Merge remote-tracking branch 'remotes/origin/develop' into feature-report

Conflicts:
	protected/biopet-gatk-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/broad/GatkGeneral.scala
	public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/Gatk.scala
	public/shiva/src/main/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaTrait.scala

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

@@ -5,10 +5,10 @@
  */
 package nl.lumc.sasc.biopet.extensions.gatk.broad
 
-import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Reference, BiopetJavaCommandLineFunction }
 import org.broadinstitute.gatk.queue.extensions.gatk.CommandLineGATK
 
-trait GatkGeneral extends CommandLineGATK with BiopetJavaCommandLineFunction {
+trait GatkGeneral extends CommandLineGATK with BiopetJavaCommandLineFunction with Reference {
   memoryLimit = Option(3)
 
   override def subPath = "gatk" :: super.subPath
@@ -19,7 +19,6 @@ trait GatkGeneral extends CommandLineGATK with BiopetJavaCommandLineFunction {
 
   if (config.contains("intervals")) intervals = config("intervals").asFileList
   if (config.contains("exclude_intervals")) excludeIntervals = config("exclude_intervals").asFileList
-  reference_sequence = config("reference")
   if (config.contains("gatk_key")) gatk_key = config("gatk_key")
   if (config.contains("pedigree")) pedigree = config("pedigree")
 
@@ -28,4 +27,9 @@ trait GatkGeneral extends CommandLineGATK with BiopetJavaCommandLineFunction {
   override def versionCommand = executable + " -jar " + jarFile + " -version"
 
   override def getVersion = super.getVersion.collect { case version => "Gatk " + version }
+
+  override def beforeGraph: Unit = {
+    super.beforeGraph
+    if (reference_sequence == null) reference_sequence = referenceFasta()
+  }
 }

protected/biopet-gatk-pipelines/src/test/resources/ref.dict

+@HD	VN:1.4	SO:unsorted
+@SQ	SN:chr1	LN:9	UR:file:/home/pjvan_thof/pipelines/biopet/public/mapping/src/test/resources/ref.fa	M5:fe15dbbd0900310caf32827f6da57550

protected/biopet-gatk-pipelines/src/test/resources/ref.fa

+>chr1
+AGTAGTAGT

protected/biopet-gatk-pipelines/src/test/resources/ref.fa.fai

+chr1	9	6	9	10

protected/biopet-gatk-pipelines/src/test/scala/nl/lumc/sasc/biopet/pipelines/gatk/ShivaTest.scala

@@ -5,6 +5,8 @@
  */
 package nl.lumc.sasc.biopet.pipelines.gatk
 
+import java.io.{ FileOutputStream, File }
+
 import com.google.common.io.Files
 import nl.lumc.sasc.biopet.core.config.Config
 import nl.lumc.sasc.biopet.extensions.bwa.BwaMem
@@ -90,10 +92,22 @@ class ShivaTest extends TestNGSuite with Matchers {
 object ShivaTest {
   val outputDir = Files.createTempDir()
 
+  private def copyFile(name: String): Unit = {
+    val is = getClass.getResourceAsStream("/" + name)
+    val os = new FileOutputStream(new File(outputDir, name))
+    org.apache.commons.io.IOUtils.copy(is, os)
+    os.close()
+  }
+
+  copyFile("ref.fa")
+  copyFile("ref.dict")
+  copyFile("ref.fa.fai")
+
   val config = Map(
     "name_prefix" -> "test",
     "output_dir" -> outputDir,
-    "reference" -> "test",
+    "reference" -> (outputDir + File.separator + "ref.fa"),
+    "reference_fasta" -> (outputDir + File.separator + "ref.fa"),
     "gatk_jar" -> "test",
     "samtools" -> Map("exe" -> "test"),
     "bcftools" -> Map("exe" -> "test"),

protected/biopet-gatk-pipelines/src/test/scala/nl/lumc/sasc/biopet/pipelines/gatk/ShivaVariantcallingTest.scala

