diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CatVariants.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CatVariants.scala
deleted file mode 100644
index ceceed5f64ba51a75b098e4cd1b18beaa4f1894d..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CatVariants.scala
+++ /dev/null
@@ -1,58 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.{ Reference, BiopetJavaCommandLineFunction }
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-
-class CatVariants(val root: Configurable) extends BiopetJavaCommandLineFunction with Reference {
-
- javaMainClass = classOf[org.broadinstitute.gatk.tools.CatVariants].getName
-
- @Input(required = true)
- var inputFiles: List[File] = Nil
-
- @Output(required = true)
- var outputFile: File = null
-
- @Input
- var reference: File = null
-
- var assumeSorted = false
-
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- if (reference == null) reference = referenceFasta()
- }
-
- override def cmdLine = super.cmdLine +
- repeat("-V", inputFiles) +
- required("-out", outputFile) +
- required("-R", reference) +
- conditional(assumeSorted, "--assumeSorted")
-}
-
-object CatVariants {
- def apply(root: Configurable, input: List[File], output: File): CatVariants = {
- val cv = new CatVariants(root)
- cv.inputFiles = input
- cv.outputFile = output
- cv
- }
-}
\ No newline at end of file
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
deleted file mode 100644
index 343e2d769656dd6800d4cd552f51aa25cec7d28c..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
+++ /dev/null
@@ -1,80 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.utils.VcfUtils
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Gather, Input, Output }
-
-/**
- * Extension for CombineVariants from GATK
- *
- * Created by pjvan_thof on 2/26/15.
- *
- * @deprecated
- */
-class CombineVariants(val root: Configurable) extends Gatk {
- val analysisType = "CombineVariants"
-
- @Input(doc = "", required = true)
- var inputFiles: List[File] = Nil
-
- @Output(doc = "", required = true)
- var outputFile: File = null
-
- var setKey: String = null
- var rodPriorityList: String = null
- var minimumN: Int = config("minimumN", default = 1)
- var genotypeMergeOptions: Option[String] = config("genotypeMergeOptions")
- var excludeNonVariants: Boolean = false
-
- var inputMap: Map[File, String] = Map()
-
- def addInput(file: File, name: String): Unit = {
- inputFiles :+= file
- inputMap += file -> name
- }
-
- @Output
- @Gather(enabled = false)
- private var outputIndex: File = _
-
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- outputIndex = VcfUtils.getVcfIndexFile(outputFile)
- genotypeMergeOptions match {
- case Some("UNIQUIFY") | Some("PRIORITIZE") | Some("UNSORTED") | Some("REQUIRE_UNIQUE") | None =>
- case _ => throw new IllegalArgumentException("Wrong option for genotypeMergeOptions")
- }
- deps :::= inputFiles.filter(_.getName.endsWith("vcf.gz")).map(x => new File(x.getAbsolutePath + ".tbi"))
- deps = deps.distinct
- }
-
- override def cmdLine = super.cmdLine +
- (for (file <- inputFiles) yield {
- inputMap.get(file) match {
- case Some(name) => required("-V:" + name, file)
- case _ => required("-V", file)
- }
- }).mkString +
- required("-o", outputFile) +
- optional("--setKey", setKey) +
- optional("--rod_priority_list", rodPriorityList) +
- optional("-genotypeMergeOptions", genotypeMergeOptions) +
- conditional(excludeNonVariants, "--excludeNonVariants")
-}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/Gatk.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/Gatk.scala
deleted file mode 100644
index 92ca40e02d94e4935f3f1c031cf1371e4b77b8a2..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/Gatk.scala
+++ /dev/null
@@ -1,76 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.{ Version, BiopetJavaCommandLineFunction, Reference }
-import org.broadinstitute.gatk.utils.commandline.Input
-
-/**
- * General extension for GATK module
- *
- * Created by pjvan_thof on 2/26/15.
