diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Grep.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Grep.scala
index 606c7af5dd84538cce4d283eff06087c10aabb2c..2f7d65916c69340336474370cad52a526cd7f465 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Grep.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/Grep.scala
@@ -7,8 +7,8 @@ import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
/**
- * Created by pjvanthof on 30/03/16.
- */
+ * Created by pjvanthof on 30/03/16.
+ */
class Grep(val root: Configurable) extends BiopetCommandLineFunction {
@Input(doc = "Input file", required = true)
var input: File = _
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/AnalyzeCovariates.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
similarity index 98%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/AnalyzeCovariates.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
index b501d47de6cb0899d8e02ae8a4372fd50de4f7e1..c0740c64008c0d887a879e445c08e41dc1a96cd6 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/AnalyzeCovariates.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
@@ -1,9 +1,9 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
+import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Output, _ }
class AnalyzeCovariates(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/ApplyRecalibration.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
similarity index 96%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/ApplyRecalibration.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
index a84aa4b4b8728a1a5c7bbab442a4d905b626821a..b3be8d8578a2a0563274bfc88fa5cf8eb14df543 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/ApplyRecalibration.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
@@ -1,15 +1,12 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
import nl.lumc.sasc.biopet.utils.VcfUtils
-import org.broadinstitute.gatk.utils.commandline.Argument
-import org.broadinstitute.gatk.utils.commandline.Gather
-import org.broadinstitute.gatk.utils.commandline.Input
-import org.broadinstitute.gatk.utils.commandline.Output
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
+import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Input, Output }
class ApplyRecalibration(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
def analysis_type = "ApplyRecalibration"
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/BamGatherFunction.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BamGatherFunction.scala
similarity index 95%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/BamGatherFunction.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BamGatherFunction.scala
index eb821f0e47ec6c5b3444cb8bed7172ae6dc906eb..c7a55537e2750e1cb316dfe51d63f9874faa6a72 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/BamGatherFunction.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BamGatherFunction.scala
@@ -1,9 +1,8 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
-
-import org.broadinstitute.gatk.queue.function.scattergather.GatherFunction
+package nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import nl.lumc.sasc.biopet.extensions.picard.MergeSamFiles
+import org.broadinstitute.gatk.queue.function.scattergather.GatherFunction
/**
* Merges BAM files using htsjdk.samtools.MergeSamFiles.
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/BaseRecalibrator.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
similarity index 98%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/BaseRecalibrator.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
index 828beeb64ea6396437fd195dbdb4718e2417f24a..7e5bbfd3ff4645d11bd2ee173005c713bf0f2458 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/BaseRecalibrator.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
@@ -1,11 +1,10 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.{ TaggedFile }
-import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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, _ }
//TODO: check gathering
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
index ceceed5f64ba51a75b098e4cd1b18beaa4f1894d..4d712a8407abb8f09b8e6e7fdcceaba8d11d2bb4 100644
--- 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
@@ -1,58 +1,56 @@
-/**
- * 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.core.BiopetJavaCommandLineFunction
import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
+import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Input, Output }
-class CatVariants(val root: Configurable) extends BiopetJavaCommandLineFunction with Reference {
+class CatVariants(val root: Configurable) extends BiopetJavaCommandLineFunction {
+ analysisName = "CatVariants"
+ javaMainClass = "org.broadinstitute.gatk.tools.CatVariants"
- javaMainClass = classOf[org.broadinstitute.gatk.tools.CatVariants].getName
+ /** genome reference file <name>.fasta */
+ @Input(fullName = "reference", shortName = "R", doc = "genome reference file <name>.fasta", required = true, exclusiveOf = "", validation = "")
+ var reference: File = _
- @Input(required = true)
- var inputFiles: List[File] = Nil
+ /** Input VCF file/s */
+ @Input(fullName = "variant", shortName = "V", doc = "Input VCF file/s", required = true, exclusiveOf = "", validation = "")
+ var variant: Seq[File] = Nil
- @Output(required = true)
- var outputFile: File = null
+ /** output file */
+ @Output(fullName = "outputFile", shortName = "out", doc = "output file", required = true, exclusiveOf = "", validation = "")
+ @Gather(classOf[org.broadinstitute.gatk.queue.function.scattergather.SimpleTextGatherFunction])
+ var outputFile: File = _
- @Input
- var reference: File = null
+ /** assumeSorted should be true if the input files are already sorted (based on the position of the variants) */
+ @Argument(fullName = "assumeSorted", shortName = "assumeSorted", doc = "assumeSorted should be true if the input files are already sorted (based on the position of the variants)", required = false, exclusiveOf = "", validation = "")
+ var assumeSorted: Boolean = _
- var assumeSorted = false
+ /** which type of IndexCreator to use for VCF/BCF indices */
+ @Argument(fullName = "variant_index_type", shortName = "", doc = "which type of IndexCreator to use for VCF/BCF indices", required = false, exclusiveOf = "", validation = "")
+ var variant_index_type: Option[String] = None
- override def beforeGraph(): Unit = {
- super.beforeGraph()
- if (reference == null) reference = referenceFasta()
- }
+ /** the parameter (bin width or features per bin) to pass to the VCF/BCF IndexCreator */
+ @Argument(fullName = "variant_index_parameter", shortName = "", doc = "the parameter (bin width or features per bin) to pass to the VCF/BCF IndexCreator", required = false, exclusiveOf = "", validation = "")
+ var variant_index_parameter: Option[Int] = None
+
+ /** Set the minimum level of logging */
+ @Argument(fullName = "logging_level", shortName = "l", doc = "Set the minimum level of logging", required = false, exclusiveOf = "", validation = "")
+ var logging_level: String = _
+
+ /** Set the logging location */
+ @Output(fullName = "log_to_file", shortName = "log", doc = "Set the logging location", required = false, exclusiveOf = "", validation = "")
+ @Gather(classOf[org.broadinstitute.gatk.queue.function.scattergather.SimpleTextGatherFunction])
+ var log_to_file: File = _
override def cmdLine = super.cmdLine +
- repeat("-V", inputFiles) +
- required("-out", outputFile) +
- required("-R", reference) +
- conditional(assumeSorted, "--assumeSorted")
+ required("-R", reference, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-V", variant, spaceSeparated = true, escape = true, format = "%s") +
+ required("-out", outputFile, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(assumeSorted, "-assumeSorted", escape = true, format = "%s") +
+ optional("--variant_index_type", variant_index_type, spaceSeparated = true, escape = true, format = "%s") +
+ optional("--variant_index_parameter", variant_index_parameter, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-l", logging_level, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-log", log_to_file, spaceSeparated = true, escape = true, format = "%s")
}
-
-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/broad/CatVariantsGather.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CatVariantsGather.scala
similarity index 96%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CatVariantsGather.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CatVariantsGather.scala
index e97d6affbf023455122c49b3df59900211df0bea..27c6cb7cadb59997c7dd0c2039e1f53c74f4f8e7 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CatVariantsGather.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CatVariantsGather.scala
@@ -1,4 +1,4 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CombineGVCFs.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CombineGVCFs.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
index e20331fe1b1c670acff8d1d1ca743585a8a0735f..ed0065e589e17000a4e4fb9742d4bca71f6622a1 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CombineGVCFs.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
@@ -1,11 +1,11 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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.{ Gather, Input, Output, _ }
class CombineGVCFs(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
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
index 343e2d769656dd6800d4cd552f51aa25cec7d28c..ba1740d3518e1ea6dbc17a9c60b0d6aa59abc9df 100644
--- 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
@@ -1,80 +1,128 @@
-/**
- * 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.ScatterGatherableFunction
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
- }
+import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
+import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Output, _ }
+
+class CombineVariants(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
+ def analysis_type = "CombineVariants"
+ scatterClass = classOf[LocusScatterFunction]
+ setupScatterFunction = { case scatter: GATKScatterFunction => scatter.includeUnmapped = false }
+
+ /** VCF files to merge together */
+ @Input(fullName = "variant", shortName = "V", doc = "VCF files to merge together", required = true, exclusiveOf = "", validation = "")
+ var variant: Seq[File] = Nil
+
+ /** File to which variants should be written */
+ @Output(fullName = "out", shortName = "o", doc = "File to which variants should be written", required = false, exclusiveOf = "", validation = "")
+ @Gather(classOf[CatVariantsGatherer])
+ var out: File = _
+
+ /** Determines how we should merge genotype records for samples shared across the ROD files */
+ @Argument(fullName = "genotypemergeoption", shortName = "genotypeMergeOptions", doc = "Determines how we should merge genotype records for samples shared across the ROD files", required = false, exclusiveOf = "", validation = "")
+ var genotypemergeoption: Option[String] = config("genotypemergeoption")
+
+ /** Determines how we should handle records seen at the same site in the VCF, but with different FILTER fields */
+ @Argument(fullName = "filteredrecordsmergetype", shortName = "filteredRecordsMergeType", doc = "Determines how we should handle records seen at the same site in the VCF, but with different FILTER fields", required = false, exclusiveOf = "", validation = "")
+ var filteredrecordsmergetype: Option[String] = config("filteredrecordsmergetype")
+
+ /** Determines how we should handle records seen at the same site in the VCF, but with different allele types (for example, SNP vs. indel) */
+ @Argument(fullName = "multipleallelesmergetype", shortName = "multipleAllelesMergeType", doc = "Determines how we should handle records seen at the same site in the VCF, but with different allele types (for example, SNP vs. indel)", required = false, exclusiveOf = "", validation = "")
+ var multipleallelesmergetype: Option[String] = config("multipleallelesmergetype")
+
+ /** Ordered list specifying priority for merging */
+ @Argument(fullName = "rod_priority_list", shortName = "priority", doc = "Ordered list specifying priority for merging", required = false, exclusiveOf = "", validation = "")
+ var rod_priority_list: Option[String] = config("rod_priority_list")
+
+ /** Emit interesting sites requiring complex compatibility merging to file */
+ @Argument(fullName = "printComplexMerges", shortName = "printComplexMerges", doc = "Emit interesting sites requiring complex compatibility merging to file", required = false, exclusiveOf = "", validation = "")