@@ -5,7 +5,7 @@
  */
 package nl.lumc.sasc.biopet.pipelines.gatk
 
-import java.io.File
+import java.io.{ FileOutputStream, File }
 
 import com.google.common.io.Files
 import nl.lumc.sasc.biopet.core.config.Config
@@ -106,10 +106,22 @@ class ShivaVariantcallingTest extends TestNGSuite with Matchers {
 object ShivaVariantcallingTest {
   val outputDir = Files.createTempDir()
 
+  private def copyFile(name: String): Unit = {
+    val is = getClass.getResourceAsStream("/" + name)
+    val os = new FileOutputStream(new File(outputDir, name))
+    org.apache.commons.io.IOUtils.copy(is, os)
+    os.close()
+  }
+
+  copyFile("ref.fa")
+  copyFile("ref.dict")
+  copyFile("ref.fa.fai")
+
   val config = Map(
     "name_prefix" -> "test",
     "output_dir" -> outputDir,
-    "reference" -> "test",
+    "reference" -> (outputDir + File.separator + "ref.fa"),
+    "reference_fasta" -> (outputDir + File.separator + "ref.fa"),
     "gatk_jar" -> "test",
     "samtools" -> Map("exe" -> "test"),
     "bcftools" -> Map("exe" -> "test"),

public/bammetrics/src/test/resources/ref.dict

+@HD	VN:1.4	SO:unsorted
+@SQ	SN:chr1	LN:9	UR:file:/home/pjvan_thof/pipelines/biopet/public/mapping/src/test/resources/ref.fa	M5:fe15dbbd0900310caf32827f6da57550

public/bammetrics/src/test/resources/ref.fa

+>chr1
+AGTAGTAGT

public/bammetrics/src/test/resources/ref.fa.fai

+chr1	9	6	9	10

public/bammetrics/src/test/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetricsTest.scala

 package nl.lumc.sasc.biopet.pipelines.bammetrics
 
-import java.io.File
+import java.io.{ FileOutputStream, File }
 
 import com.google.common.io.Files
 import nl.lumc.sasc.biopet.core.config.Config
@@ -81,9 +81,20 @@ class BamMetricsTest extends TestNGSuite with Matchers {
 object BamMetricsTest {
   val outputDir = Files.createTempDir()
 
+  private def copyFile(name: String): Unit = {
+    val is = getClass.getResourceAsStream("/" + name)
+    val os = new FileOutputStream(new File(outputDir, name))
+    org.apache.commons.io.IOUtils.copy(is, os)
+    os.close()
+  }
+
+  copyFile("ref.fa")
+  copyFile("ref.dict")
+  copyFile("ref.fa.fai")
+
   val executables = Map(
     "refFlat" -> "bla.refFlat",
-    "reference" -> "reference.fa",
+    "reference_fasta" -> (outputDir + File.separator + "ref.fa"),
     "samtools" -> Map("exe" -> "test"),
     "bedtools" -> Map("exe" -> "test")
   )

public/biopet-framework/src/main/resources/nl/lumc/sasc/biopet/extensions/svcallers/breakdancer2vcf.py → public/biopet-framework/src/main/resources/nl/lumc/sasc/biopet/extensions/breakdancer/breakdancer2vcf.py

@@ -15,21 +15,18 @@
 # license, please contact us to obtain a separate license.
 #
 
-
 __copyright__ = """
 Copyright (C) 2013 - Tim te Beek
 Copyright (C) 2013 - Wai Yi Leung
 Copyright (C) 2013 AllBio (see AUTHORS file)
 """
 