- *
- * @deprecated
- */
-abstract class Gatk extends BiopetJavaCommandLineFunction with Reference with Version {
- override def subPath = "gatk" :: super.subPath
-
- jarFile = config("gatk_jar")
-
- val analysisType: String
-
- override def defaultCoreMemory = 3.0
-
- @Input(required = true)
- var reference: File = null
-
- @Input(required = false)
- var gatkKey: Option[File] = config("gatk_key")
-
- @Input(required = false)
- var intervals: List[File] = config("intervals", default = Nil)
-
- @Input(required = false)
- var excludeIntervals: List[File] = config("exclude_intervals", default = Nil)
-
- @Input(required = false)
- var pedigree: List[File] = config("pedigree", default = Nil)
-
- var et: Option[String] = config("et")
-
- def versionRegex = """(.*)""".r
- override def versionExitcode = List(0, 1)
- def versionCommand = executable + " -jar " + jarFile + " -version"
-
- override def getVersion = super.getVersion.collect { case version => "Gatk " + version }
- override def dictRequired = true
-
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- if (reference == null) reference = referenceFasta()
- }
-
- override def cmdLine = super.cmdLine +
- required("-T", analysisType) +
- required("-R", reference) +
- optional("-K", gatkKey) +
- optional("-et", et) +
- repeat("-L", intervals) +
- repeat("-XL", excludeIntervals) +
- repeat("-ped", pedigree)
-}
\ No newline at end of file
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeConcordance.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeConcordance.scala
deleted file mode 100644
index 62d2457de0431b8c28ddb3e2eae58352a4b39b23..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeConcordance.scala
+++ /dev/null
@@ -1,96 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.summary.Summarizable
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-import org.broadinstitute.gatk.utils.report.{ GATKReportTable, GATKReport }
-
-/**
- * Extension for CombineVariants from GATK
- *
- * Created by pjvan_thof on 2/26/15.
- *
- * @deprecated
- */
-class GenotypeConcordance(val root: Configurable) extends Gatk with Summarizable {
- val analysisType = "GenotypeConcordance"
-
- @Input(required = true)
- var evalFile: File = null
-
- @Input(required = true)
- var compFile: File = null
-
- @Output(required = true)
- var outputFile: File = null
-
- var moltenize = true
-
- def summaryFiles = Map("output" -> outputFile)
-
- def summaryStats = {
- val report = new GATKReport(outputFile)
- val compProportions = report.getTable("GenotypeConcordance_CompProportions")
- val counts = report.getTable("GenotypeConcordance_Counts")
- val evalProportions = report.getTable("GenotypeConcordance_EvalProportions")
- val genotypeSummary = report.getTable("GenotypeConcordance_Summary")
- val siteSummary = report.getTable("SiteConcordance_Summary")
-
- val samples = for (i <- 0 until genotypeSummary.getNumRows) yield genotypeSummary.get(i, "Sample").toString
-
- def getMap(table: GATKReportTable, column: String) = samples.distinct.map(sample => sample -> {
- (for (i <- 0 until table.getNumRows if table.get(i, "Sample") == sample) yield s"${table.get(i, "Eval_Genotype")}__${table.get(i, "Comp_Genotype")}" -> table.get(i, column)).toMap
- }).toMap
-
- Map(
- "compProportions" -> getMap(compProportions, "Proportion"),
- "counts" -> getMap(counts, "Count"),
- "evalProportions" -> getMap(evalProportions, "Proportion"),
- "genotypeSummary" -> samples.distinct.map(sample => {
- val i = samples.indexOf(sample)
- sample -> Map(
- "Non-Reference_Discrepancy" -> genotypeSummary.get(i, "Non-Reference_Discrepancy"),
- "Non-Reference_Sensitivity" -> genotypeSummary.get(i, "Non-Reference_Sensitivity"),
- "Overall_Genotype_Concordance" -> genotypeSummary.get(i, "Overall_Genotype_Concordance")
- )
- }).toMap,
- "siteSummary" -> Map(
- "ALLELES_MATCH" -> siteSummary.get(0, "ALLELES_MATCH"),
- "EVAL_SUPERSET_TRUTH" -> siteSummary.get(0, "EVAL_SUPERSET_TRUTH"),
- "EVAL_SUBSET_TRUTH" -> siteSummary.get(0, "EVAL_SUBSET_TRUTH"),
- "ALLELES_DO_NOT_MATCH" -> siteSummary.get(0, "ALLELES_DO_NOT_MATCH"),
- "EVAL_ONLY" -> siteSummary.get(0, "EVAL_ONLY"),
- "TRUTH_ONLY" -> siteSummary.get(0, "TRUTH_ONLY")
- )
- )
- }
-
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- deps :::= (evalFile :: compFile :: Nil).filter(_.getName.endsWith("vcf.gz")).map(x => new File(x.getAbsolutePath + ".tbi"))
- deps = deps.distinct
- }
-
- override def cmdLine = super.cmdLine +
- required("--eval", evalFile) +
- required("--comp", compFile) +
- required("-o", outputFile) +
- conditional(moltenize, "--moltenize")
-}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
deleted file mode 100644
index d98abff1485b59cd0424eff47d03b0d1dbfe585d..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
+++ /dev/null
@@ -1,69 +0,0 @@
-/**
- * Biopet is built on top of GATK Queue for building bioinformatic
- * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
- * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
- * should also be able to execute Biopet tools and pipelines.