+ var printComplexMerges: Boolean = config("printComplexMerges", default = false)
+
+ /** Treat filtered variants as uncalled */
+ @Argument(fullName = "filteredAreUncalled", shortName = "filteredAreUncalled", doc = "Treat filtered variants as uncalled", required = false, exclusiveOf = "", validation = "")
+ var filteredAreUncalled: Boolean = config("filteredAreUncalled", default = false)
+
+ /** Emit a sites-only file */
+ @Argument(fullName = "minimalVCF", shortName = "minimalVCF", doc = "Emit a sites-only file", required = false, exclusiveOf = "", validation = "")
+ var minimalVCF: Boolean = config("minimalVCF", default = false)
+
+ /** Exclude sites where no variation is present after merging */
+ @Argument(fullName = "excludeNonVariants", shortName = "env", doc = "Exclude sites where no variation is present after merging", required = false, exclusiveOf = "", validation = "")
+ var excludeNonVariants: Boolean = config("excludeNonVariants", default = false)
+
+ /** Key name for the set attribute */
+ @Argument(fullName = "setKey", shortName = "setKey", doc = "Key name for the set attribute", required = false, exclusiveOf = "", validation = "")
+ var setKey: Option[String] = config("set_key")
+
+ /** Assume input VCFs have identical sample sets and disjoint calls */
+ @Argument(fullName = "assumeIdenticalSamples", shortName = "assumeIdenticalSamples", doc = "Assume input VCFs have identical sample sets and disjoint calls", required = false, exclusiveOf = "", validation = "")
+ var assumeIdenticalSamples: Boolean = config("assumeIdenticalSamples", default = false)
+
+ /** Minimum number of input files the site must be observed in to be included */
+ @Argument(fullName = "minimumN", shortName = "minN", doc = "Minimum number of input files the site must be observed in to be included", required = false, exclusiveOf = "", validation = "")
+ var minimumN: Option[Int] = config("minimumN")
+
+ /** Do not output the command line to the header */
+ @Argument(fullName = "suppressCommandLineHeader", shortName = "suppressCommandLineHeader", doc = "Do not output the command line to the header", required = false, exclusiveOf = "", validation = "")
+ var suppressCommandLineHeader: Boolean = config("suppressCommandLineHeader", default = false)
+
+ /** Use the INFO content of the record with the highest AC */
+ @Argument(fullName = "mergeInfoWithMaxAC", shortName = "mergeInfoWithMaxAC", doc = "Use the INFO content of the record with the highest AC", required = false, exclusiveOf = "", validation = "")
+ var mergeInfoWithMaxAC: Boolean = config("mergeInfoWithMaxAC", default = false)
+
+ /** 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)
@Output
@Gather(enabled = false)
private var outputIndex: File = _
- override def beforeGraph(): Unit = {
+ override def beforeGraph() {
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
+ deps ++= variant.filter(orig => orig != null && (!orig.getName.endsWith(".list"))).map(orig => VcfUtils.getVcfIndexFile(orig))
+ if (out != null && !org.broadinstitute.gatk.utils.io.IOUtils.isSpecialFile(out))
+ outputIndex = VcfUtils.getVcfIndexFile(out)
}
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")
+ repeat("-V", variant, formatPrefix = TaggedFile.formatCommandLineParameter, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-o", out, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-genotypeMergeOptions", genotypemergeoption, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-filteredRecordsMergeType", filteredrecordsmergetype, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-multipleAllelesMergeType", multipleallelesmergetype, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-priority", rod_priority_list, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(printComplexMerges, "-printComplexMerges", escape = true, format = "%s") +
+ conditional(filteredAreUncalled, "-filteredAreUncalled", escape = true, format = "%s") +
+ conditional(minimalVCF, "-minimalVCF", escape = true, format = "%s") +
+ conditional(excludeNonVariants, "-env", escape = true, format = "%s") +
+ optional("-setKey", setKey, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(assumeIdenticalSamples, "-assumeIdenticalSamples", escape = true, format = "%s") +
+ optional("-minN", minimumN, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(suppressCommandLineHeader, "-suppressCommandLineHeader", escape = true, format = "%s") +
+ conditional(mergeInfoWithMaxAC, "-mergeInfoWithMaxAC", 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")
+}
+
+object CombineVariants {
+ def apply(root: Configurable, input: List[File], output: File): CombineVariants = {
+ val cv = new CombineVariants(root)
+ cv.variant = input
+ cv.out = output
+ cv
+ }
}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CommandLineGATK.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CommandLineGATK.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CommandLineGATK.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CommandLineGATK.scala
index 3e8091437d7bfe377748a827fef43655cf5b65b4..7fbba210ce42d99573c3dfd127a45ab9346f438a 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CommandLineGATK.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CommandLineGATK.scala
@@ -1,4 +1,4 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/ContigScatterFunction.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ContigScatterFunction.scala
similarity index 88%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/ContigScatterFunction.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ContigScatterFunction.scala
index 12350d3ad5d891e410f15dc90662645c3ceb2319..abfc807c26b7a88623b4b3ec649b010cb3d5d526 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/ContigScatterFunction.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ContigScatterFunction.scala
@@ -1,8 +1,9 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
-import collection.JavaConversions._
-import org.broadinstitute.gatk.utils.interval.IntervalUtils
import org.broadinstitute.gatk.queue.function.InProcessFunction
+import org.broadinstitute.gatk.utils.interval.IntervalUtils
+
+import scala.collection.JavaConversions._
/**
* Splits intervals by contig instead of evenly.
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/broad/GatkScatterFunction.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkScatterFunction.scala
similarity index 97%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GatkScatterFunction.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkScatterFunction.scala
index f2399b946ca51488bc102b90c9b96f4368f91147..d49b4d34372dfebdd5eafb6469d643e3067a8d4b 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GatkScatterFunction.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkScatterFunction.scala
@@ -1,12 +1,12 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
-import org.broadinstitute.gatk.utils.interval.IntervalUtils
import java.io.File
import org.broadinstitute.gatk.queue.extensions.gatk.GATKIntervals
-import org.broadinstitute.gatk.utils.io.IOUtils
import org.broadinstitute.gatk.queue.function.scattergather.{ CloneFunction, ScatterFunction }
-import org.broadinstitute.gatk.utils.commandline.{ Output, _ }
+import org.broadinstitute.gatk.utils.commandline.Output
+import org.broadinstitute.gatk.utils.interval.IntervalUtils
+import org.broadinstitute.gatk.utils.io.IOUtils
trait GATKScatterFunction extends ScatterFunction {
/* The runtime field to set for specifying intervals. */
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
index 62d2457de0431b8c28ddb3e2eae58352a4b39b23..aea609fb98b311748e98cd044cf0b454a88bfe94 100644
--- 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
@@ -1,52 +1,70 @@
-/**
- * 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.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.utils.commandline.{ Input, Output }
-import org.broadinstitute.gatk.utils.report.{ GATKReportTable, GATKReport }
+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 }
-/**
- * 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"
+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 }
- @Input(required = true)
- var evalFile: File = null
+ /** 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 = _
- @Input(required = true)
- var compFile: File = null
+ /** 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 = _
- @Output(required = true)
- var outputFile: File = null
+ /** Filters will be ignored */
+ @Argument(fullName = "ignoreFilters", shortName = "", doc = "Filters will be ignored", required = false, exclusiveOf = "", validation = "")
+ var ignoreFilters: Boolean = config("ignoreFilters", default = false)
- var moltenize = true
+ /** 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)
- def summaryFiles = Map("output" -> outputFile)
+ /** 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(outputFile)
+ val report = new GATKReport(out)
val compProportions = report.getTable("GenotypeConcordance_CompProportions")
val counts = report.getTable("GenotypeConcordance_Counts")
val evalProportions = report.getTable("GenotypeConcordance_EvalProportions")
@@ -82,15 +100,22 @@ class GenotypeConcordance(val root: Configurable) extends Gatk with Summarizable
)
}
- override def beforeGraph(): Unit = {
+ override def beforeGraph() {
super.beforeGraph()
- deps :::= (evalFile :: compFile :: Nil).filter(_.getName.endsWith("vcf.gz")).map(x => new File(x.getAbsolutePath + ".tbi"))
- deps = deps.distinct
+ if (eval != null) deps :+= VcfUtils.getVcfIndexFile(eval)
+ if (comp != null) deps :+= VcfUtils.getVcfIndexFile(comp)
}
override def cmdLine = super.cmdLine +
- required("--eval", evalFile) +
- required("--comp", compFile) +
- required("-o", outputFile) +
- conditional(moltenize, "--moltenize")
+ 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/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeGVCFs.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeGVCFs.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
index b1a54e34f4b9a079fef323110c2b61b7d9c5ad25..650340d63c1be0ba9195609a616ddddb4abee8ef 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GenotypeGVCFs.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
@@ -1,11 +1,11 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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, _ }
class GenotypeGVCFs(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/HaplotypeCaller.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/HaplotypeCaller.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
index 5ffdcb306b32bcc06152fd3e1a7457715443cee9..9eac2ba9e3d4974e7b479addcb3d0f1dadf5ef56 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/HaplotypeCaller.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
@@ -1,10 +1,10 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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, Input, Output }
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/IndelRealigner.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/IndelRealigner.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
index 34b7c58f9af92fdaee68bb710fc800779984e953..7d16d832892a0daaffd999f549f5fd00f327b51c 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/IndelRealigner.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
@@ -1,11 +1,11 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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, _ }
class IndelRealigner(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/LocusScatterFunction.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/LocusScatterFunction.scala
similarity index 87%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/LocusScatterFunction.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/LocusScatterFunction.scala
index 853d185b37d7cb1838b2c3f2928a91cdb8b82548..6a3b961ecbfb034465909714305e469af63a816a 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/LocusScatterFunction.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/LocusScatterFunction.scala
@@ -1,8 +1,9 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
-import collection.JavaConversions._
-import org.broadinstitute.gatk.utils.interval.IntervalUtils
import org.broadinstitute.gatk.queue.function.InProcessFunction
+import org.broadinstitute.gatk.utils.interval.IntervalUtils
+
+import scala.collection.JavaConversions._
/**
* A scatter function that divides down to the locus level.
