Merge branch 'feature-sortvcf-picard' into 'develop'

Adding SortVcf extension

This wrapper can be used to sort VCF files, whenever they have to be sorted (some variant callers generate non-sorted VCF).

See merge request !372

public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala

@@ -73,6 +73,15 @@ trait BiopetCommandLineFunction extends CommandLineResources { biopetFunction =>
   def beforeGraph() {}
 
   override def freezeFieldValues() {
+
+    this match {
+      case r: Reference =>
+        if (r.dictRequired) deps :+= r.referenceDict
+        if (r.faiRequired) deps :+= r.referenceFai
+        deps = deps.distinct
+      case _ =>
+    }
+
     preProcessExecutable()
     beforeGraph()
     internalBeforeGraph()

public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala

@@ -61,25 +61,25 @@ trait Reference extends Configurable {
   }
 
   /** When set override this on true the pipeline with raise an exception when fai index is not found */
-  protected def faiRequired = false
+  def faiRequired = false
 
   /** When set override this on true the pipeline with raise an exception when dict index is not found */
-  protected def dictRequired = this.isInstanceOf[Summarizable] || this.isInstanceOf[SummaryQScript]
+  def dictRequired = this.isInstanceOf[Summarizable] || this.isInstanceOf[SummaryQScript]
+
+  /** Returns the dict file belonging to the fasta file */
+  def referenceDict = new File(referenceFasta().getAbsolutePath
+    .stripSuffix(".fa")
+    .stripSuffix(".fasta")
+    .stripSuffix(".fna") + ".dict")
+
+  /** Returns the fai file belonging to the fasta file */
+  def referenceFai = new File(referenceFasta().getAbsolutePath + ".fai")
 
   /** Returns the fasta file */
   def referenceFasta(): File = {
     val file: File = config("reference_fasta")
-    if (config.contains("reference_fasta")) {
-      checkFasta(file)
-
-      val dict = new File(file.getAbsolutePath.stripSuffix(".fa").stripSuffix(".fasta").stripSuffix(".fna") + ".dict")
-      val fai = new File(file.getAbsolutePath + ".fai")
-
-      this match {
-        case c: BiopetCommandLineFunction => c.deps :::= dict :: fai :: Nil
-        case _                            =>
-      }
-    } else {
+    if (config.contains("reference_fasta")) checkFasta(file)
+    else {
       val defaults = ConfigUtils.mergeMaps(this.defaults, this.internalDefaults)
 
       def getReferences(map: Map[String, Any]): Set[(String, String)] = (for (

public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SortVcf.scala

+/**
+ * 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.picard
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.Reference
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
+
+/** Extension for picard SortVcf */
+class SortVcf(val root: Configurable) extends Picard with Reference {
+  javaMainClass = new picard.vcf.SortVcf().getClass.getName
+
+  @Input(doc = "Input VCF(s) to be sorted. Multiple inputs must have the same sample names (in order)", required = true)
+  var input: File = _
+
+  @Output(doc = "Output VCF to be written.", required = true)
+  var output: File = _
+
+  @Input(doc = "Sequence dictionary to use", required = true)
+  var sequenceDictionary: File = _
+
+  override val dictRequired = true
+
+  override def beforeGraph(): Unit = {
+    super.beforeGraph()
+    if (sequenceDictionary == null) sequenceDictionary = referenceDict
+  }
+
+  /** Returns command to execute */
+  override def cmdLine = super.cmdLine +
+    (if (inputAsStdin) required("INPUT=", new File("/dev/stdin"), spaceSeparated = false)
+    else required("INPUT=", input, spaceSeparated = false)) +
+    (if (outputAsStsout) required("OUTPUT=", new File("/dev/stdout"), spaceSeparated = false)
+    else required("OUTPUT=", output, spaceSeparated = false)) +
+    required("SEQUENCE_DICTIONARY=", sequenceDictionary, spaceSeparated = false)
+}
+
+object SortVcf {
+  /** Returns default SortSam */
+  def apply(root: Configurable, input: File, output: File): SortVcf = {
+    val sortVcf = new SortVcf(root)
+    sortVcf.input = input
+    sortVcf.output = output
+    sortVcf
+  }
+}
\ No newline at end of file

public/tinycap/src/test/resources/log4j.properties

+#
+# 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.
+#
+
+# Set root logger level to DEBUG and its only appender to A1.
+log4j.rootLogger=ERROR, A1
+
+# A1 is set to be a ConsoleAppender.
+log4j.appender.A1=org.apache.log4j.ConsoleAppender
+
+# A1 uses PatternLayout.
+log4j.appender.A1.layout=org.apache.log4j.PatternLayout
+log4j.appender.A1.layout.ConversionPattern=%-5p [%d] [%C{1}] - %m%n
\ No newline at end of file