- *
- * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
- *
- * Contact us at: sasc@lumc.nl
- *
- * A dual licensing mode is applied. The source code within this project that are
- * not part of GATK Queue is freely available for non-commercial use under an AGPL
- * license; For commercial users or users who do not want to follow the AGPL
- * license, please contact us to obtain a separate license.
- */
-package nl.lumc.sasc.biopet.extensions.gatk
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.utils.VcfUtils
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Gather, Input, Output }
-
-/**
- * Extension for CombineVariants from GATK
- *
- * Created by pjvan_thof on 2/26/15.
- *
- * @deprecated
- */
-class SelectVariants(val root: Configurable) extends Gatk {
- val analysisType = "SelectVariants"
-
- @Input(doc = "", required = true)
- var inputFiles: List[File] = Nil
-
- @Output(doc = "", required = true)
- var outputFile: File = null
-
- var excludeNonVariants: Boolean = false
-
- var inputMap: Map[File, String] = Map()
-
- def addInput(file: File, name: String): Unit = {
- inputFiles :+= file
- inputMap += file -> name
- }
-
- @Output
- @Gather(enabled = false)
- private var outputIndex: File = _
-
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- outputIndex = VcfUtils.getVcfIndexFile(outputFile)
- deps :::= inputFiles.filter(_.getName.endsWith("vcf.gz")).map(x => new File(x.getAbsolutePath + ".tbi"))
- deps = deps.distinct
- }
-
- override def cmdLine = super.cmdLine +
- (for (file <- inputFiles) yield {
- inputMap.get(file) match {
- case Some(name) => required("-V:" + name, file)
- case _ => required("-V", file)
- }
- }).mkString +
- required("-o", outputFile) +
- conditional(excludeNonVariants, "--excludeNonVariants")
-}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeConcordance.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeConcordance.scala
new file mode 100644
index 0000000000000000000000000000000000000000..c5cf2d28ab375280d412ddcfbf26217dcee771ef
--- /dev/null
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeConcordance.scala
@@ -0,0 +1,122 @@
+package nl.lumc.sasc.biopet.extensions.gatk.broad
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
+import nl.lumc.sasc.biopet.core.summary.Summarizable
+import nl.lumc.sasc.biopet.utils.VcfUtils
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
+import org.broadinstitute.gatk.utils.commandline.{Argument, Gather, Output, _}
+import org.broadinstitute.gatk.utils.report.{GATKReport, GATKReportTable}
+
+class GenotypeConcordance(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction with Summarizable {
+ analysisName = "GenotypeConcordance"
+ val analysis_type = "GenotypeConcordance"
+ scatterClass = classOf[LocusScatterFunction]
+ setupScatterFunction = { case scatter: GATKScatterFunction => scatter.includeUnmapped = false }
+
+ /** The variants and genotypes to evaluate */
+ @Input(fullName="eval", shortName="eval", doc="The variants and genotypes to evaluate", required=true, exclusiveOf="", validation="")
+ var eval: File = _
+
+ /** The variants and genotypes to compare against */
+ @Input(fullName="comp", shortName="comp", doc="The variants and genotypes to compare against", required=true, exclusiveOf="", validation="")
+ var comp: File = _
+
+ /** Filters will be ignored */
+ @Argument(fullName="ignoreFilters", shortName="", doc="Filters will be ignored", required=false, exclusiveOf="", validation="")
+ var ignoreFilters: Boolean = config("ignoreFilters", default = false)
+
+ /** One or more criteria to use to set EVAL genotypes to no-call. These genotype-level filters are only applied to the EVAL rod. */
+ @Argument(fullName="genotypeFilterExpressionEval", shortName="gfe", doc="One or more criteria to use to set EVAL genotypes to no-call. These genotype-level filters are only applied to the EVAL rod.", required=false, exclusiveOf="", validation="")