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/PrintReads.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/PrintReads.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
index 9f18533cf8f78dcf9ebc8f3749112db9e6d6bd4f..6eaca11891f0d5a559cd3723f5ee8852800f9260 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/PrintReads.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
@@ -1,9 +1,9 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
+import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline._
class PrintReads(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/RealignerTargetCreator.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
similarity index 97%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/RealignerTargetCreator.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
index 383e74fbf0e4055c2fb5ec296b5a4ccaf72ead39..74ce632bd78dba9de535c3f3b4f82fb481976410 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/RealignerTargetCreator.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
@@ -1,11 +1,11 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.{ TaggedFile }
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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, Input, _ }
class RealignerTargetCreator(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
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
index d98abff1485b59cd0424eff47d03b0d1dbfe585d..a1ed7b732f9b72d1660c9ea8c1995e5fc0137a68 100644
--- 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
@@ -1,69 +1,262 @@
-/**
- * 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.ScatterGatherableFunction
import nl.lumc.sasc.biopet.utils.VcfUtils
import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.{ Gather, Input, Output }
+import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
+import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, 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"
+class SelectVariants(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
+ def analysis_type = "SelectVariants"
+ scatterClass = classOf[LocusScatterFunction]
+ setupScatterFunction = { case scatter: GATKScatterFunction => scatter.includeUnmapped = false }
- @Input(doc = "", required = true)
- var inputFiles: List[File] = Nil
+ /** Input VCF file */
+ @Input(fullName = "variant", shortName = "V", doc = "Input VCF file", required = true, exclusiveOf = "", validation = "")
+ var variant: File = _
- @Output(doc = "", required = true)
- var outputFile: File = null
+ /** Output variants not called in this comparison track */
+ @Input(fullName = "discordance", shortName = "disc", doc = "Output variants not called in this comparison track", required = false, exclusiveOf = "", validation = "")
+ var discordance: Option[File] = None
- var excludeNonVariants: Boolean = false
+ /** Output variants also called in this comparison track */
+ @Input(fullName = "concordance", shortName = "conc", doc = "Output variants also called in this comparison track", required = false, exclusiveOf = "", validation = "")
+ var concordance: Option[File] = None
- var inputMap: Map[File, String] = Map()
+ /** File to which variants should be written */
+ @Output(fullName = "out", shortName = "o", doc = "File to which variants should be written", required = false, exclusiveOf = "", validation = "")
+ @Gather(classOf[CatVariantsGatherer])
+ var out: File = _
- def addInput(file: File, name: String): Unit = {
- inputFiles :+= file
- inputMap += file -> name
- }
+ /** Include genotypes from this sample */
+ @Argument(fullName = "sample_name", shortName = "sn", doc = "Include genotypes from this sample", required = false, exclusiveOf = "", validation = "")
+ var sample_name: List[String] = config("sample_name", default = Nil)
+
+ /** Regular expression to select multiple samples */
+ @Argument(fullName = "sample_expressions", shortName = "se", doc = "Regular expression to select multiple samples", required = false, exclusiveOf = "", validation = "")
+ var sample_expressions: List[String] = config("sample_expressions", default = Nil)
+
+ /** File containing a list of samples to include */
+ @Input(fullName = "sample_file", shortName = "sf", doc = "File containing a list of samples to include", required = false, exclusiveOf = "", validation = "")
+ var sample_file: List[File] = config("sample_file", default = Nil)
+
+ /** Exclude genotypes from this sample */
+ @Argument(fullName = "exclude_sample_name", shortName = "xl_sn", doc = "Exclude genotypes from this sample", required = false, exclusiveOf = "", validation = "")
+ var exclude_sample_name: List[String] = config("exclude_sample_name", default = Nil)
+
+ /** List of samples to exclude */
+ @Input(fullName = "exclude_sample_file", shortName = "xl_sf", doc = "List of samples to exclude", required = false, exclusiveOf = "", validation = "")
+ var exclude_sample_file: List[File] = config("exclude_sample_file", default = Nil)
+
+ /** List of sample expressions to exclude */
+ @Input(fullName = "exclude_sample_expressions", shortName = "xl_se", doc = "List of sample expressions to exclude", required = false, exclusiveOf = "", validation = "")
+ var exclude_sample_expressions: List[File] = config("exclude_sample_expressions", default = Nil)
+
+ /** One or more criteria to use when selecting the data */
+ @Argument(fullName = "selectexpressions", shortName = "select", doc = "One or more criteria to use when selecting the data", required = false, exclusiveOf = "", validation = "")
+ var selectexpressions: List[String] = config("selectexpressions", default = Nil)
+
+ /** Invert the selection criteria for -select */
+ @Argument(fullName = "invertselect", shortName = "invertSelect", doc = "Invert the selection criteria for -select", required = false, exclusiveOf = "", validation = "")
+ var invertselect: Boolean = config("invertselect", default = false)
+
+ /** Don't include non-variant sites */
+ @Argument(fullName = "excludeNonVariants", shortName = "env", doc = "Don't include non-variant sites", required = false, exclusiveOf = "", validation = "")
+ var excludeNonVariants: Boolean = config("excludeNonVariants", default = false)
+
+ /** Don't include filtered sites */
+ @Argument(fullName = "excludeFiltered", shortName = "ef", doc = "Don't include filtered sites", required = false, exclusiveOf = "", validation = "")
+ var excludeFiltered: Boolean = config("excludeFiltered", default = false)
+
+ /** Preserve original alleles, do not trim */
+ @Argument(fullName = "preserveAlleles", shortName = "noTrim", doc = "Preserve original alleles, do not trim", required = false, exclusiveOf = "", validation = "")
+ var preserveAlleles: Boolean = config("preserveAlleles", default = false)
+
+ /** Remove alternate alleles not present in any genotypes */
+ @Argument(fullName = "removeUnusedAlternates", shortName = "trimAlternates", doc = "Remove alternate alleles not present in any genotypes", required = false, exclusiveOf = "", validation = "")
+ var removeUnusedAlternates: Boolean = config("removeUnusedAlternates", default = false)
+
+ /** Select only variants of a particular allelicity */
+ @Argument(fullName = "restrictAllelesTo", shortName = "restrictAllelesTo", doc = "Select only variants of a particular allelicity", required = false, exclusiveOf = "", validation = "")
+ var restrictAllelesTo: Option[String] = config("restrictAllelesTo")
+
+ /** Store the original AC, AF, and AN values after subsetting */
+ @Argument(fullName = "keepOriginalAC", shortName = "keepOriginalAC", doc = "Store the original AC, AF, and AN values after subsetting", required = false, exclusiveOf = "", validation = "")
+ var keepOriginalAC: Boolean = config("keepOriginalAC", default = false)
+
+ /** Store the original DP value after subsetting */
+ @Argument(fullName = "keepOriginalDP", shortName = "keepOriginalDP", doc = "Store the original DP value after subsetting", required = false, exclusiveOf = "", validation = "")
+ var keepOriginalDP: Boolean = config("keepOriginalDP", default = false)
+
+ /** Output mendelian violation sites only */
+ @Argument(fullName = "mendelianViolation", shortName = "mv", doc = "Output mendelian violation sites only", required = false, exclusiveOf = "", validation = "")
+ var mendelianViolation: Boolean = config("mendelianViolation", default = false)
+
+ /** Output non-mendelian violation sites only */
+ @Argument(fullName = "invertMendelianViolation", shortName = "invMv", doc = "Output non-mendelian violation sites only", required = false, exclusiveOf = "", validation = "")
+ var invertMendelianViolation: Boolean = config("invertMendelianViolation", default = false)
+
+ /** Minimum GQ score for each trio member to accept a site as a violation */
+ @Argument(fullName = "mendelianViolationQualThreshold", shortName = "mvq", doc = "Minimum GQ score for each trio member to accept a site as a violation", required = false, exclusiveOf = "", validation = "")
+ var mendelianViolationQualThreshold: Option[Double] = config("mendelianViolationQualThreshold")
+
+ /** Format string for mendelianViolationQualThreshold */
+ @Argument(fullName = "mendelianViolationQualThresholdFormat", shortName = "", doc = "Format string for mendelianViolationQualThreshold", required = false, exclusiveOf = "", validation = "")
+ var mendelianViolationQualThresholdFormat: String = "%s"
+
+ /** Select a fraction of variants at random from the input */
+ @Argument(fullName = "select_random_fraction", shortName = "fraction", doc = "Select a fraction of variants at random from the input", required = false, exclusiveOf = "", validation = "")
+ var select_random_fraction: Option[Double] = config("select_random_fraction")
+
+ /** Format string for select_random_fraction */
+ @Argument(fullName = "select_random_fractionFormat", shortName = "", doc = "Format string for select_random_fraction", required = false, exclusiveOf = "", validation = "")
+ var select_random_fractionFormat: String = "%s"
+
+ /** Select a fraction of genotypes at random from the input and sets them to no-call */
+ @Argument(fullName = "remove_fraction_genotypes", shortName = "fractionGenotypes", doc = "Select a fraction of genotypes at random from the input and sets them to no-call", required = false, exclusiveOf = "", validation = "")
+ var remove_fraction_genotypes: Option[Double] = config("remove_fraction_genotypes")
+
+ /** Format string for remove_fraction_genotypes */
+ @Argument(fullName = "remove_fraction_genotypesFormat", shortName = "", doc = "Format string for remove_fraction_genotypes", required = false, exclusiveOf = "", validation = "")
+ var remove_fraction_genotypesFormat: String = "%s"
+
+ /** Select only a certain type of variants from the input file */
+ @Argument(fullName = "selectTypeToInclude", shortName = "selectType", doc = "Select only a certain type of variants from the input file", required = false, exclusiveOf = "", validation = "")
