Fixed haplotypecaller index files

protected/biopet-gatk-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeGVCFs.scala

@@ -8,8 +8,13 @@ package nl.lumc.sasc.biopet.extensions.gatk.broad
 import java.io.File
 
 import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Output
 
 class GenotypeGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.GenotypeGVCFs with GatkGeneral {
+
+  @Output(required = false)
+  protected var vcfIndex: File = _
+
   annotation ++= config("annotation", default = Seq(), freeVar = false).asStringList
 
   if (config.contains("dbsnp")) dbsnp = config("dbsnp")
@@ -22,6 +27,11 @@ class GenotypeGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queu
     stand_call_conf = config("stand_call_conf", default = 30)
     stand_emit_conf = config("stand_emit_conf", default = 0)
   }
+
+  override def freezeFieldValues(): Unit = {
+    super.freezeFieldValues()
+    if (out.getName.endsWith(".vcf.gz")) vcfIndex = new File(out.getAbsolutePath + ".tbi")
+  }
 }
 
 object GenotypeGVCFs {
@@ -29,6 +39,7 @@ object GenotypeGVCFs {
     val gg = new GenotypeGVCFs(root)
     gg.variant = gvcfFiles
     gg.out = output
+    if (gg.out.getName.endsWith(".vcf.gz")) gg.vcfIndex = new File(gg.out.getAbsolutePath + ".tbi")
     gg
   }
 }
\ No newline at end of file

protected/biopet-gatk-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/HaplotypeCaller.scala

@@ -5,11 +5,17 @@
  */
 package nl.lumc.sasc.biopet.extensions.gatk.broad
 
+import java.io.File
+
 import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Output
 import org.broadinstitute.gatk.utils.variant.GATKVCFIndexType
 
 class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.HaplotypeCaller with GatkGeneral {
 
+  @Output(required = false)
+  protected var vcfIndex: File = _
+
   override val defaultThreads = 1
 
   min_mapping_quality_score = config("minMappingQualityScore", default = 20)
@@ -40,6 +46,7 @@ class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.qu
 
   override def freezeFieldValues() {
     super.freezeFieldValues()
+    if (out.getName.endsWith(".vcf.gz")) vcfIndex = new File(out.getAbsolutePath + ".tbi")
     if (bamOutput != null && nct.getOrElse(1) > 1) {
       logger.warn("BamOutput is on, nct/threads is forced to set on 1, this option is only for debug")
       nCoresRequest = Some(1)
@@ -47,10 +54,22 @@ class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.qu
     nct = Some(getThreads)
     memoryLimit = Option(memoryLimit.getOrElse(2.0) * nct.getOrElse(1))
   }
+}
+
+object HaplotypeCaller {
+  def apply(root: Configurable, inputFiles: List[File], outputFile: File): HaplotypeCaller = {
+    val hc = new HaplotypeCaller(root)
+    hc.input_file = inputFiles
+    hc.out = outputFile
+    if (hc.out.getName.endsWith(".vcf.gz")) hc.vcfIndex = new File(hc.out.getAbsolutePath + ".tbi")
+    hc
+  }
 
-  def useGvcf() {
-    emitRefConfidence = org.broadinstitute.gatk.tools.walkers.haplotypecaller.ReferenceConfidenceMode.GVCF
-    variant_index_type = GATKVCFIndexType.LINEAR
-    variant_index_parameter = config("variant_index_parameter", default = 128000)
+  def gvcf(root: Configurable, inputFile: File, outputFile: File): HaplotypeCaller = {
+    val hc = apply(root, List(inputFile), outputFile)
+    hc.emitRefConfidence = org.broadinstitute.gatk.tools.walkers.haplotypecaller.ReferenceConfidenceMode.GVCF
+    hc.variant_index_type = GATKVCFIndexType.LINEAR
+    hc.variant_index_parameter = Some(hc.config("variant_index_parameter", default = 128000).asInt)
+    hc
   }
-}
+}
\ No newline at end of file

protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala

@@ -111,7 +111,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
 
       if (sampleID != null && (useHaplotypecaller || config("joint_genotyping", default = false).asBoolean)) {
         val hcGvcf = new HaplotypeCaller(this)
-        hcGvcf.useGvcf()
+        //hcGvcf.useGvcf()
         hcGvcf.input_file = scriptOutput.bamFiles
         hcGvcf.out = new File(outputDir, outputName + ".hc.discovery.gvcf.vcf.gz")
         add(hcGvcf)

protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/variantcallers/HaplotypeCaller.scala