+ var genotypeFilterExpressionEval: List[String] = config("genotypeFilterExpressionEval", default = Nil)
+
+ /** One or more criteria to use to set COMP genotypes to no-call. These genotype-level filters are only applied to the COMP rod. */
+ @Argument(fullName="genotypeFilterExpressionComp", shortName="gfc", doc="One or more criteria to use to set COMP genotypes to no-call. These genotype-level filters are only applied to the COMP rod.", required=false, exclusiveOf="", validation="")
+ var genotypeFilterExpressionComp: Seq[String] = config("genotypeFilterExpressionComp", default = Nil)
+
+ /** Molten rather than tabular output */
+ @Argument(fullName="moltenize", shortName="moltenize", doc="Molten rather than tabular output", required=false, exclusiveOf="", validation="")
+ var moltenize: Boolean = config("moltenize", default = true)
+
+ /** File to output the discordant sites and genotypes. */
+ @Output(fullName="printInterestingSites", shortName="sites", doc="File to output the discordant sites and genotypes.", required=false, exclusiveOf="", validation="")
+ var printInterestingSites: Option[File] = None
+
+ /** An output file created by the walker. Will overwrite contents if file exists */
+ @Output(fullName="out", shortName="o", doc="An output file created by the walker. Will overwrite contents if file exists", required=false, exclusiveOf="", validation="")
+ @Gather(classOf[org.broadinstitute.gatk.queue.function.scattergather.SimpleTextGatherFunction])
+ var out: File = _
+
+ /** Filter out reads with CIGAR containing the N operator, instead of failing with an error */
+ @Argument(fullName="filter_reads_with_N_cigar", shortName="filterRNC", doc="Filter out reads with CIGAR containing the N operator, instead of failing with an error", required=false, exclusiveOf="", validation="")
+ var filter_reads_with_N_cigar: Boolean = config("filter_reads_with_N_cigar", default = false)
+
+ /** Filter out reads with mismatching numbers of bases and base qualities, instead of failing with an error */
+ @Argument(fullName="filter_mismatching_base_and_quals", shortName="filterMBQ", doc="Filter out reads with mismatching numbers of bases and base qualities, instead of failing with an error", required=false, exclusiveOf="", validation="")
+ var filter_mismatching_base_and_quals: Boolean = config("filter_mismatching_base_and_quals", default = false)
+
+ /** Filter out reads with no stored bases (i.e. '*' where the sequence should be), instead of failing with an error */
+ @Argument(fullName="filter_bases_not_stored", shortName="filterNoBases", doc="Filter out reads with no stored bases (i.e. '*' where the sequence should be), instead of failing with an error", required=false, exclusiveOf="", validation="")
+ var filter_bases_not_stored: Boolean = config("filter_bases_not_stored", default = false)
+
+ def summaryFiles = Map("output" -> out)
+
+ def summaryStats = {
+ val report = new GATKReport(out)
+ val compProportions = report.getTable("GenotypeConcordance_CompProportions")
+ val counts = report.getTable("GenotypeConcordance_Counts")
+ val evalProportions = report.getTable("GenotypeConcordance_EvalProportions")
+ val genotypeSummary = report.getTable("GenotypeConcordance_Summary")
+ val siteSummary = report.getTable("SiteConcordance_Summary")
+
+ val samples = for (i <- 0 until genotypeSummary.getNumRows) yield genotypeSummary.get(i, "Sample").toString
+
+ def getMap(table: GATKReportTable, column: String) = samples.distinct.map(sample => sample -> {
+ (for (i <- 0 until table.getNumRows if table.get(i, "Sample") == sample) yield s"${table.get(i, "Eval_Genotype")}__${table.get(i, "Comp_Genotype")}" -> table.get(i, column)).toMap
+ }).toMap
+
+ Map(
+ "compProportions" -> getMap(compProportions, "Proportion"),
+ "counts" -> getMap(counts, "Count"),
+ "evalProportions" -> getMap(evalProportions, "Proportion"),