+ var selectTypeToInclude: List[String] = config("selectTypeToInclude", default = Nil)
+
+ /** Do not select certain type of variants from the input file */
+ @Argument(fullName = "selectTypeToExclude", shortName = "xlSelectType", doc = "Do not select certain type of variants from the input file", required = false, exclusiveOf = "", validation = "")
+ var selectTypeToExclude: Seq[String] = config("selectTypeToExclude", default = Nil)
+
+ /** List of variant IDs to select */
+ @Input(fullName = "keepIDs", shortName = "IDs", doc = "List of variant IDs to select", required = false, exclusiveOf = "", validation = "")
+ var keepIDs: Option[File] = config("keepIDs")
+
+ /** List of variant IDs to select */
+ @Argument(fullName = "excludeIDs", shortName = "xlIDs", doc = "List of variant IDs to select", required = false, exclusiveOf = "", validation = "")
+ var excludeIDs: Option[File] = config("excludeIDs")
+
+ /** If true, the incoming VariantContext will be fully decoded */
+ @Argument(fullName = "fullyDecode", shortName = "", doc = "If true, the incoming VariantContext will be fully decoded", required = false, exclusiveOf = "", validation = "")
+ var fullyDecode: Boolean = config("fullyDecode", default = false)
+
+ /** If true, we won't actually write the output file. For efficiency testing only */
+ @Argument(fullName = "justRead", shortName = "", doc = "If true, we won't actually write the output file. For efficiency testing only", required = false, exclusiveOf = "", validation = "")
+ var justRead: Boolean = config("justRead", default = false)
+
+ /** Maximum size of indels to include */
+ @Argument(fullName = "maxIndelSize", shortName = "", doc = "Maximum size of indels to include", required = false, exclusiveOf = "", validation = "")
+ var maxIndelSize: Option[Int] = config("maxIndelSize")
+
+ /** Minimum size of indels to include */
+ @Argument(fullName = "minIndelSize", shortName = "", doc = "Minimum size of indels to include", required = false, exclusiveOf = "", validation = "")
+ var minIndelSize: Option[Int] = config("minIndelSize")
+
+ /** Maximum number of samples filtered at the genotype level */
+ @Argument(fullName = "maxFilteredGenotypes", shortName = "", doc = "Maximum number of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
+ var maxFilteredGenotypes: Option[Int] = config("maxFilteredGenotypes")
+
+ /** Minimum number of samples filtered at the genotype level */
+ @Argument(fullName = "minFilteredGenotypes", shortName = "", doc = "Minimum number of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
+ var minFilteredGenotypes: Option[Int] = config("minFilteredGenotypes")
+
+ /** Maximum fraction of samples filtered at the genotype level */
+ @Argument(fullName = "maxFractionFilteredGenotypes", shortName = "", doc = "Maximum fraction of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
+ var maxFractionFilteredGenotypes: Option[Double] = config("maxFractionFilteredGenotypes")
+
+ /** Format string for maxFractionFilteredGenotypes */
+ @Argument(fullName = "maxFractionFilteredGenotypesFormat", shortName = "", doc = "Format string for maxFractionFilteredGenotypes", required = false, exclusiveOf = "", validation = "")
+ var maxFractionFilteredGenotypesFormat: String = "%s"
+
+ /** Maximum fraction of samples filtered at the genotype level */
+ @Argument(fullName = "minFractionFilteredGenotypes", shortName = "", doc = "Maximum fraction of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
+ var minFractionFilteredGenotypes: Option[Double] = config("minFractionFilteredGenotypes")
+
+ /** Format string for minFractionFilteredGenotypes */
+ @Argument(fullName = "minFractionFilteredGenotypesFormat", shortName = "", doc = "Format string for minFractionFilteredGenotypes", required = false, exclusiveOf = "", validation = "")
+ var minFractionFilteredGenotypesFormat: String = "%s"
+
+ /** Set filtered genotypes to no-call */
+ @Argument(fullName = "setFilteredGtToNocall", shortName = "", doc = "Set filtered genotypes to no-call", required = false, exclusiveOf = "", validation = "")
+ var setFilteredGtToNocall: Boolean = config("setFilteredGtToNocall", default = false)
+
+ /** Allow samples other than those in the VCF to be specified on the command line. These samples will be ignored. */
+ @Argument(fullName = "ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES", shortName = "", doc = "Allow samples other than those in the VCF to be specified on the command line. These samples will be ignored.", required = false, exclusiveOf = "", validation = "")
+ var ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES: Boolean = config("ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES", default = false)
+
+ /** Forces output VCF to be compliant to up-to-date version */
+ @Argument(fullName = "forceValidOutput", shortName = "", doc = "Forces output VCF to be compliant to up-to-date version", required = false, exclusiveOf = "", validation = "")
+ var forceValidOutput: Boolean = config("forceValidOutput", default = false)
+
+ /** 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)
@Output
@Gather(enabled = false)
private var outputIndex: File = _
- override def beforeGraph(): Unit = {
+ override def beforeGraph() {
super.beforeGraph()
- outputIndex = VcfUtils.getVcfIndexFile(outputFile)
- deps :::= inputFiles.filter(_.getName.endsWith("vcf.gz")).map(x => new File(x.getAbsolutePath + ".tbi"))
- deps = deps.distinct
+ if (variant != null)
+ deps :+= VcfUtils.getVcfIndexFile(variant)
+ discordance.foreach(deps :+= VcfUtils.getVcfIndexFile(_))
+ concordance.foreach(deps :+= VcfUtils.getVcfIndexFile(_))
+ if (out != null && !org.broadinstitute.gatk.utils.io.IOUtils.isSpecialFile(out))
+ outputIndex = VcfUtils.getVcfIndexFile(out)
}
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")
+ required(TaggedFile.formatCommandLineParameter("-V", variant), variant, spaceSeparated = true, escape = true, format = "%s") +
+ optional(TaggedFile.formatCommandLineParameter("-disc", discordance), discordance, spaceSeparated = true, escape = true, format = "%s") +
+ optional(TaggedFile.formatCommandLineParameter("-conc", concordance), concordance, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-o", out, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-sn", sample_name, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-se", sample_expressions, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-sf", sample_file, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-xl_sn", exclude_sample_name, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-xl_sf", exclude_sample_file, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-xl_se", exclude_sample_expressions, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-select", selectexpressions, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(invertselect, "-invertSelect", escape = true, format = "%s") +
+ conditional(excludeNonVariants, "-env", escape = true, format = "%s") +
+ conditional(excludeFiltered, "-ef", escape = true, format = "%s") +
+ conditional(preserveAlleles, "-noTrim", escape = true, format = "%s") +
+ conditional(removeUnusedAlternates, "-trimAlternates", escape = true, format = "%s") +
+ optional("-restrictAllelesTo", restrictAllelesTo, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(keepOriginalAC, "-keepOriginalAC", escape = true, format = "%s") +
+ conditional(keepOriginalDP, "-keepOriginalDP", escape = true, format = "%s") +
+ conditional(mendelianViolation, "-mv", escape = true, format = "%s") +
+ conditional(invertMendelianViolation, "-invMv", escape = true, format = "%s") +
+ optional("-mvq", mendelianViolationQualThreshold, spaceSeparated = true, escape = true, format = mendelianViolationQualThresholdFormat) +
+ optional("-fraction", select_random_fraction, spaceSeparated = true, escape = true, format = select_random_fractionFormat) +
+ optional("-fractionGenotypes", remove_fraction_genotypes, spaceSeparated = true, escape = true, format = remove_fraction_genotypesFormat) +
+ repeat("-selectType", selectTypeToInclude, spaceSeparated = true, escape = true, format = "%s") +
+ repeat("-xlSelectType", selectTypeToExclude, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-IDs", keepIDs, spaceSeparated = true, escape = true, format = "%s") +
+ optional("-xlIDs", excludeIDs, spaceSeparated = true, escape = true, format = "%s") +
+ conditional(fullyDecode, "--fullyDecode", escape = true, format = "%s") +
+ conditional(justRead, "--justRead", escape = true, format = "%s") +
+ optional("--maxIndelSize", maxIndelSize, spaceSeparated = true, escape = true, format = "%s") +
+ optional("--minIndelSize", minIndelSize, spaceSeparated = true, escape = true, format = "%s") +
+ optional("--maxFilteredGenotypes", maxFilteredGenotypes, spaceSeparated = true, escape = true, format = "%s") +
+ optional("--minFilteredGenotypes", minFilteredGenotypes, spaceSeparated = true, escape = true, format = "%s") +
+ optional("--maxFractionFilteredGenotypes", maxFractionFilteredGenotypes, spaceSeparated = true, escape = true, format = maxFractionFilteredGenotypesFormat) +
+ optional("--minFractionFilteredGenotypes", minFractionFilteredGenotypes, spaceSeparated = true, escape = true, format = minFractionFilteredGenotypesFormat) +
+ conditional(setFilteredGtToNocall, "--setFilteredGtToNocall", escape = true, format = "%s") +
+ conditional(ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES, "--ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES", escape = true, format = "%s") +
+ conditional(forceValidOutput, "--forceValidOutput", 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/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/UnifiedGenotyper.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/UnifiedGenotyper.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
index fbb4423898d3f0c688a71cce40a2f1ad2b632978..0edfe5260fe2fb9101fd92d01fbcebce94ba0441 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/UnifiedGenotyper.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
@@ -1,11 +1,11 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
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.{ Gather, Input, Output, _ }
class UnifiedGenotyper(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantAnnotator.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantAnnotator.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
index 7fa034cfe6c48b3e4498a7ee4f968404a157a88c..d98a55a49eb6e34c00588fddde66dc00cddfe610 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantAnnotator.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
@@ -1,4 +1,4 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantEval.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala
similarity index 98%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantEval.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala
index a595ce5c1494101ac9104220db3a2c28d3120d2a..cf1c362c7dd06b2eec25104fdfd3fb5a06dea2f8 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantEval.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantEval.scala
@@ -1,13 +1,11 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+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.queue.extensions.gatk.TaggedFile
-import java.io.File
-import org.broadinstitute.gatk.utils.commandline.Argument
-import org.broadinstitute.gatk.utils.commandline.Gather
-import org.broadinstitute.gatk.utils.commandline.Input
-import org.broadinstitute.gatk.utils.commandline.Output
+import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Input, Output }
class VariantEval(val root: Configurable) extends CommandLineGATK {
def analysis_type = "VariantEval"
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantRecalibrator.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
similarity index 99%
rename from biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantRecalibrator.scala
rename to biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
index db631449a9e6c59112832247367634ee8d256983..96b5ee4c00fc1350e6298f31d11c2308010b6e23 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/VariantRecalibrator.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
@@ -1,4 +1,4 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
+package nl.lumc.sasc.biopet.extensions.gatk
import java.io.File
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CatVariants.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CatVariants.scala
deleted file mode 100644
index 6a23df5ff8d1f1a66c7606e826d7a09ad8924cc5..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CatVariants.scala
+++ /dev/null
@@ -1,59 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.utils.commandline.Argument
-import org.broadinstitute.gatk.utils.commandline.Gather
-import org.broadinstitute.gatk.utils.commandline.Input
-import org.broadinstitute.gatk.utils.commandline.Output
-
-class CatVariants(val root: Configurable) extends BiopetJavaCommandLineFunction {
- analysisName = "CatVariants"
- javaMainClass = "org.broadinstitute.gatk.tools.CatVariants"
-
- /** genome reference file <name>.fasta */
- @Input(fullName = "reference", shortName = "R", doc = "genome reference file <name>.fasta", required = true, exclusiveOf = "", validation = "")
- var reference: File = _
-
- /** Input VCF file/s */
- @Input(fullName = "variant", shortName = "V", doc = "Input VCF file/s", required = true, exclusiveOf = "", validation = "")
- var variant: Seq[File] = Nil
-
- /** output file */
- @Output(fullName = "outputFile", shortName = "out", doc = "output file", required = true, exclusiveOf = "", validation = "")
- @Gather(classOf[org.broadinstitute.gatk.queue.function.scattergather.SimpleTextGatherFunction])
- var outputFile: File = _
-
- /** assumeSorted should be true if the input files are already sorted (based on the position of the variants) */
- @Argument(fullName = "assumeSorted", shortName = "assumeSorted", doc = "assumeSorted should be true if the input files are already sorted (based on the position of the variants)", required = false, exclusiveOf = "", validation = "")
- var assumeSorted: Boolean = _
-
- /** which type of IndexCreator to use for VCF/BCF indices */
- @Argument(fullName = "variant_index_type", shortName = "", doc = "which type of IndexCreator to use for VCF/BCF indices", required = false, exclusiveOf = "", validation = "")
- var variant_index_type: Option[String] = None
-
- /** the parameter (bin width or features per bin) to pass to the VCF/BCF IndexCreator */
- @Argument(fullName = "variant_index_parameter", shortName = "", doc = "the parameter (bin width or features per bin) to pass to the VCF/BCF IndexCreator", required = false, exclusiveOf = "", validation = "")
- var variant_index_parameter: Option[Int] = None
-
- /** Set the minimum level of logging */
- @Argument(fullName = "logging_level", shortName = "l", doc = "Set the minimum level of logging", required = false, exclusiveOf = "", validation = "")
- var logging_level: String = _
-
- /** Set the logging location */
- @Output(fullName = "log_to_file", shortName = "log", doc = "Set the logging location", required = false, exclusiveOf = "", validation = "")
- @Gather(classOf[org.broadinstitute.gatk.queue.function.scattergather.SimpleTextGatherFunction])
- var log_to_file: File = _
-
- override def cmdLine = super.cmdLine +
- required("-R", reference, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-V", variant, spaceSeparated = true, escape = true, format = "%s") +
- required("-out", outputFile, spaceSeparated = true, escape = true, format = "%s") +
- conditional(assumeSorted, "-assumeSorted", escape = true, format = "%s") +
- optional("--variant_index_type", variant_index_type, spaceSeparated = true, escape = true, format = "%s") +
- optional("--variant_index_parameter", variant_index_parameter, spaceSeparated = true, escape = true, format = "%s") +
- optional("-l", logging_level, spaceSeparated = true, escape = true, format = "%s") +
- optional("-log", log_to_file, spaceSeparated = true, escape = true, format = "%s")
-}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CombineVariants.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CombineVariants.scala
deleted file mode 100644
index 7873ba3e44a3be042a923024af37a36922bb46d4..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/CombineVariants.scala
+++ /dev/null
@@ -1,128 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
-import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
-import nl.lumc.sasc.biopet.utils.VcfUtils
-import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Output, _ }
-
-class CombineVariants(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
- def analysis_type = "CombineVariants"
- scatterClass = classOf[LocusScatterFunction]
- setupScatterFunction = { case scatter: GATKScatterFunction => scatter.includeUnmapped = false }
-
- /** VCF files to merge together */
- @Input(fullName = "variant", shortName = "V", doc = "VCF files to merge together", required = true, exclusiveOf = "", validation = "")
- var variant: Seq[File] = Nil
-
- /** File to which variants should be written */
- @Output(fullName = "out", shortName = "o", doc = "File to which variants should be written", required = false, exclusiveOf = "", validation = "")
- @Gather(classOf[CatVariantsGatherer])
- var out: File = _
-
- /** Determines how we should merge genotype records for samples shared across the ROD files */
- @Argument(fullName = "genotypemergeoption", shortName = "genotypeMergeOptions", doc = "Determines how we should merge genotype records for samples shared across the ROD files", required = false, exclusiveOf = "", validation = "")
- var genotypemergeoption: Option[String] = config("genotypemergeoption")
-
- /** Determines how we should handle records seen at the same site in the VCF, but with different FILTER fields */
- @Argument(fullName = "filteredrecordsmergetype", shortName = "filteredRecordsMergeType", doc = "Determines how we should handle records seen at the same site in the VCF, but with different FILTER fields", required = false, exclusiveOf = "", validation = "")
- var filteredrecordsmergetype: Option[String] = config("filteredrecordsmergetype")
-
- /** Determines how we should handle records seen at the same site in the VCF, but with different allele types (for example, SNP vs. indel) */
- @Argument(fullName = "multipleallelesmergetype", shortName = "multipleAllelesMergeType", doc = "Determines how we should handle records seen at the same site in the VCF, but with different allele types (for example, SNP vs. indel)", required = false, exclusiveOf = "", validation = "")
- var multipleallelesmergetype: Option[String] = config("multipleallelesmergetype")
-
- /** Ordered list specifying priority for merging */
- @Argument(fullName = "rod_priority_list", shortName = "priority", doc = "Ordered list specifying priority for merging", required = false, exclusiveOf = "", validation = "")
- var rod_priority_list: Option[String] = config("rod_priority_list")
-
- /** Emit interesting sites requiring complex compatibility merging to file */
- @Argument(fullName = "printComplexMerges", shortName = "printComplexMerges", doc = "Emit interesting sites requiring complex compatibility merging to file", required = false, exclusiveOf = "", validation = "")
- var printComplexMerges: Boolean = config("printComplexMerges", default = false)
-
- /** Treat filtered variants as uncalled */
- @Argument(fullName = "filteredAreUncalled", shortName = "filteredAreUncalled", doc = "Treat filtered variants as uncalled", required = false, exclusiveOf = "", validation = "")
- var filteredAreUncalled: Boolean = config("filteredAreUncalled", default = false)
-
- /** Emit a sites-only file */
- @Argument(fullName = "minimalVCF", shortName = "minimalVCF", doc = "Emit a sites-only file", required = false, exclusiveOf = "", validation = "")
- var minimalVCF: Boolean = config("minimalVCF", default = false)
-
- /** Exclude sites where no variation is present after merging */
- @Argument(fullName = "excludeNonVariants", shortName = "env", doc = "Exclude sites where no variation is present after merging", required = false, exclusiveOf = "", validation = "")
- var excludeNonVariants: Boolean = config("excludeNonVariants", default = false)
-
- /** Key name for the set attribute */
- @Argument(fullName = "setKey", shortName = "setKey", doc = "Key name for the set attribute", required = false, exclusiveOf = "", validation = "")
- var setKey: Option[String] = config("set_key")
-
- /** Assume input VCFs have identical sample sets and disjoint calls */
- @Argument(fullName = "assumeIdenticalSamples", shortName = "assumeIdenticalSamples", doc = "Assume input VCFs have identical sample sets and disjoint calls", required = false, exclusiveOf = "", validation = "")
- var assumeIdenticalSamples: Boolean = config("assumeIdenticalSamples", default = false)
-
- /** Minimum number of input files the site must be observed in to be included */
- @Argument(fullName = "minimumN", shortName = "minN", doc = "Minimum number of input files the site must be observed in to be included", required = false, exclusiveOf = "", validation = "")
- var minimumN: Option[Int] = config("minimumN")
-
- /** Do not output the command line to the header */
- @Argument(fullName = "suppressCommandLineHeader", shortName = "suppressCommandLineHeader", doc = "Do not output the command line to the header", required = false, exclusiveOf = "", validation = "")
- var suppressCommandLineHeader: Boolean = config("suppressCommandLineHeader", default = false)
-
- /** Use the INFO content of the record with the highest AC */
- @Argument(fullName = "mergeInfoWithMaxAC", shortName = "mergeInfoWithMaxAC", doc = "Use the INFO content of the record with the highest AC", required = false, exclusiveOf = "", validation = "")
