Added some picard tools to biopet

biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/picard/CalculateHsMetrics.scala

+package nl.lumc.sasc.biopet.function.picard
+
+import java.io.File
+import nl.lumc.sasc.biopet.core.config.Configurable
+import org.broadinstitute.sting.commandline.{Argument, Input, Output}
+
+class CalculateHsMetrics(val root:Configurable) extends Picard {
+  javaMainClass = "net.sf.picard.analysis.directed.CalculateHsMetrics"
+  
+  @Input(doc="The input SAM or BAM files to analyze.  Must be coordinate sorted.", required = true)
+  var input: File = _
+  
+  @Input(doc="BAIT_INTERVALS", required = true)
+  var baitIntervals: File = _
+  
+  @Input(doc="TARGET_INTERVALS", required = true)
+  var targetIntervals: File = _
+  
+  @Output(doc="The output file to write statistics to", required = true)
+  var output: File = _
+  
+  @Output(doc="PER_TARGET_COVERAGE", required = false)
+  var perTargetCoverage: File = _
+  
+  @Argument(doc="Reference file", required = false)
+  var reference: File = config("reference", "")
+  
+  @Argument(doc="METRIC_ACCUMULATION_LEVEL", required=false)
+  var metricAccumulationLevel: List[String] = config("metricaccumulationlevel", List())
+  
+  @Argument(doc="BAIT_SET_NAME", required = false)
+  var baitSetName: String = _
+  
+  override def commandLine = super.commandLine +
+    required("INPUT=", input, spaceSeparated=false) +
+    required("OUTPUT=", output, spaceSeparated=false) +
+    optional("REFERENCE_SEQUENCE=", reference, spaceSeparated=false) + 
+    repeat("METRIC_ACCUMULATION_LEVEL=", metricAccumulationLevel, spaceSeparated=false) +
+    required("BAIT_INTERVALS=", baitIntervals, spaceSeparated=false) + 
+    required("TARGET_INTERVALS=", targetIntervals, spaceSeparated=false) +
+    optional("PER_TARGET_COVERAGE=", perTargetCoverage, spaceSeparated=false) +
+    optional("BAIT_SET_NAME=", baitSetName, spaceSeparated=false)
+}
+
+object CalculateHsMetrics {
+  def apply(root:Configurable, input:File, baitIntervals:File, targetIntervals:File, outputDir:String) : CalculateHsMetrics = {
+    val calculateHsMetrics = new CalculateHsMetrics(root)
+    calculateHsMetrics.input = input
+    calculateHsMetrics.baitIntervals = baitIntervals
+    calculateHsMetrics.targetIntervals = targetIntervals
+    calculateHsMetrics.output = new File(outputDir, input.getName.stripSuffix(".bam") + ".capmetrics")
+    calculateHsMetrics.perTargetCoverage = new File(outputDir, input.getName.stripSuffix(".bam") + ".per_target_coverage")
+    return calculateHsMetrics
+  }
+}
\ No newline at end of file

biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/picard/CollectGcBiasMetrics.scala