+ "genotypeSummary" -> samples.distinct.map(sample => {
+ val i = samples.indexOf(sample)
+ sample -> Map(
+ "Non-Reference_Discrepancy" -> genotypeSummary.get(i, "Non-Reference_Discrepancy"),
+ "Non-Reference_Sensitivity" -> genotypeSummary.get(i, "Non-Reference_Sensitivity"),
+ "Overall_Genotype_Concordance" -> genotypeSummary.get(i, "Overall_Genotype_Concordance")
+ )
+ }).toMap,
+ "siteSummary" -> Map(
+ "ALLELES_MATCH" -> siteSummary.get(0, "ALLELES_MATCH"),
+ "EVAL_SUPERSET_TRUTH" -> siteSummary.get(0, "EVAL_SUPERSET_TRUTH"),
+ "EVAL_SUBSET_TRUTH" -> siteSummary.get(0, "EVAL_SUBSET_TRUTH"),
+ "ALLELES_DO_NOT_MATCH" -> siteSummary.get(0, "ALLELES_DO_NOT_MATCH"),
+ "EVAL_ONLY" -> siteSummary.get(0, "EVAL_ONLY"),
+ "TRUTH_ONLY" -> siteSummary.get(0, "TRUTH_ONLY")
+ )
+ )
+ }
+
+
+ override def beforeGraph() {
+ super.beforeGraph()
+ if (eval != null) deps :+= VcfUtils.getVcfIndexFile(eval)
+ if (comp != null) deps :+= VcfUtils.getVcfIndexFile(comp)
+ }
+
+ override def cmdLine = super.cmdLine +
+ required(TaggedFile.formatCommandLineParameter("-eval", eval), eval, spaceSeparated=true, escape=true, format="%s") +
+ required(TaggedFile.formatCommandLineParameter("-comp", comp), comp, spaceSeparated=true, escape=true, format="%s") +
+ conditional(ignoreFilters, "--ignoreFilters", escape=true, format="%s") +
+ repeat("-gfe", genotypeFilterExpressionEval, spaceSeparated=true, escape=true, format="%s") +
+ repeat("-gfc", genotypeFilterExpressionComp, spaceSeparated=true, escape=true, format="%s") +
+ conditional(moltenize, "-moltenize", escape=true, format="%s") +
+ optional("-sites", printInterestingSites, spaceSeparated=true, escape=true, format="%s") +
+ optional("-o", out, spaceSeparated=true, escape=true, format="%s") +
+ conditional(filter_reads_with_N_cigar, "-filterRNC", escape=true, format="%s") +
+ conditional(filter_mismatching_base_and_quals, "-filterMBQ", escape=true, format="%s") +
+ conditional(filter_bases_not_stored, "-filterNoBases", escape=true, format="%s")
+}
diff --git a/generate-indexes/src/main/scala/nl/lumc/sasc/biopet/pipelines/GenerateIndexes.scala b/generate-indexes/src/main/scala/nl/lumc/sasc/biopet/pipelines/GenerateIndexes.scala
index 6e2aa683f8e6e2abe31e2e8307d71db8c41c5258..ebba259271ebb0ea1174f56e5500468d04873387 100644
--- a/generate-indexes/src/main/scala/nl/lumc/sasc/biopet/pipelines/GenerateIndexes.scala
+++ b/generate-indexes/src/main/scala/nl/lumc/sasc/biopet/pipelines/GenerateIndexes.scala
@@ -24,7 +24,7 @@ import nl.lumc.sasc.biopet.core.{ BiopetCommandLineFunction, BiopetQScript, Pipe
import nl.lumc.sasc.biopet.extensions._
import nl.lumc.sasc.biopet.extensions.bowtie.{ Bowtie2Build, BowtieBuild }
import nl.lumc.sasc.biopet.extensions.bwa.BwaIndex
-import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
+import nl.lumc.sasc.biopet.extensions.gatk.broad.CombineVariants
import nl.lumc.sasc.biopet.extensions.gmap.GmapBuild
import nl.lumc.sasc.biopet.extensions.picard.CreateSequenceDictionary
import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsFaidx
@@ -173,7 +173,7 @@ class GenerateIndexes(val root: Configurable) extends QScript with BiopetQScript
genomeConfig.get("dbsnp_vcf_uri").foreach { dbsnpUri =>
val cv = new CombineVariants(this)
- cv.reference = fastaFile
+ cv.reference_sequence = fastaFile
cv.deps ::= createDict.output
def addDownload(uri: String): Unit = {
val curl = new Curl(this)
@@ -181,7 +181,7 @@ class GenerateIndexes(val root: Configurable) extends QScript with BiopetQScript
curl.output = new File(annotationDir, new File(curl.url).getName)
curl.isIntermediate = true
add(curl)
- cv.inputFiles ::= curl.output
+ cv.variant :+= curl.output
val tabix = new Tabix(this)
tabix.input = curl.output
@@ -198,7 +198,7 @@ class GenerateIndexes(val root: Configurable) extends QScript with BiopetQScript
case _ => addDownload(dbsnpUri.toString)
}
- cv.outputFile = new File(annotationDir, "dbsnp.vcf.gz")