- var mergeInfoWithMaxAC: Boolean = config("mergeInfoWithMaxAC", default = false)
-
- /** 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)
-
- @Output
- @Gather(enabled = false)
- private var outputIndex: File = _
-
- override def beforeGraph() {
- super.beforeGraph()
- deps ++= variant.filter(orig => orig != null && (!orig.getName.endsWith(".list"))).map(orig => VcfUtils.getVcfIndexFile(orig))
- if (out != null && !org.broadinstitute.gatk.utils.io.IOUtils.isSpecialFile(out))
- outputIndex = VcfUtils.getVcfIndexFile(out)
- }
-
- override def cmdLine = super.cmdLine +
- repeat("-V", variant, formatPrefix = TaggedFile.formatCommandLineParameter, spaceSeparated = true, escape = true, format = "%s") +
- optional("-o", out, spaceSeparated = true, escape = true, format = "%s") +
- optional("-genotypeMergeOptions", genotypemergeoption, spaceSeparated = true, escape = true, format = "%s") +
- optional("-filteredRecordsMergeType", filteredrecordsmergetype, spaceSeparated = true, escape = true, format = "%s") +
- optional("-multipleAllelesMergeType", multipleallelesmergetype, spaceSeparated = true, escape = true, format = "%s") +
- optional("-priority", rod_priority_list, spaceSeparated = true, escape = true, format = "%s") +
- conditional(printComplexMerges, "-printComplexMerges", escape = true, format = "%s") +
- conditional(filteredAreUncalled, "-filteredAreUncalled", escape = true, format = "%s") +
- conditional(minimalVCF, "-minimalVCF", escape = true, format = "%s") +
- conditional(excludeNonVariants, "-env", escape = true, format = "%s") +
- optional("-setKey", setKey, spaceSeparated = true, escape = true, format = "%s") +
- conditional(assumeIdenticalSamples, "-assumeIdenticalSamples", escape = true, format = "%s") +
- optional("-minN", minimumN, spaceSeparated = true, escape = true, format = "%s") +
- conditional(suppressCommandLineHeader, "-suppressCommandLineHeader", escape = true, format = "%s") +
- conditional(mergeInfoWithMaxAC, "-mergeInfoWithMaxAC", 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")
-}
-
-object CombineVariants {
- def apply(root: Configurable, input: List[File], output: File): CombineVariants = {
- val cv = new CombineVariants(root)
- cv.variant = input
- cv.out = output
- cv
- }
-}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GatkGeneral.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GatkGeneral.scala
deleted file mode 100644
index b8c3e6ba238836cf5a1c6f71a534a0359275e8c8..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GatkGeneral.scala
+++ /dev/null
@@ -1,44 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
-
-import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.gatk.engine.phonehome.GATKRunReport
-
-/**
- * @deprecated
- */
-trait GatkGeneral extends org.broadinstitute.gatk.queue.extensions.gatk.CommandLineGATK with CommandLineResources with Reference with Version {
- var executable: String = config("java", default = "java", namespace = "java", freeVar = false)
-
- override def subPath = "gatk" :: super.subPath
-
- jarFile = config("gatk_jar")
-
- reference_sequence = referenceFasta()
-
- override def defaultCoreMemory = 4.0
- override def faiRequired = true
- override def dictRequired = true
-
- if (config.contains("intervals")) intervals = config("intervals").asFileList
- if (config.contains("exclude_intervals")) excludeIntervals = config("exclude_intervals").asFileList
-
- Option(config("et").value) match {
- case Some("NO_ET") => et = GATKRunReport.PhoneHomeOption.NO_ET
- case Some("AWS") => et = GATKRunReport.PhoneHomeOption.AWS
- case Some("STDOUT") => et = GATKRunReport.PhoneHomeOption.STDOUT
- case Some(x) => throw new IllegalArgumentException(s"Unknown et option for gatk: $x")
- case _ =>
- }
-
- if (config.contains("gatk_key")) gatk_key = config("gatk_key")
- if (config.contains("pedigree")) pedigree = config("pedigree")
-
- def versionRegex = """(.*)""".r
- override def versionExitcode = List(0, 1)
- def versionCommand = "java" + " -jar " + jarFile + " -version"
-
- override def getVersion = {
- BiopetCommandLineFunction.preProcessExecutable(executable).path.foreach(executable = _)
- super.getVersion.collect { case v => "Gatk " + v }
- }
-}
diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/SelectVariants.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/SelectVariants.scala
deleted file mode 100644
index dd49dd75da5fb6d91f5cc0826338796799a198c3..0000000000000000000000000000000000000000
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/SelectVariants.scala
+++ /dev/null
@@ -1,262 +0,0 @@
-package nl.lumc.sasc.biopet.extensions.gatk.broad
-
-import java.io.File
-
-import nl.lumc.sasc.biopet.utils.config.Configurable
-import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
-import nl.lumc.sasc.biopet.core.ScatterGatherableFunction
-import nl.lumc.sasc.biopet.utils.VcfUtils
-import org.broadinstitute.gatk.utils.commandline.{ Argument, Gather, Output, _ }
-
-class SelectVariants(val root: Configurable) extends CommandLineGATK with ScatterGatherableFunction {
- def analysis_type = "SelectVariants"
- scatterClass = classOf[LocusScatterFunction]
- setupScatterFunction = { case scatter: GATKScatterFunction => scatter.includeUnmapped = false }
-
- /** Input VCF file */
- @Input(fullName = "variant", shortName = "V", doc = "Input VCF file", required = true, exclusiveOf = "", validation = "")
- var variant: File = _
-
- /** Output variants not called in this comparison track */
- @Input(fullName = "discordance", shortName = "disc", doc = "Output variants not called in this comparison track", required = false, exclusiveOf = "", validation = "")
- var discordance: Option[File] = None
-
- /** Output variants also called in this comparison track */
- @Input(fullName = "concordance", shortName = "conc", doc = "Output variants also called in this comparison track", required = false, exclusiveOf = "", validation = "")
- var concordance: Option[File] = None
-
- /** File to which variants should be written */
- @Output(fullName = "out", shortName = "o", doc = "File to which variants should be written", required = false, exclusiveOf = "", validation = "")
- @Gather(classOf[CatVariantsGatherer])
- var out: File = _
-
- /** Include genotypes from this sample */
- @Argument(fullName = "sample_name", shortName = "sn", doc = "Include genotypes from this sample", required = false, exclusiveOf = "", validation = "")
- var sample_name: List[String] = config("sample_name", default = Nil)
-
- /** Regular expression to select multiple samples */
- @Argument(fullName = "sample_expressions", shortName = "se", doc = "Regular expression to select multiple samples", required = false, exclusiveOf = "", validation = "")
- var sample_expressions: List[String] = config("sample_expressions", default = Nil)
-
- /** File containing a list of samples to include */
- @Input(fullName = "sample_file", shortName = "sf", doc = "File containing a list of samples to include", required = false, exclusiveOf = "", validation = "")
- var sample_file: List[File] = config("sample_file", default = Nil)
-
- /** Exclude genotypes from this sample */
- @Argument(fullName = "exclude_sample_name", shortName = "xl_sn", doc = "Exclude genotypes from this sample", required = false, exclusiveOf = "", validation = "")
- var exclude_sample_name: List[String] = config("exclude_sample_name", default = Nil)
-
- /** List of samples to exclude */
- @Input(fullName = "exclude_sample_file", shortName = "xl_sf", doc = "List of samples to exclude", required = false, exclusiveOf = "", validation = "")
- var exclude_sample_file: List[File] = config("exclude_sample_file", default = Nil)
-
- /** List of sample expressions to exclude */
- @Input(fullName = "exclude_sample_expressions", shortName = "xl_se", doc = "List of sample expressions to exclude", required = false, exclusiveOf = "", validation = "")
- var exclude_sample_expressions: List[File] = config("exclude_sample_expressions", default = Nil)
-
- /** One or more criteria to use when selecting the data */
- @Argument(fullName = "selectexpressions", shortName = "select", doc = "One or more criteria to use when selecting the data", required = false, exclusiveOf = "", validation = "")
- var selectexpressions: List[String] = config("selectexpressions", default = Nil)
-
- /** Invert the selection criteria for -select */
- @Argument(fullName = "invertselect", shortName = "invertSelect", doc = "Invert the selection criteria for -select", required = false, exclusiveOf = "", validation = "")
- var invertselect: Boolean = config("invertselect", default = false)
-
- /** Don't include non-variant sites */
- @Argument(fullName = "excludeNonVariants", shortName = "env", doc = "Don't include non-variant sites", required = false, exclusiveOf = "", validation = "")
- var excludeNonVariants: Boolean = config("excludeNonVariants", default = false)
-
- /** Don't include filtered sites */
- @Argument(fullName = "excludeFiltered", shortName = "ef", doc = "Don't include filtered sites", required = false, exclusiveOf = "", validation = "")
- var excludeFiltered: Boolean = config("excludeFiltered", default = false)
-
- /** Preserve original alleles, do not trim */
- @Argument(fullName = "preserveAlleles", shortName = "noTrim", doc = "Preserve original alleles, do not trim", required = false, exclusiveOf = "", validation = "")
- var preserveAlleles: Boolean = config("preserveAlleles", default = false)
-
- /** Remove alternate alleles not present in any genotypes */
- @Argument(fullName = "removeUnusedAlternates", shortName = "trimAlternates", doc = "Remove alternate alleles not present in any genotypes", required = false, exclusiveOf = "", validation = "")
- var removeUnusedAlternates: Boolean = config("removeUnusedAlternates", default = false)
-
- /** Select only variants of a particular allelicity */
- @Argument(fullName = "restrictAllelesTo", shortName = "restrictAllelesTo", doc = "Select only variants of a particular allelicity", required = false, exclusiveOf = "", validation = "")
- var restrictAllelesTo: Option[String] = config("restrictAllelesTo")
-
- /** Store the original AC, AF, and AN values after subsetting */
- @Argument(fullName = "keepOriginalAC", shortName = "keepOriginalAC", doc = "Store the original AC, AF, and AN values after subsetting", required = false, exclusiveOf = "", validation = "")
- var keepOriginalAC: Boolean = config("keepOriginalAC", default = false)
-
- /** Store the original DP value after subsetting */
- @Argument(fullName = "keepOriginalDP", shortName = "keepOriginalDP", doc = "Store the original DP value after subsetting", required = false, exclusiveOf = "", validation = "")
- var keepOriginalDP: Boolean = config("keepOriginalDP", default = false)
-
- /** Output mendelian violation sites only */
- @Argument(fullName = "mendelianViolation", shortName = "mv", doc = "Output mendelian violation sites only", required = false, exclusiveOf = "", validation = "")