-__desc__ = """Convert breakdancer output to pseudo .vcf file format."""
+__desc__ = """Convert breakdancer output to VCF v4.2 .file format."""
 __created__ = "Mar 18, 2013"
-__author__ = "tbeek"
+__author__ = "tbeek,wyleung"
 
 import argparse
 import csv
-import os.path
-import sys
 import datetime
 
 
@@ -43,16 +40,10 @@ def main(tsvfile, vcffile):
     with open(tsvfile) as reader:
         # Parse file
         dictreader = _parse_tsvfile(reader)
-        print dictreader.fieldnames
 
         # Write out file
         _format_vcffile(dictreader, vcffile)
 
-    # Quick output
-    with open(vcffile) as reader:
-        print reader.read(1000)
-
-
 def _parse_tsvfile(readable):
     '''
     Read readable using csv.Sniffer and csv.DictReader
@@ -111,7 +102,38 @@ VCF_HEADER = """##fileformat=VCFv4.1
 ##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
 ##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
 ##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency">
-##INFO=<ID=SVLEN,Number=1,Type=Integer,Description="Length of variation">
+##INFO=<ID=IMPRECISE,Number=0,Type=Flag,Description="Imprecise structural variation">
+##INFO=<ID=NOVEL,Number=0,Type=Flag,Description="Indicates a novel structural variation">
+##INFO=<ID=SVEND,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">
+##INFO=<ID=SVLEN,Number=.,Type=Integer,Description="Difference in length between REF and ALT alleles">
+##INFO=<ID=CIPOS,Number=2,Type=Integer,Description="Confidence interval around POS for imprecise variants">
+##INFO=<ID=CIEND,Number=2,Type=Integer,Description="Confidence interval around END for imprecise variants">
+##INFO=<ID=HOMLEN,Number=.,Type=Integer,Description="Length of base pair identical micro-homology at event breakpoints">
+##INFO=<ID=HOMSEQ,Number=.,Type=String,Description="Sequence of base pair identical micro-homology at event breakpoints">
+##INFO=<ID=BKPTID,Number=.,Type=String,Description="ID of the assembled alternate allele in the assembly file">
+##INFO=<ID=MEINFO,Number=4,Type=String,Description="Mobile element info of the form NAME,START,END,POLARITY">
+##INFO=<ID=METRANS,Number=4,Type=String,Description="Mobile element transduction info of the form CHR,START,END,POLARITY">
+##INFO=<ID=DGVID,Number=1,Type=String,Description="ID of this element in Database of Genomic Variation">
+##INFO=<ID=DBVARID,Number=1,Type=String,Description="ID of this element in DBVAR">
+##INFO=<ID=DBRIPID,Number=1,Type=String,Description="ID of this element in DBRIP">
+##INFO=<ID=MATEID,Number=.,Type=String,Description="ID of mate breakends">
+##INFO=<ID=PARID,Number=1,Type=String,Description="ID of partner breakend">
+##INFO=<ID=EVENT,Number=1,Type=String,Description="ID of event associated to breakend">
+##INFO=<ID=CILEN,Number=2,Type=Integer,Description="Confidence interval around the inserted material between breakends">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Read Depth of segment containing breakend">
+##INFO=<ID=DPADJ,Number=.,Type=Integer,Description="Read Depth of adjacency">
+##INFO=<ID=CN,Number=1,Type=Integer,Description="Copy number of segment containing breakend">
+##INFO=<ID=CNADJ,Number=.,Type=Integer,Description="Copy number of adjacency">
+##INFO=<ID=CICN,Number=2,Type=Integer,Description="Confidence interval around copy number for the segment">
+##INFO=<ID=CICNADJ,Number=.,Type=Integer,Description="Confidence interval around copy number for the adjacency">
+##FORMAT=<ID=CN,Number=1,Type=Integer,Description="Copy number genotype for imprecise events">
+##FORMAT=<ID=CNQ,Number=1,Type=Float,Description="Copy number genotype quality for imprecise events">
+##FORMAT=<ID=CNL,Number=.,Type=Float,Description="Copy number genotype likelihood for imprecise events">
+##FORMAT=<ID=NQ,Number=1,Type=Integer,Description="Phred style probability score that the variant is novel">
+##FORMAT=<ID=HAP,Number=1,Type=Integer,Description="Unique haplotype identifier">
+##FORMAT=<ID=AHAP,Number=1,Type=Integer,Description="Unique identifier of ancestral haplotype">
 ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
 ##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
 ##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">""".format( filedate=TS_NOW.strftime( "%Y%m%d" ) )
@@ -140,6 +162,7 @@ def _format_vcffile(dictreader, vcffile):
             if line['Type'] not in ['CTX']:
                 INFO += ';SVLEN={}'.format(int(line['Size']))
                 INFO += ";SVEND={}".format(SVEND)
+                INFO += ";END={}".format(SVEND)
             