+ cv.out = new File(annotationDir, "dbsnp.vcf.gz")
add(cv)
}
diff --git a/gwas-test/src/main/scala/nl/lumc/sasc/biopet/pipelines/gwastest/GwasTest.scala b/gwas-test/src/main/scala/nl/lumc/sasc/biopet/pipelines/gwastest/GwasTest.scala
index afc6bbdc3ba737db63f5c4270009de0a60b8deaa..52f769fff21887a7556b97c18ba8b1f24b023d73 100644
--- a/gwas-test/src/main/scala/nl/lumc/sasc/biopet/pipelines/gwastest/GwasTest.scala
+++ b/gwas-test/src/main/scala/nl/lumc/sasc/biopet/pipelines/gwastest/GwasTest.scala
@@ -6,7 +6,7 @@ import java.util
import htsjdk.samtools.reference.FastaSequenceFile
import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand, Reference }
import nl.lumc.sasc.biopet.extensions.Snptest
-import nl.lumc.sasc.biopet.extensions.gatk.{ CatVariants, SelectVariants }
+import nl.lumc.sasc.biopet.extensions.gatk.broad.{ CatVariants, SelectVariants }
import nl.lumc.sasc.biopet.extensions.tools.{ GensToVcf, SnptestToVcf }
import nl.lumc.sasc.biopet.pipelines.gwastest.impute.ImputeOutput
import nl.lumc.sasc.biopet.utils.Logging
@@ -82,10 +82,10 @@ class GwasTest(val root: Configurable) extends QScript with BiopetQScript with R
gensToVcf.outputVcf = new File(outputDirGens, gen._1.genotypes.getName + s".${gen._2}.vcf.gz")
gensToVcf.isIntermediate = true
add(gensToVcf)
- cvChr.inputFiles :+= gensToVcf.outputVcf
+ cvChr.variant :+= gensToVcf.outputVcf
}
add(cvChr)
- cvTotal.inputFiles :+= cvChr.outputFile
+ cvTotal.variant :+= cvChr.outputFile
contig -> cvChr.outputFile
}
add(cvTotal)
@@ -105,14 +105,14 @@ class GwasTest(val root: Configurable) extends QScript with BiopetQScript with R
bedFile.deleteOnExit()
val sv = new SelectVariants(this)
- sv.inputFiles :+= chrVcfFiles.getOrElse(region.chr, vcfFile)
- sv.outputFile = new File(regionDir, s"$name.vcf.gz")
+ sv.variant :+= chrVcfFiles.getOrElse(region.chr, vcfFile)
+ sv.out = new File(regionDir, s"$name.vcf.gz")
sv.intervals :+= bedFile
sv.isIntermediate = true
add(sv)
val snptest = new Snptest(this)
- snptest.inputGenotypes :+= sv.outputFile
+ snptest.inputGenotypes :+= sv.out
snptest.inputSampleFiles :+= phenotypeFile
snptest.outputFile = Some(new File(regionDir, s"$name.snptest"))
add(snptest)
@@ -127,7 +127,7 @@ class GwasTest(val root: Configurable) extends QScript with BiopetQScript with R
}
val cv = new CatVariants(this)
- cv.inputFiles = snpTests.map(_._2).toList
+ cv.variant = snpTests.map(_._2).toList
cv.outputFile = new File(outputDir, "snptest" + File.separator + "snptest.vcf.gz")
add(cv)
}
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcalling.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcalling.scala
index 6020412479bf3331a35ff69c82327c212d889352..acb2076013c56d8d2ef06479f942ab1775ab7abf 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcalling.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcalling.scala
@@ -15,17 +15,18 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva
-import nl.lumc.sasc.biopet.core.{ PipelineCommand, Reference, SampleLibraryTag }
+import nl.lumc.sasc.biopet.core.{PipelineCommand, Reference, SampleLibraryTag}
import nl.lumc.sasc.biopet.core.summary.SummaryQScript
import nl.lumc.sasc.biopet.extensions.Tabix
-import nl.lumc.sasc.biopet.extensions.gatk.{ CombineVariants, GenotypeConcordance }
+import nl.lumc.sasc.biopet.extensions.gatk.broad.{CombineVariants, GenotypeConcordance}
import nl.lumc.sasc.biopet.extensions.tools.VcfStats
-import nl.lumc.sasc.biopet.extensions.vt.{ VtDecompose, VtNormalize }
+import nl.lumc.sasc.biopet.extensions.vt.{VtDecompose, VtNormalize}
import nl.lumc.sasc.biopet.pipelines.bammetrics.TargetRegions
-import nl.lumc.sasc.biopet.pipelines.shiva.variantcallers.{ VarscanCnsSingleSample, _ }
-import nl.lumc.sasc.biopet.utils.{ BamUtils, Logging }
+import nl.lumc.sasc.biopet.pipelines.shiva.variantcallers.{VarscanCnsSingleSample, _}
+import nl.lumc.sasc.biopet.utils.{BamUtils, Logging}