- var mendelianViolation: Boolean = config("mendelianViolation", default = false)
-
- /** Output non-mendelian violation sites only */
- @Argument(fullName = "invertMendelianViolation", shortName = "invMv", doc = "Output non-mendelian violation sites only", required = false, exclusiveOf = "", validation = "")
- var invertMendelianViolation: Boolean = config("invertMendelianViolation", default = false)
-
- /** Minimum GQ score for each trio member to accept a site as a violation */
- @Argument(fullName = "mendelianViolationQualThreshold", shortName = "mvq", doc = "Minimum GQ score for each trio member to accept a site as a violation", required = false, exclusiveOf = "", validation = "")
- var mendelianViolationQualThreshold: Option[Double] = config("mendelianViolationQualThreshold")
-
- /** Format string for mendelianViolationQualThreshold */
- @Argument(fullName = "mendelianViolationQualThresholdFormat", shortName = "", doc = "Format string for mendelianViolationQualThreshold", required = false, exclusiveOf = "", validation = "")
- var mendelianViolationQualThresholdFormat: String = "%s"
-
- /** Select a fraction of variants at random from the input */
- @Argument(fullName = "select_random_fraction", shortName = "fraction", doc = "Select a fraction of variants at random from the input", required = false, exclusiveOf = "", validation = "")
- var select_random_fraction: Option[Double] = config("select_random_fraction")
-
- /** Format string for select_random_fraction */
- @Argument(fullName = "select_random_fractionFormat", shortName = "", doc = "Format string for select_random_fraction", required = false, exclusiveOf = "", validation = "")
- var select_random_fractionFormat: String = "%s"
-
- /** Select a fraction of genotypes at random from the input and sets them to no-call */
- @Argument(fullName = "remove_fraction_genotypes", shortName = "fractionGenotypes", doc = "Select a fraction of genotypes at random from the input and sets them to no-call", required = false, exclusiveOf = "", validation = "")
- var remove_fraction_genotypes: Option[Double] = config("remove_fraction_genotypes")
-
- /** Format string for remove_fraction_genotypes */
- @Argument(fullName = "remove_fraction_genotypesFormat", shortName = "", doc = "Format string for remove_fraction_genotypes", required = false, exclusiveOf = "", validation = "")
- var remove_fraction_genotypesFormat: String = "%s"
-
- /** Select only a certain type of variants from the input file */
- @Argument(fullName = "selectTypeToInclude", shortName = "selectType", doc = "Select only a certain type of variants from the input file", required = false, exclusiveOf = "", validation = "")
- var selectTypeToInclude: List[String] = config("selectTypeToInclude", default = Nil)
-
- /** Do not select certain type of variants from the input file */
- @Argument(fullName = "selectTypeToExclude", shortName = "xlSelectType", doc = "Do not select certain type of variants from the input file", required = false, exclusiveOf = "", validation = "")
- var selectTypeToExclude: Seq[String] = config("selectTypeToExclude", default = Nil)
-
- /** List of variant IDs to select */
- @Input(fullName = "keepIDs", shortName = "IDs", doc = "List of variant IDs to select", required = false, exclusiveOf = "", validation = "")
- var keepIDs: Option[File] = config("keepIDs")
-
- /** List of variant IDs to select */
- @Argument(fullName = "excludeIDs", shortName = "xlIDs", doc = "List of variant IDs to select", required = false, exclusiveOf = "", validation = "")
- var excludeIDs: Option[File] = config("excludeIDs")
-
- /** If true, the incoming VariantContext will be fully decoded */
- @Argument(fullName = "fullyDecode", shortName = "", doc = "If true, the incoming VariantContext will be fully decoded", required = false, exclusiveOf = "", validation = "")
- var fullyDecode: Boolean = config("fullyDecode", default = false)
-
- /** If true, we won't actually write the output file. For efficiency testing only */
- @Argument(fullName = "justRead", shortName = "", doc = "If true, we won't actually write the output file. For efficiency testing only", required = false, exclusiveOf = "", validation = "")
- var justRead: Boolean = config("justRead", default = false)
-
- /** Maximum size of indels to include */
- @Argument(fullName = "maxIndelSize", shortName = "", doc = "Maximum size of indels to include", required = false, exclusiveOf = "", validation = "")
- var maxIndelSize: Option[Int] = config("maxIndelSize")
-
- /** Minimum size of indels to include */
- @Argument(fullName = "minIndelSize", shortName = "", doc = "Minimum size of indels to include", required = false, exclusiveOf = "", validation = "")
- var minIndelSize: Option[Int] = config("minIndelSize")
-
- /** Maximum number of samples filtered at the genotype level */
- @Argument(fullName = "maxFilteredGenotypes", shortName = "", doc = "Maximum number of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
- var maxFilteredGenotypes: Option[Int] = config("maxFilteredGenotypes")
-
- /** Minimum number of samples filtered at the genotype level */
- @Argument(fullName = "minFilteredGenotypes", shortName = "", doc = "Minimum number of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
- var minFilteredGenotypes: Option[Int] = config("minFilteredGenotypes")
-
- /** Maximum fraction of samples filtered at the genotype level */
- @Argument(fullName = "maxFractionFilteredGenotypes", shortName = "", doc = "Maximum fraction of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
- var maxFractionFilteredGenotypes: Option[Double] = config("maxFractionFilteredGenotypes")
-
- /** Format string for maxFractionFilteredGenotypes */
- @Argument(fullName = "maxFractionFilteredGenotypesFormat", shortName = "", doc = "Format string for maxFractionFilteredGenotypes", required = false, exclusiveOf = "", validation = "")
- var maxFractionFilteredGenotypesFormat: String = "%s"
-
- /** Maximum fraction of samples filtered at the genotype level */
- @Argument(fullName = "minFractionFilteredGenotypes", shortName = "", doc = "Maximum fraction of samples filtered at the genotype level", required = false, exclusiveOf = "", validation = "")
- var minFractionFilteredGenotypes: Option[Double] = config("minFractionFilteredGenotypes")
-
- /** Format string for minFractionFilteredGenotypes */
- @Argument(fullName = "minFractionFilteredGenotypesFormat", shortName = "", doc = "Format string for minFractionFilteredGenotypes", required = false, exclusiveOf = "", validation = "")
- var minFractionFilteredGenotypesFormat: String = "%s"
-
- /** Set filtered genotypes to no-call */
- @Argument(fullName = "setFilteredGtToNocall", shortName = "", doc = "Set filtered genotypes to no-call", required = false, exclusiveOf = "", validation = "")
- var setFilteredGtToNocall: Boolean = config("setFilteredGtToNocall", default = false)
-
- /** Allow samples other than those in the VCF to be specified on the command line. These samples will be ignored. */
- @Argument(fullName = "ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES", shortName = "", doc = "Allow samples other than those in the VCF to be specified on the command line. These samples will be ignored.", required = false, exclusiveOf = "", validation = "")
- var ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES: Boolean = config("ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES", default = false)
-
- /** Forces output VCF to be compliant to up-to-date version */
- @Argument(fullName = "forceValidOutput", shortName = "", doc = "Forces output VCF to be compliant to up-to-date version", required = false, exclusiveOf = "", validation = "")
- var forceValidOutput: Boolean = config("forceValidOutput", default = false)
-
- /** 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)
-
- @Output
- @Gather(enabled = false)
- private var outputIndex: File = _
-
- override def beforeGraph() {
- super.beforeGraph()
- if (variant != null)
- deps :+= VcfUtils.getVcfIndexFile(variant)
- discordance.foreach(deps :+= VcfUtils.getVcfIndexFile(_))
- concordance.foreach(deps :+= VcfUtils.getVcfIndexFile(_))
- if (out != null && !org.broadinstitute.gatk.utils.io.IOUtils.isSpecialFile(out))
- outputIndex = VcfUtils.getVcfIndexFile(out)
- }
-
- override def cmdLine = super.cmdLine +
- required(TaggedFile.formatCommandLineParameter("-V", variant), variant, spaceSeparated = true, escape = true, format = "%s") +
- optional(TaggedFile.formatCommandLineParameter("-disc", discordance), discordance, spaceSeparated = true, escape = true, format = "%s") +
- optional(TaggedFile.formatCommandLineParameter("-conc", concordance), concordance, spaceSeparated = true, escape = true, format = "%s") +
- optional("-o", out, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-sn", sample_name, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-se", sample_expressions, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-sf", sample_file, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-xl_sn", exclude_sample_name, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-xl_sf", exclude_sample_file, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-xl_se", exclude_sample_expressions, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-select", selectexpressions, spaceSeparated = true, escape = true, format = "%s") +
- conditional(invertselect, "-invertSelect", escape = true, format = "%s") +
- conditional(excludeNonVariants, "-env", escape = true, format = "%s") +
- conditional(excludeFiltered, "-ef", escape = true, format = "%s") +
- conditional(preserveAlleles, "-noTrim", escape = true, format = "%s") +
- conditional(removeUnusedAlternates, "-trimAlternates", escape = true, format = "%s") +
- optional("-restrictAllelesTo", restrictAllelesTo, spaceSeparated = true, escape = true, format = "%s") +
- conditional(keepOriginalAC, "-keepOriginalAC", escape = true, format = "%s") +
- conditional(keepOriginalDP, "-keepOriginalDP", escape = true, format = "%s") +
- conditional(mendelianViolation, "-mv", escape = true, format = "%s") +
- conditional(invertMendelianViolation, "-invMv", escape = true, format = "%s") +
- optional("-mvq", mendelianViolationQualThreshold, spaceSeparated = true, escape = true, format = mendelianViolationQualThresholdFormat) +
- optional("-fraction", select_random_fraction, spaceSeparated = true, escape = true, format = select_random_fractionFormat) +
- optional("-fractionGenotypes", remove_fraction_genotypes, spaceSeparated = true, escape = true, format = remove_fraction_genotypesFormat) +
- repeat("-selectType", selectTypeToInclude, spaceSeparated = true, escape = true, format = "%s") +
- repeat("-xlSelectType", selectTypeToExclude, spaceSeparated = true, escape = true, format = "%s") +
- optional("-IDs", keepIDs, spaceSeparated = true, escape = true, format = "%s") +
- optional("-xlIDs", excludeIDs, spaceSeparated = true, escape = true, format = "%s") +