             # write alternate ALT field for Intrachromosomal translocations
             if line['Type'] in ['CTX']:

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

+package nl.lumc.sasc.biopet.core
+
+import java.io.File
+
+import htsjdk.samtools.reference.IndexedFastaSequenceFile
+import nl.lumc.sasc.biopet.core.config.Configurable
+import scala.collection.JavaConversions._
+
+/**
+ * Created by pjvan_thof on 4/6/15.
+ */
+trait Reference extends Configurable {
+
+  def referenceSpecies: String = {
+    root match {
+      case r: Reference if r.referenceSpecies != "unknown_species" => r.referenceSpecies
+      case _ => config("species", default = "unknown_species", path = super.configPath)
+    }
+  }
+
+  def referenceName: String = {
+    root match {
+      case r: Reference if r.referenceName != "unknown_ref" => r.referenceName
+      case _ => {
+        val default: String = config("default", default = "unknown_ref", path = List("references", referenceSpecies))
+        config("reference_name", default = default, path = super.configPath)
+      }
+    }
+  }
+
+  override def subPath = {
+    referenceConfigPath ::: super.subPath
+  }
+
+  /** Returns the reference config path */
+  def referenceConfigPath = {
+    List("references", referenceSpecies, referenceName)
+  }
+
+  protected def faiRequired = false
+
+  protected def dictRequired = false
+
+  /** Returns the fasta file */
+  def referenceFasta(): File = {
+    val file: File = config("reference_fasta")
+    checkFasta(file)
+
+    val dict = new File(file.getAbsolutePath.stripSuffix(".fa").stripSuffix(".fasta") + ".dict")
+    val fai = new File(file.getAbsolutePath + ".fai")
+
+    this match {
+      case c: BiopetCommandLineFunctionTrait => c.deps :::= dict :: fai :: Nil
+      case _                                 =>
+    }
+
+    file
+  }
+
+  /** Create summary part for reference */
+  def referenceSummary: Map[String, Any] = {
+    val file = new IndexedFastaSequenceFile(referenceFasta())
+    Map("contigs" ->
+      (for (seq <- file.getSequenceDictionary.getSequences) yield seq.getSequenceName -> {
+        val md5 = Option(seq.getAttribute("M5"))
+        Map("md5" -> md5, "length" -> seq.getSequenceLength)
+      }).toMap,
+      "species" -> referenceSpecies,
+      "name" -> referenceName
+    )
+  }
+
+  //TODO: this become obsolete when index get autogenerated
+
+  /** Check fasta file if file exist and index file are there */
+  def checkFasta(file: File): Unit = {
+    if (!Reference.checked.contains(file)) {
+      require(file.exists(), "Reference not found: " + file)
+
+      if (dictRequired) {
+        val dict = new File(file.getAbsolutePath.stripSuffix(".fa").stripSuffix(".fasta") + ".dict")
+        require(dict.exists(), "Reference is missing a dict file")
+      }
+
+      if (faiRequired) {
+        val fai = new File(file.getAbsolutePath + ".fai")
+        require(fai.exists(), "Reference is missing a fai file")
+        require(IndexedFastaSequenceFile.canCreateIndexedFastaReader(file), "Index of reference cannot be loaded, reference: " + file)
+      }
+
+      Reference.checked += file
+    }
+  }
+}
+
+object Reference {
+
+  /** Used as cache to avoid double checking */
+  private var checked: Set[File] = Set()
+}

