description="functionGVS">
+##INFO=<ID=FD,Number=.,Type=String,Description="functionDBSNP">
+##INFO=<ID=GM,Number=.,Type=String,Description="accession">
+##INFO=<ID=GL,Number=.,Type=String,Description="geneList">
+##INFO=<ID=AAC,Number=.,Type=String,Description="aminoAcids">
+##INFO=<ID=PP,Number=.,Type=String,Description="proteinPosition">
+##INFO=<ID=CDP,Number=.,Type=String,Description="cDNAPosition">
+##INFO=<ID=PH,Number=.,Type=String,Description="polyPhen">
+##INFO=<ID=CP,Number=1,Type=String,Description="scorePhastCons">
+##INFO=<ID=CG,Number=1,Type=String,Description="consScoreGERP">
+##INFO=<ID=AA,Number=1,Type=String,Description="chimpAllele">
+##INFO=<ID=CN,Number=.,Type=String,Description="CNV">
+##INFO=<ID=HA,Number=1,Type=String,Description="AfricanHapMapFreq">
+##INFO=<ID=HE,Number=1,Type=String,Description="EuropeanHapMapFreq">
+##INFO=<ID=HC,Number=1,Type=String,Description="AsianHapMapFreq">
+##INFO=<ID=DG,Number=0,Type=Flag,Description="hasGenotypes">
+##INFO=<ID=DV,Number=.,Type=String,Description="dbSNPValidation">
+##INFO=<ID=RM,Number=.,Type=String,Description="repeatMasker">
+##INFO=<ID=RT,Number=.,Type=String,Description="tandemRepeat">
+##INFO=<ID=CA,Number=0,Type=Flag,Description="clinicalAssociation">
+##INFO=<ID=DSP,Number=1,Type=Integer,Description="distanceToSplice">
+##INFO=<ID=GS,Number=.,Type=String,Description="granthamScore">
+##INFO=<ID=MR,Number=.,Type=String,Description="microRNAs">
+##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=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##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=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##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=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=NEGATIVE_TRAIN_SITE,Number=0,Type=Flag,Description="This variant was used to build the negative training set of bad variants">
+##INFO=<ID=POSITIVE_TRAIN_SITE,Number=0,Type=Flag,Description="This variant was used to build the positive training set of good variants">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=RPA,Number=.,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=VQSLOD,Number=1,Type=Float,Description="Log odds ratio of being a true variant versus being false under the trained gaussian mixture model">
+##INFO=<ID=culprit,Number=1,Type=String,Description="The annotation which was the worst performing in the Gaussian mixture model, likely the reason why the variant was filtered out">
+##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">
+##INFO=<ID=GATKCaller,Number=.,Type=String,Description="GATK variant caller used to call the variant">
+##INFO=<ID=PartOfCompound,Number=.,Type=String,Description="Whether the record was originally part of a record containing compound variants">
+##FORMAT=<ID=AD,Number=.,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">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FILTER=<ID=VQSRTrancheINDEL99.00to99.90,Description="Truth sensitivity tranche level for INDEL model at VQS Lod: -1.4714 <= x < -0.3324">
+##FILTER=<ID=VQSRTrancheINDEL99.90to100.00+,Description="Truth sensitivity tranche level for INDEL model at VQS Lod < -6.093">
+##FILTER=<ID=VQSRTrancheINDEL99.90to100.00,Description="Truth sensitivity tranche level for INDEL model at VQS Lod: -6.093 <= x < -1.4714">
+##FILTER=<ID=VQSRTrancheSNP99.00to99.90,Description="Truth sensitivity tranche level for SNP model at VQS Lod: -4.8126 <= x < 0.2264">
+##FILTER=<ID=VQSRTrancheSNP99.90to100.00+,Description="Truth sensitivity tranche level for SNP model at VQS Lod < -39474.9285">
+##FILTER=<ID=VQSRTrancheSNP99.90to100.00,Description="Truth sensitivity tranche level for SNP model at VQS Lod: -39474.9285 <= x < -4.8126">
+##FILTER=<ID=TooHigh1000GAF,Description="Allele frequency in 1000G is more than 5%">
+##FILTER=<ID=TooHighGoNLAF,Description="Allele frequency in 1000G is more than 5%">
+##FILTER=<ID=IndexNotCalled,Description="Position in index sample is not called">
+##FILTER=<ID=IndexIsVariant,Description="Index call is a variant">
+##FILTER=<ID=InArtificialChrom,Description="Variant found in an artificial chromosome">
+##FILTER=<ID=IsIntergenic,Description="Variant found in intergenic region">
+##contig=<ID=chrQ,length=16571>
+#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT Sample_101 Sample_102 Sample_103
+chrQ 10000 rs199537431 C CA 1541.12 PASS FG=intron;FD=unknown;GM=NM_152486.2;GL=SAMD11;CP=0.000;CG=-1.630;CN=2294,3274,30362,112930;DSP=107;AC=2;AF=0.333;AN=6;BaseQRankSum=4.068;DB;DP=124;FS=1.322;MLEAC=2;MLEAF=0.333;MQ=60.0;MQ0=0;MQRankSum=-0.197;QD=19.03;RPA=1,2;RU=A;ReadPosRankSum=-0.424;STR;VQSLOD=0.079;culprit=FS;GATKCaller=UG,HC GT:AD:DP:GQ:PL 0/1:24,21:45:99:838,0,889 0/1:17,19:36:99:744,0,603 0/0:42,0:43:99:0,126,1717
diff --git a/public/biopet-tools/src/test/resources/unvep_online.vcf.gz b/public/biopet-tools/src/test/resources/unvep_online.vcf.gz
index 210f83e016e5d83d303e755b4772cb8299089997..cb2934f5c19796e58f20ecb501eafbd3b141e432 100644
Binary files a/public/biopet-tools/src/test/resources/unvep_online.vcf.gz and b/public/biopet-tools/src/test/resources/unvep_online.vcf.gz differ