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.queue.QScript
+import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
/**
* Implementation of ShivaVariantcalling
@@ -86,10 +87,10 @@ class ShivaVariantcalling(val root: Configurable) extends QScript
require(callers.nonEmpty, "must select at least 1 variantcaller, choices are: " + callersList.map(_.name).mkString(", "))
val cv = new CombineVariants(qscript)
- cv.outputFile = finalFile
+ cv.out = finalFile
cv.setKey = "VariantCaller"
- cv.genotypeMergeOptions = Some("PRIORITIZE")
- cv.rodPriorityList = callers.map(_.name).mkString(",")
+ cv.genotypemergeoption = Some("PRIORITIZE")
+ cv.rod_priority_list = Some(callers.map(_.name).mkString(","))
for (caller <- callers) {
caller.inputBams = inputBams
caller.namePrefix = namePrefix
@@ -110,17 +111,17 @@ class ShivaVariantcalling(val root: Configurable) extends QScript
vtDecompose.inputVcf = vtNormalize.outputVcf
vtDecompose.outputVcf = swapExt(caller.outputDir, vtNormalize.outputVcf, ".vcf.gz", ".decompose.vcf.gz")
add(vtDecompose, Tabix(this, vtDecompose.outputVcf))
- cv.addInput(vtDecompose.outputVcf, caller.name)
+ cv.variant :+= TaggedFile(vtDecompose.outputVcf, caller.name)
} else if (normalize && !decompose) {
vtNormalize.outputVcf = swapExt(caller.outputDir, caller.outputFile, ".vcf.gz", ".normalized.vcf.gz")
add(vtNormalize, Tabix(this, vtNormalize.outputVcf))
- cv.addInput(vtNormalize.outputVcf, caller.name)
+ cv.variant :+= TaggedFile(vtNormalize.outputVcf, caller.name)
} else if (!normalize && decompose) {
vtDecompose.inputVcf = caller.outputFile
vtDecompose.outputVcf = swapExt(caller.outputDir, caller.outputFile, ".vcf.gz", ".decompose.vcf.gz")
add(vtDecompose, Tabix(this, vtDecompose.outputVcf))
- cv.addInput(vtDecompose.outputVcf, caller.name)
- } else cv.addInput(caller.outputFile, caller.name)
+ cv.variant :+= TaggedFile(vtDecompose.outputVcf, caller.name)
+ } else cv.variant :+= TaggedFile(caller.outputFile, caller.name)
}
add(cv)
@@ -139,9 +140,9 @@ class ShivaVariantcalling(val root: Configurable) extends QScript
referenceVcf.foreach(referenceVcfFile => {
val gc = new GenotypeConcordance(this)
- gc.evalFile = vcfFile
- gc.compFile = referenceVcfFile
- gc.outputFile = new File(vcfFile.getParentFile, s"$namePrefix-genotype_concordance.$name.txt")
+ gc.eval = vcfFile
+ gc.comp = referenceVcfFile
+ gc.out = new File(vcfFile.getParentFile, s"$namePrefix-genotype_concordance.$name.txt")
referenceVcfRegions.foreach(gc.intervals ::= _)
add(gc)
addSummarizable(gc, s"$namePrefix-genotype_concordance-$name")
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala
index 98fe0e0a06342cee60db461acc33f1a64b5c23b2..ddf7af84be9b26dcf759273eac370abdeb76a1b7 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/svcallers/Delly.scala
@@ -16,7 +16,7 @@
package nl.lumc.sasc.biopet.pipelines.shiva.svcallers
import nl.lumc.sasc.biopet.extensions.delly.DellyCaller
-import nl.lumc.sasc.biopet.extensions.gatk.CatVariants
+import nl.lumc.sasc.biopet.extensions.gatk.broad.CatVariants
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Script for sv caller delly */
@@ -41,7 +41,7 @@ class Delly(val root: Configurable) extends SvCaller {
delly.analysistype = "DEL"
delly.outputvcf = new File(dellyDir, sample + ".delly.del.vcf")
add(delly)
- catVariants.inputFiles :+= delly.outputvcf
+ catVariants.variant :+= delly.outputvcf
}
if (dup) {
val delly = new DellyCaller(this)
@@ -49,7 +49,7 @@ class Delly(val root: Configurable) extends SvCaller {
delly.analysistype = "DUP"
delly.outputvcf = new File(dellyDir, sample + ".delly.dup.vcf")
add(delly)
- catVariants.inputFiles :+= delly.outputvcf
+ catVariants.variant :+= delly.outputvcf
}
if (inv) {
val delly = new DellyCaller(this)
@@ -57,18 +57,18 @@ class Delly(val root: Configurable) extends SvCaller {
delly.analysistype = "INV"
delly.outputvcf = new File(dellyDir, sample + ".delly.inv.vcf")