- conditional(fullyDecode, "--fullyDecode", escape = true, format = "%s") +
- conditional(justRead, "--justRead", escape = true, format = "%s") +
- optional("--maxIndelSize", maxIndelSize, spaceSeparated = true, escape = true, format = "%s") +
- optional("--minIndelSize", minIndelSize, spaceSeparated = true, escape = true, format = "%s") +
- optional("--maxFilteredGenotypes", maxFilteredGenotypes, spaceSeparated = true, escape = true, format = "%s") +
- optional("--minFilteredGenotypes", minFilteredGenotypes, spaceSeparated = true, escape = true, format = "%s") +
- optional("--maxFractionFilteredGenotypes", maxFractionFilteredGenotypes, spaceSeparated = true, escape = true, format = maxFractionFilteredGenotypesFormat) +
- optional("--minFractionFilteredGenotypes", minFractionFilteredGenotypes, spaceSeparated = true, escape = true, format = minFractionFilteredGenotypesFormat) +
- conditional(setFilteredGtToNocall, "--setFilteredGtToNocall", escape = true, format = "%s") +
- conditional(ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES, "--ALLOW_NONOVERLAPPING_COMMAND_LINE_SAMPLES", escape = true, format = "%s") +
- conditional(forceValidOutput, "--forceValidOutput", 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..d7c40fb76197f77ddb944803c113b65cf124a0bf 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
@@ -30,8 +30,8 @@ import nl.lumc.sasc.biopet.extensions.picard.CreateSequenceDictionary
import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsFaidx
import nl.lumc.sasc.biopet.utils.ConfigUtils
import org.broadinstitute.gatk.queue.QScript
-import scala.language.reflectiveCalls
+import scala.language.reflectiveCalls
import scala.collection.JavaConversions._
class GenerateIndexes(val root: Configurable) extends QScript with BiopetQScript {
@@ -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..d2303ac3e014110652af209dbaee180565405ca0 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
@@ -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/Shiva.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/Shiva.scala
index 7bebb491a55a52b7b77ce8141f11f162ab7eb643..ed0e1318d96c615346172b5e1add0df6dc4476d0 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/Shiva.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/Shiva.scala
@@ -17,7 +17,7 @@ package nl.lumc.sasc.biopet.pipelines.shiva
import nl.lumc.sasc.biopet.core.{ PipelineCommand, Reference }
import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
-import nl.lumc.sasc.biopet.extensions.gatk.broad._
+import nl.lumc.sasc.biopet.extensions.gatk._
import nl.lumc.sasc.biopet.pipelines.bammetrics.TargetRegions
import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingTrait
import nl.lumc.sasc.biopet.pipelines.toucan.Toucan
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..c38cb8564ddb0f9243443bab60f6cb41ceec5b53 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
@@ -26,6 +26,7 @@ import nl.lumc.sasc.biopet.pipelines.shiva.variantcallers.{ VarscanCnsSingleSamp
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.setKey = "VariantCaller"
- cv.genotypeMergeOptions = Some("PRIORITIZE")
- cv.rodPriorityList = callers.map(_.name).mkString(",")
+ cv.out = finalFile
+ cv.setKey = Some("VariantCaller")
+ 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..91f8468b189b878d756554782b956a8a0037ceef 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
@@ -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/HaplotypeCaller.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCaller.scala
index cd039f946a182b70c23d715b9efc3cf57960f2b4..1224592eb7fb66eb4075eb9aff9215379d6553c4 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCaller.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCaller.scala
@@ -5,7 +5,7 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
-import nl.lumc.sasc.biopet.extensions.gatk.broad
+import nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Default mode for the haplotypecaller */
@@ -14,7 +14,7 @@ class HaplotypeCaller(val root: Configurable) extends Variantcaller {
protected def defaultPrio = 1
def biopetScript() {
- val hc = broad.HaplotypeCaller(this, inputBams.values.toList, outputFile)
+ val hc = gatk.HaplotypeCaller(this, inputBams.values.toList, outputFile)
add(hc)
}
}
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerAllele.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerAllele.scala
index 3de2234b78317c0182aaf8db6a163c087b4afe34..09e7b5e0286fee0da538c23ce9d8b5f639df1555 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerAllele.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerAllele.scala
@@ -5,7 +5,7 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
-import nl.lumc.sasc.biopet.extensions.gatk.broad
+import nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Allele mode for Haplotypecaller */
@@ -14,7 +14,7 @@ class HaplotypeCallerAllele(val root: Configurable) extends Variantcaller {
protected def defaultPrio = 5
def biopetScript() {
- val hc = broad.HaplotypeCaller(this, inputBams.values.toList, outputFile)
+ val hc = gatk.HaplotypeCaller(this, inputBams.values.toList, outputFile)
hc.alleles = config("input_alleles")
hc.genotyping_mode = Some("GENOTYPE_GIVEN_ALLELES")
add(hc)
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerGvcf.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerGvcf.scala
index 6a0cb91c9b4c3131d0479b853071d5f6826b0513..2f7b8446b4c0a64b1348edb396f43fedcaaab4d3 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerGvcf.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/HaplotypeCallerGvcf.scala
@@ -5,7 +5,7 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
-import nl.lumc.sasc.biopet.extensions.gatk.broad
+import nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Gvcf mode for haplotypecaller */
@@ -15,12 +15,12 @@ class HaplotypeCallerGvcf(val root: Configurable) extends Variantcaller {
def biopetScript() {
val gvcfFiles = for ((sample, inputBam) <- inputBams) yield {
- val hc = broad.HaplotypeCaller.gvcf(this, inputBam, new File(outputDir, sample + ".gvcf.vcf.gz"))
+ val hc = gatk.HaplotypeCaller.gvcf(this, inputBam, new File(outputDir, sample + ".gvcf.vcf.gz"))
add(hc)
hc.out
}
- val genotypeGVCFs = broad.GenotypeGVCFs(this, gvcfFiles.toList, outputFile)
+ val genotypeGVCFs = gatk.GenotypeGVCFs(this, gvcfFiles.toList, outputFile)
add(genotypeGVCFs)
}
}
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..ec46b9c348b3761786195777057852a96f6b214f 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
@@ -15,11 +15,9 @@
*/
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.samtools.SamtoolsMpileup
-import nl.lumc.sasc.biopet.extensions.tools.{ VcfFilter, MpileupToVcf }
+import nl.lumc.sasc.biopet.extensions.tools.{ MpileupToVcf, VcfFilter }
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Makes a vcf file from a mpileup without statistics */
@@ -60,9 +58,9 @@ class RawVcf(val root: Configurable) extends Variantcaller {
}
val cv = new CombineVariants(this)
- cv.inputFiles = rawFiles.toList
- cv.outputFile = outputFile
- cv.setKey = "null"
+ cv.variant = rawFiles.toList
+ cv.out = outputFile
+ cv.setKey = Some("null")
cv.excludeNonVariants = !keepRefCalls
add(cv)
}
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyper.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyper.scala
index 96c3821bcb1343163507d9b0e9a950f477a47c6c..43fbe730d4b585edacff62b7a8388a5c82fbe062 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyper.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyper.scala
@@ -5,7 +5,7 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
-import nl.lumc.sasc.biopet.extensions.gatk.broad
+import nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Default mode for UnifiedGenotyper */
@@ -14,7 +14,7 @@ class UnifiedGenotyper(val root: Configurable) extends Variantcaller {
protected def defaultPrio = 20
def biopetScript() {
- val ug = broad.UnifiedGenotyper(this, inputBams.values.toList, outputFile)
+ val ug = gatk.UnifiedGenotyper(this, inputBams.values.toList, outputFile)
add(ug)
}
}
diff --git a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyperAllele.scala b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyperAllele.scala
index 8ffdcd962107840ccfbf175310c70035c8c668a1..364691f517c7434a39dc498a58ac1349e7e46d2f 100644
--- a/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyperAllele.scala
+++ b/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/variantcallers/UnifiedGenotyperAllele.scala
@@ -5,7 +5,7 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva.variantcallers
-import nl.lumc.sasc.biopet.extensions.gatk.broad
+import nl.lumc.sasc.biopet.extensions.gatk
import nl.lumc.sasc.biopet.utils.config.Configurable
/** Allele mode for GenotyperAllele */
@@ -14,7 +14,7 @@ class UnifiedGenotyperAllele(val root: Configurable) extends Variantcaller {
protected def defaultPrio = 9
def biopetScript() {
- val ug = broad.UnifiedGenotyper(this, inputBams.values.toList, outputFile)
+ val ug = gatk.UnifiedGenotyper(this, inputBams.values.toList, outputFile)
ug.alleles = config("input_alleles")
ug.genotyping_mode = Some("GENOTYPE_GIVEN_ALLELES")
add(ug)
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..cb213f28e6485c04c7bf8f76a7293cf062516d8a 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
@@ -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/ShivaTest.scala b/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTest.scala
index 736cff399b1dc09d41ea1df8cc6adfc697503d44..eb1d40ece24ce6862023eae3343b84c840ea3e42 100644
--- a/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTest.scala
+++ b/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTest.scala
@@ -18,7 +18,7 @@ package nl.lumc.sasc.biopet.pipelines.shiva
import java.io.{ File, FileOutputStream }
import com.google.common.io.Files
-import nl.lumc.sasc.biopet.extensions.gatk.broad._
+import nl.lumc.sasc.biopet.extensions.gatk.{ BaseRecalibrator, IndelRealigner, PrintReads, RealignerTargetCreator }
import nl.lumc.sasc.biopet.extensions.picard.MarkDuplicates
import nl.lumc.sasc.biopet.extensions.tools.VcfStats
import nl.lumc.sasc.biopet.utils.ConfigUtils
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..8c9dcb1e5496d3e43792bcc83d56644396eaeee6 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
@@ -11,16 +11,14 @@ import com.google.common.io.Files
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.extensions.gatk.{ CombineVariants, HaplotypeCaller, UnifiedGenotyper }
import nl.lumc.sasc.biopet.utils.config.Config
-import nl.lumc.sasc.biopet.extensions.gatk.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
-import org.apache.commons.io.FileUtils
import org.broadinstitute.gatk.queue.QSettings
import org.scalatest.Matchers
import org.scalatest.testng.TestNGSuite
-import org.testng.annotations.{ AfterClass, DataProvider, Test }
+import org.testng.annotations.{ DataProvider, Test }
import scala.collection.mutable.ListBuffer