diff --git a/public/biopet-tools/src/test/resources/unvep_online.vcf.gz.tbi b/public/biopet-tools/src/test/resources/unvep_online.vcf.gz.tbi
index c52458d5601b25642ad72a90934955f280428dea..a70174d51594773e3c85d89ed17981ace4893e2e 100644
Binary files a/public/biopet-tools/src/test/resources/unvep_online.vcf.gz.tbi and b/public/biopet-tools/src/test/resources/unvep_online.vcf.gz.tbi differ
diff --git a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfWithVcfTest.scala b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfWithVcfTest.scala
index 2f1814210f0ccc760da2235969910e5a335524f7..bfb4d7c044b652a3c90e46d0226379cda595f460 100644
--- a/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfWithVcfTest.scala
+++ b/public/biopet-tools/src/test/scala/nl/lumc/sasc/biopet/tools/VcfWithVcfTest.scala
@@ -44,60 +44,68 @@ class VcfWithVcfTest extends TestNGSuite with MockitoSugar with Matchers {
val veppedPath = resourcePath("/VEP_oneline.vcf.gz")
val unveppedPath = resourcePath("/unvep_online.vcf.gz")
+ val referenceFasta = resourcePath("/fake_chrQ.fa")
val rand = new Random()
- @Test def testOutputTypeVcf() = {
+ @Test
+ def testOutputTypeVcf() = {
val tmpFile = File.createTempFile("VcfWithVcf_", ".vcf")
tmpFile.deleteOnExit()
- val arguments = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ")
+ val arguments = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ", "-R", referenceFasta)
main(arguments)
}
- @Test def testOutputTypeVcfGz() = {
+ @Test
+ def testOutputTypeVcfGz() = {
val tmpFile = File.createTempFile("VcfWithVcf_", ".vcf.gz")
tmpFile.deleteOnExit()
- val arguments = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ")
+ val arguments = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ", "-R", referenceFasta)
main(arguments)
}
- @Test def testOutputTypeBcf() = {
+ @Test
+ def testOutputTypeBcf() = {
val tmpFile = File.createTempFile("VcfWithVcf_", ".bcf")
tmpFile.deleteOnExit()
- val arguments = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ")
+ val arguments = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ", "-R", referenceFasta)
main(arguments)
}
- @Test def testOutputFieldException = {
+ @Test
+ def testOutputFieldException = {
val tmpFile = File.createTempFile("VCFWithVCf", ".vcf")
tmpFile.deleteOnExit()
- val args = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:AC")
+ val args = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:AC", "-R", referenceFasta)
an[IllegalArgumentException] should be thrownBy main(args)
val thrown = the[IllegalArgumentException] thrownBy main(args)
thrown.getMessage should equal("Field 'AC' already exists in input vcf")
}
- @Test def testInputFieldException = {
+ @Test
+ def testInputFieldException = {
val tmpFile = File.createTempFile("VCFWithVCf", ".vcf")
tmpFile.deleteOnExit()
- val args = Array("-I", unveppedPath, "-s", unveppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:NEW_CSQ")
+ val args = Array("-I", unveppedPath, "-s", unveppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:NEW_CSQ", "-R", referenceFasta)
an[IllegalArgumentException] should be thrownBy main(args)
val thrown = the[IllegalArgumentException] thrownBy main(args)
thrown.getMessage should equal("Field 'CSQ' does not exist in secondary vcf")
}
- @Test def testMinMethodException = {
+ @Test
+ def testMinMethodException = {
val tmpFile = File.createTempFile("VcfWithVcf_", ".vcf")
tmpFile.deleteOnExit()
- val args = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:CSQ:min")
+ val args = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:CSQ:min", "-R", referenceFasta)
an[IllegalArgumentException] should be thrownBy main(args)
val thrown = the[IllegalArgumentException] thrownBy main(args)
thrown.getMessage should equal("Type of field CSQ is not numeric")
}
- @Test def testMaxMethodException = {
+ @Test
+ def testMaxMethodException = {
val tmpFile = File.createTempFile("VcfWithVcf_", ".vcf")
tmpFile.deleteOnExit()
- val args = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:CSQ:max")
+ val args = Array("-I", unveppedPath, "-s", veppedPath, "-o", tmpFile.getAbsolutePath, "-f", "CSQ:CSQ:max", "-R", referenceFasta)
an[IllegalArgumentException] should be thrownBy main(args)
val thrown = the[IllegalArgumentException] thrownBy main(args)
thrown.getMessage should equal("Type of field CSQ is not numeric")
@@ -162,7 +170,8 @@ class VcfWithVcfTest extends TestNGSuite with MockitoSugar with Matchers {
}
- @Test def testGetSecondaryRecords = {
+ @Test
+ def testGetSecondaryRecords = {
val unvepRecord = new VCFFileReader(new File(unveppedPath)).iterator().next()
val vepReader = new VCFFileReader(new File(veppedPath))
val vepRecord = vepReader.iterator().next()
@@ -172,7 +181,8 @@ class VcfWithVcfTest extends TestNGSuite with MockitoSugar with Matchers {
secRec.foreach(x => identicalVariantContext(x, vepRecord) shouldBe true)
}
- @Test def testCreateRecord = {
+ @Test
+ def testCreateRecord = {
val unvepRecord = new VCFFileReader(new File(unveppedPath)).iterator().next()
val vepReader = new VCFFileReader(new File(veppedPath))
val header = vepReader.getFileHeader