add(delly)
- catVariants.inputFiles :+= delly.outputvcf
+ catVariants.variant :+= delly.outputvcf
}
if (tra) {
val delly = new DellyCaller(this)
delly.input = bamFile
delly.analysistype = "TRA"
delly.outputvcf = new File(dellyDir, sample + ".delly.tra.vcf")
- catVariants.inputFiles :+= delly.outputvcf
+ catVariants.variant :+= delly.outputvcf
add(delly)
}
- require(catVariants.inputFiles.nonEmpty, "Must atleast 1 SV-type be selected for Delly")
+ require(catVariants.variant.nonEmpty, "Must atleast 1 SV-type be selected for Delly")
add(catVariants)
addVCF(sample, catVariants.outputFile)
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/RawVcf.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/RawVcf.scala
index 847e671166191da3153cc2df818828c66de37aa1..4fe9d88c10e5fa63742aa20b57769c47b0a96b61 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/RawVcf.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/RawVcf.scala
@@ -17,7 +17,7 @@ package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
import java.io.File
-import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
+import nl.lumc.sasc.biopet.extensions.gatk.broad.CombineVariants
import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsMpileup
import nl.lumc.sasc.biopet.extensions.tools.{ VcfFilter, MpileupToVcf }
import nl.lumc.sasc.biopet.utils.config.Configurable
@@ -60,8 +60,8 @@ class RawVcf(val root: Configurable) extends Variantcaller {
}
val cv = new CombineVariants(this)
- cv.inputFiles = rawFiles.toList
- cv.outputFile = outputFile
+ cv.variant = rawFiles.toList
+ cv.out = outputFile
cv.setKey = "null"
cv.excludeNonVariants = !keepRefCalls
add(cv)
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala
index 9a0fb2839413948de68d3d16101fc4ce912df5b3..96c6d9a78bc42f561b3de20936bea603337135be 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/VarscanCnsSingleSample.scala
@@ -17,7 +17,7 @@ package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
import java.io.PrintWriter
-import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
+import nl.lumc.sasc.biopet.extensions.gatk.broad.CombineVariants
import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsMpileup
import nl.lumc.sasc.biopet.extensions.varscan.{ FixMpileup, VarscanMpileup2cns }
import nl.lumc.sasc.biopet.extensions.{ Bgzip, Tabix }
@@ -35,7 +35,8 @@ class VarscanCnsSingleSample(val root: Configurable) extends Variantcaller {
"disable_baq" -> true,
"depth" -> 1000000
),
- "varscanmpileup2cns" -> Map("strand_filter" -> 0)
+ "varscanmpileup2cns" -> Map("strand_filter" -> 0),
+ "combinevariants" -> Map("scattercount" -> 20)
)
override def fixedValues = Map(
@@ -67,9 +68,9 @@ class VarscanCnsSingleSample(val root: Configurable) extends Variantcaller {
}
val cv = new CombineVariants(this)
- cv.inputFiles = sampleVcfs
- cv.outputFile = outputFile
- cv.setKey = "null"
+ cv.variant = sampleVcfs
+ cv.out = outputFile
+ cv.setKey = Some("null")
cv.excludeNonVariants = true
add(cv)
}
diff --git a/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala b/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
index f85137cc27a87069021752d42517e3fe6685359a..e3e7d00d40dadf49ffd4390652f8d417f65653ae 100644
--- a/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
+++ b/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
@@ -12,7 +12,7 @@ import nl.lumc.sasc.biopet.core.BiopetPipe
import nl.lumc.sasc.biopet.extensions.Freebayes
import nl.lumc.sasc.biopet.extensions.bcftools.{ BcftoolsCall, BcftoolsMerge }
import nl.lumc.sasc.biopet.utils.config.Config
-import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
+import nl.lumc.sasc.biopet.extensions.gatk.broad.CombineVariants
import nl.lumc.sasc.biopet.extensions.gatk.broad.{ HaplotypeCaller, UnifiedGenotyper }
import nl.lumc.sasc.biopet.extensions.tools.{ MpileupToVcf, VcfFilter, VcfStats }
import nl.lumc.sasc.biopet.utils.ConfigUtils