+package nl.lumc.sasc.biopet.function.picard
+
+import java.io.File
+import nl.lumc.sasc.biopet.core.config.Configurable
+import org.broadinstitute.sting.commandline.{Argument, Input, Output}
+
+class CollectGcBiasMetrics(val root:Configurable) extends Picard {
+  javaMainClass = "net.sf.picard.analysis.CollectGcBiasMetrics"
+
+  @Input(doc="The input SAM or BAM files to analyze.  Must be coordinate sorted.", required = true)
+  var input: Seq[File] = Nil
+
+  @Output(doc="The output file to write statistics to", required = true)
+  var output: File = _
+  
+  @Output(doc="Output chart", required = false)
+  var outputChart: File = _
+  
+  @Output(doc="Output summary", required = false)
+  var outputSummary: File = _
+
+  @Argument(doc="Reference file", required = false)
+  var reference: File = config("reference", "")
+  
+  @Argument(doc="Window size", required = false)
+  var windowSize: Int = config("windowsize", 100)
+  
+  @Argument(doc="MINIMUM_GENOME_FRACTION", required=false)
+  var minGenomeFraction: Double = config("mingenomefraction", 1.0E-5)
+  
+  @Argument(doc="ASSUME_SORTED", required=false)
+  var assumeSorted: Boolean = config("assumesorted", false)
+  
+  @Argument(doc="IS_BISULFITE_SEQUENCED", required=false)
+  var isBisulfiteSequinced: Boolean = config("isbisulfitesequinced", false)
+  
+  override def afterGraph {
+    if (outputChart == null) outputChart = new File(output + ".pdf")
+    //require(reference.exists)
+  }
+  
+  override def commandLine = super.commandLine +
+    repeat("INPUT=", input, spaceSeparated=false) +
+    required("OUTPUT=", output, spaceSeparated=false) +
+    optional("CHART_OUTPUT=", outputChart, spaceSeparated=false) +
+    required("REFERENCE_SEQUENCE=", reference, spaceSeparated=false) + 
+    optional("SUMMARY_OUTPUT=", outputSummary, spaceSeparated=false) +
+    optional("WINDOW_SIZE=", windowSize, spaceSeparated=false) +
+    optional("MINIMUM_GENOME_FRACTION=", minGenomeFraction, spaceSeparated=false) + 
+    conditional(assumeSorted, "ASSUME_SORTED=TRUE") +
+    conditional(isBisulfiteSequinced, "IS_BISULFITE_SEQUENCED=TRUE")
+}
+
+object CollectGcBiasMetrics {
+  def apply(root:Configurable, input:File, outputDir:String) : CollectGcBiasMetrics = {
+    val collectGcBiasMetrics = new CollectGcBiasMetrics(root)
+    collectGcBiasMetrics.input :+= input
+    collectGcBiasMetrics.output = new File(outputDir, input.getName.stripSuffix(".bam") + ".gcbiasmetrics")
+    return collectGcBiasMetrics
+  }
+}

biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/picard/CollectInsertSizeMetrics.scala

+package nl.lumc.sasc.biopet.function.picard
+
+import java.io.File
+import nl.lumc.sasc.biopet.core.config.Configurable
+import org.broadinstitute.sting.commandline.{Argument, Input, Output}
+
+class CollectInsertSizeMetrics(val root:Configurable) extends Picard {
+  javaMainClass = "net.sf.picard.analysis.CollectInsertSizeMetrics"
+
+  @Input(doc="The input SAM or BAM files to analyze.  Must be coordinate sorted.", required = true)
+  var input: File = _
+
+  @Output(doc="The output file to write statistics to", required = true)
+  var output: File = _
+  
+  @Output(doc="Output histogram", required = true)
+  var outputHistogram: File = _
+  
+  @Argument(doc="Reference file", required = false)
+  var reference: File = config("reference", "")
+  
+  @Argument(doc="DEVIATIONS", required = false)
+  var deviations: Double = config("deviations", 10.0)
+  
+  @Argument(doc="MINIMUM_PCT", required=false)
+  var minPct: Double = config("minpct", 0.05)
+  
+  @Argument(doc="ASSUME_SORTED", required=false)
+  var assumeSorted: Boolean = config("assumesorted", false)
+  
+  @Argument(doc="STOP_AFTER", required=false)
+  var stopAfter: Long = config("metricaccumulationlevel", 0)
+  
+  @Argument(doc="METRIC_ACCUMULATION_LEVEL", required=false)
+  var metricAccumulationLevel: List[String] = config("metricaccumulationlevel", List())
+  
+  @Argument(doc="HISTOGRAM_WIDTH", required=false)
+  var histogramWidth: Int = config("histogramWidth", 0)
+  
+  override def afterGraph {
+    if (outputHistogram == null) outputHistogram = new File(output + ".pdf")
+    //require(reference.exists)
+  }
+  
+  override def commandLine = super.commandLine +
+    required("INPUT=", input, spaceSeparated=false) +
+    required("OUTPUT=", output, spaceSeparated=false) +
+    optional("HISTOGRAM_FILE=", outputHistogram, spaceSeparated=false) +
+    required("REFERENCE_SEQUENCE=", reference, spaceSeparated=false) + 
+    optional("DEVIATIONS=", deviations, spaceSeparated=false) +
+    repeat("METRIC_ACCUMULATION_LEVEL=", metricAccumulationLevel, spaceSeparated=false) +
+    (if (stopAfter > 0) optional("STOP_AFTER=", stopAfter, spaceSeparated=false) else "") +
+    (if (histogramWidth > 0) optional("HISTOGRAM_WIDTH=", histogramWidth, spaceSeparated=false) else "") +
+    conditional(assumeSorted, "ASSUME_SORTED=TRUE")
+}
+
+object CollectInsertSizeMetrics {
+  def apply(root:Configurable, input:File, outputDir:String) : CollectInsertSizeMetrics = {
+    val collectInsertSizeMetrics = new CollectInsertSizeMetrics(root)
+    collectInsertSizeMetrics.input = input
+    collectInsertSizeMetrics.output = new File(outputDir, input.getName.stripSuffix(".bam") + ".insertsizemetrics")
+    return collectInsertSizeMetrics
+  }
+}
\ No newline at end of file

biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/picard/MarkDuplicates.scala

+package nl.lumc.sasc.biopet.function.picard
+
+import java.io.File
+import nl.lumc.sasc.biopet.core.config.Configurable
+import org.broadinstitute.sting.commandline.{Argument, Input, Output}
+
+class MarkDuplicates(val root:Configurable) extends Picard {
+  javaMainClass = "net.sf.picard.sam.MarkDuplicates"
+
+  @Input(doc="The input SAM or BAM files to analyze.  Must be coordinate sorted.", required = true)
+  var input: List[File] = Nil
+
+  @Output(doc="The output file to bam file to", required = true)
+  var output: File = _
+  
+  @Output(doc="The output file to write statistics to", required = true)
+  var outputMetrics: File = _
+  
+  @Argument(doc="PROGRAM_RECORD_ID", required=false)
+  var programRecordId: String = if (configContains("programrecordid")) config("programrecordid") else null
+  
+  @Argument(doc="PROGRAM_GROUP_VERSION", required=false)
+  var programGroupVersion: String = if (configContains("programgroupversion")) config("programgroupversion") else null
+  
+  @Argument(doc="PROGRAM_GROUP_COMMAND_LINE", required=false)
+  var programGroupCommandLine: String = if (configContains("programgroupcommandline")) config("programgroupcommandline") else null
+  
+  @Argument(doc="PROGRAM_GROUP_NAME", required=false)
+  var programGroupName: String = if (configContains("programgroupname")) config("programgroupname") else null
+  
+  @Argument(doc="COMMENT", required=false)
+  var comment: String = if (configContains("comment")) config("comment") else null
+  
+  @Argument(doc="REMOVE_DUPLICATES", required=false)
+  var removeDuplicates: Boolean = config("removeduplicates", false)
+  
+  @Argument(doc="ASSUME_SORTED", required=false)
+  var assumeSorted: Boolean = config("assumesorted", false)
+  
+  @Argument(doc="MAX_SEQUENCES_FOR_DISK_READ_ENDS_MAP", required=false)
+  var maxSequencesForDiskReadEndsMap: Int = config("maxSequencesForDiskReadEndsMap", 50000)
+  
+  @Argument(doc="MAX_FILE_HANDLES_FOR_READ_ENDS_MAP", required=false)
+  var maxFileHandlesForReadEndsMap: Int = config("maxFileHandlesForReadEndsMap", 8000)
+  
+  @Argument(doc="SORTING_COLLECTION_SIZE_RATIO", required=false)
+  var sortingCollectionSizeRatio: Double = config("sortingCollectionSizeRatio", 0.25)
+  
+  @Argument(doc="READ_NAME_REGEX", required=false)
+  var readNameRegex: String = if (configContains("readNameRegex")) config("readNameRegex") else null
+  
+  @Argument(doc="OPTICAL_DUPLICATE_PIXEL_DISTANCE", required=false)
+  var opticalDuplicatePixelDistance: Int = config("opticalDuplicatePixelDistance", 100)
+  
+  override def commandLine = super.commandLine +
+    repeat("INPUT=", input, spaceSeparated=false) +
+    required("OUTPUT=", output, spaceSeparated=false) +
+    required("METRICS_FILE=", outputMetrics, spaceSeparated=false) +
+    optional("PROGRAM_RECORD_ID=", programRecordId, spaceSeparated=false) + 
+    optional("PROGRAM_GROUP_VERSION=", programGroupVersion, spaceSeparated=false) +
+    optional("PROGRAM_GROUP_COMMAND_LINE=", programGroupCommandLine, spaceSeparated=false) +
+    optional("PROGRAM_GROUP_NAME=", programGroupName, spaceSeparated=false) +
+    optional("COMMENT=", comment, spaceSeparated=false) +
+    conditional(removeDuplicates, "REMOVE_DUPLICATES=TRUE") + 
+    conditional(assumeSorted, "ASSUME_SORTED=TRUE") + 
+    (if (maxSequencesForDiskReadEndsMap > 0) optional("MAX_SEQUENCES_FOR_DISK_READ_ENDS_MAP=", maxSequencesForDiskReadEndsMap, spaceSeparated=false) else "") +
+    (if (maxFileHandlesForReadEndsMap > 0) optional("MAX_FILE_HANDLES_FOR_READ_ENDS_MAP=", maxFileHandlesForReadEndsMap, spaceSeparated=false) else "") +
+    (if (sortingCollectionSizeRatio > 0) optional("SORTING_COLLECTION_SIZE_RATIO=", sortingCollectionSizeRatio, spaceSeparated=false) else "") +
+    optional("READ_NAME_REGEX=", readNameRegex, spaceSeparated=false) +
+    (if (opticalDuplicatePixelDistance > 0) optional("OPTICAL_DUPLICATE_PIXEL_DISTANCE=", opticalDuplicatePixelDistance, spaceSeparated=false) else "")
+}
+ object MarkDuplicates {
+   def apply(root:Configurable, input:List[File], outputDir:String) : MarkDuplicates = {
+    val markDuplicates = new MarkDuplicates(root)
+    markDuplicates.input = input
+    markDuplicates.output = new File(outputDir, input.head.getName.stripSuffix(".bam") + ".dedup.bam")
+    markDuplicates.outputMetrics = new File(outputDir, input.head.getName.stripSuffix(".bam") + ".dedup.metrics")
+    return markDuplicates
+  }
+  
+  def apply(root:Configurable, input:List[File], output:File) : MarkDuplicates = {
+    val markDuplicates = new MarkDuplicates(root)
+    markDuplicates.input = input
+    markDuplicates.output = output
+    markDuplicates.outputMetrics = new File(output.getParent, output.getName.stripSuffix(".bam") + ".metrics")
+    return markDuplicates
+  }
+ }
\ No newline at end of file

biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/picard/Picard.scala

+package nl.lumc.sasc.biopet.function.picard
+
+import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
+import org.broadinstitute.sting.commandline._
+
+abstract class Picard extends BiopetJavaCommandLineFunction {
+  @Argument(doc="VERBOSITY", required = false)
+  var verbosity: String = config("verbosity", "INFO", "picard")
+  
+  @Argument(doc="QUIET", required = false)
+  var quiet: Boolean = config("quiet", false, "picard")
+  
+  @Argument(doc="VALIDATION_STRINGENCY", required = false)
+  var stringency: String = config("validationstringency", "STRICT", "picard")
+  
+  @Argument(doc="COMPRESSION_LEVEL", required = false)
+  var compression: Int = config("compressionlevel", 5, "picard")
+  
+  @Argument(doc="MAX_RECORDS_IN_RAM", required = false)
+  var maxRecordsInRam: Int = config("maxrecordsinram", 500000, "picard")
+  
+  @Argument(doc="CREATE_INDEX", required = false)
+  var createIndex: Boolean = config("createindex", true, "picard")
+  
+  @Argument(doc="CREATE_MD5_FILE", required = false)
+  var createMd5: Boolean = config("createmd5", false, "picard")
+  
+  override def versionCommand = executeble + " " + javaOpts + " " + javaExecutable + " -h"
+  override val versionRegex = """Version: (.*)""".r
+  override val versionExitcode = List(0,1)
+  
+  override val defaultVmem = "8G"
+  memoryLimit = Option(5.0)
+  
+  override def commandLine = super.commandLine +
+    required("TMP_DIR=" + jobTempDir) +
+    optional("VERBOSITY=", verbosity, spaceSeparated=false) +
+    conditional(quiet, "QUIET=TRUE") +
+    optional("VALIDATION_STRINGENCY=", stringency, spaceSeparated=false) +
+    optional("COMPRESSION_LEVEL=", compression, spaceSeparated=false) +
+    optional("MAX_RECORDS_IN_RAM=", maxRecordsInRam, spaceSeparated=false) +
+    conditional(createIndex, "CREATE_INDEX=TRUE") +
+    conditional(createMd5, "CREATE_MD5_FILE=TRUE")
+}