@@ -2,6 +2,7 @@ package nl.lumc.sasc.biopet.pipelines.gatk.variantcallers
 
 import nl.lumc.sasc.biopet.pipelines.shiva.variantcallers.Variantcaller
 import nl.lumc.sasc.biopet.utils.config.Configurable
+import nl.lumc.sasc.biopet.extensions.gatk.broad
 
 /** Default mode for the haplotypecaller */
 class HaplotypeCaller(val root: Configurable) extends Variantcaller {
@@ -9,9 +10,7 @@ class HaplotypeCaller(val root: Configurable) extends Variantcaller {
   protected def defaultPrio = 1
 
   def biopetScript() {
-    val hc = new nl.lumc.sasc.biopet.extensions.gatk.broad.HaplotypeCaller(this)
-    hc.input_file = inputBams.values.toList
-    hc.out = outputFile
+    val hc = broad.HaplotypeCaller(this, inputBams.values.toList, outputFile)
     add(hc)
   }
 }

protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/variantcallers/HaplotypeCallerAllele.scala

@@ -2,6 +2,7 @@ package nl.lumc.sasc.biopet.pipelines.gatk.variantcallers
 
 import nl.lumc.sasc.biopet.pipelines.shiva.variantcallers.Variantcaller
 import nl.lumc.sasc.biopet.utils.config.Configurable
+import nl.lumc.sasc.biopet.extensions.gatk.broad
 
 /** Allele mode for Haplotypecaller */
 class HaplotypeCallerAllele(val root: Configurable) extends Variantcaller {
@@ -9,9 +10,7 @@ class HaplotypeCallerAllele(val root: Configurable) extends Variantcaller {
   protected def defaultPrio = 5
 
   def biopetScript() {
-    val hc = new nl.lumc.sasc.biopet.extensions.gatk.broad.HaplotypeCaller(this)
-    hc.input_file = inputBams.values.toList
-    hc.out = outputFile
+    val hc = broad.HaplotypeCaller(this, inputBams.values.toList, outputFile)
     hc.alleles = config("input_alleles")
     hc.genotyping_mode = org.broadinstitute.gatk.tools.walkers.genotyper.GenotypingOutputMode.GENOTYPE_GIVEN_ALLELES
     add(hc)

protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/variantcallers/HaplotypeCallerGvcf.scala

 package nl.lumc.sasc.biopet.pipelines.gatk.variantcallers
 
-import nl.lumc.sasc.biopet.extensions.gatk.broad.GenotypeGVCFs
 import nl.lumc.sasc.biopet.pipelines.shiva.variantcallers.Variantcaller
 import nl.lumc.sasc.biopet.utils.config.Configurable
+import nl.lumc.sasc.biopet.extensions.gatk.broad
 
 /** Gvcf mode for haplotypecaller */
 class HaplotypeCallerGvcf(val root: Configurable) extends Variantcaller {
@@ -11,15 +11,12 @@ class HaplotypeCallerGvcf(val root: Configurable) extends Variantcaller {
 
   def biopetScript() {
     val gvcfFiles = for ((sample, inputBam) <- inputBams) yield {
-      val hc = new nl.lumc.sasc.biopet.extensions.gatk.broad.HaplotypeCaller(this)
-      hc.input_file = List(inputBam)
-      hc.out = new File(outputDir, sample + ".gvcf.vcf.gz")
-      hc.useGvcf()
+      val hc = broad.HaplotypeCaller.gvcf(this, inputBam, new File(outputDir, sample + ".gvcf.vcf.gz"))
       add(hc)
       hc.out
     }
 
-    val genotypeGVCFs = GenotypeGVCFs(this, gvcfFiles.toList, outputFile)
+    val genotypeGVCFs = broad.GenotypeGVCFs(this, gvcfFiles.toList, outputFile)
     add(genotypeGVCFs)
   }
 }