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Configurable.scala

@@ -22,11 +22,11 @@ trait Configurable extends ImplicitConversions {
   val root: Configurable
   def globalConfig: Config = if (root != null) root.globalConfig else Config.global
 
-  /** subfix to the path */
+  /** suffix to the path */
   def subPath: List[String] = Nil
 
   /** Get default path to search config values for current object */
-  def configPath: List[String] = if (root != null) root.configFullPath ::: subPath else subPath
+  def configPath: List[String] = if (root != null) root.configFullPath else Nil
 
   /** Gets name of module for config */
   protected[core] def configName = getClass.getSimpleName.toLowerCase
@@ -92,7 +92,7 @@ trait Configurable extends ImplicitConversions {
       val s = if (sample != null || defaultSample.isEmpty) sample else defaultSample.get
       val l = if (library != null || defaultLibrary.isEmpty) library else defaultLibrary.get
       val m = if (submodule != null) submodule else configName
-      val p = if (path == null) getConfigPath(s, l, submodule) else path
+      val p = (if (path == null) getConfigPath(s, l, submodule) ::: subPath else path)
       val d = {
         val value = Config.getValueFromMap(defaults.toMap, ConfigValueIndex(m, p, key, freeVar))
         if (value.isDefined) value.get.value else default
@@ -119,7 +119,7 @@ trait Configurable extends ImplicitConversions {
       val s = if (sample != null || defaultSample.isEmpty) sample else defaultSample.get
       val l = if (library != null || defaultLibrary.isEmpty) library else defaultLibrary.get
       val m = if (submodule != null) submodule else configName
-      val p = if (path == null) getConfigPath(s, l, submodule) else path
+      val p = (if (path == null) getConfigPath(s, l, submodule) ::: subPath else path)
 
       globalConfig.contains(m, p, key, freeVar) || !(Config.getValueFromMap(defaults.toMap, ConfigValueIndex(m, p, key, freeVar)) == None)
     }

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Bowtie.scala

@@ -17,7 +17,7 @@ package nl.lumc.sasc.biopet.extensions
 
 import java.io.File
 
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Reference, BiopetCommandLineFunction }
 import nl.lumc.sasc.biopet.core.config.Configurable
 import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
 
@@ -26,7 +26,7 @@ import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
  *
  * Based on version 1.1.1
  */
-class Bowtie(val root: Configurable) extends BiopetCommandLineFunction {
+class Bowtie(val root: Configurable) extends BiopetCommandLineFunction with Reference {
   @Input(doc = "Fastq file R1", shortName = "R1")
   var R1: File = null
 
@@ -34,7 +34,7 @@ class Bowtie(val root: Configurable) extends BiopetCommandLineFunction {
   var R2: Option[File] = None
 
   @Input(doc = "The reference file for the bam files.", shortName = "R", required = true)
-  var reference: File = config("reference")
+  var reference: File = null
 
   @Output(doc = "Output file SAM", shortName = "output", required = true)
   var output: File = null
@@ -59,6 +59,11 @@ class Bowtie(val root: Configurable) extends BiopetCommandLineFunction {
   var maqerr: Option[Int] = config("maqerr")
   var maxins: Option[Int] = config("maxins")
 
+  override def beforeGraph {
+    super.beforeGraph
+    if (reference == null) reference = referenceFasta()
+  }
+
   /** return commandline to execute */
   def cmdLine = {
     required(executable) +

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Gsnap.scala

@@ -19,14 +19,14 @@ import java.io.File
 
 import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
 
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Reference, BiopetCommandLineFunction }
 import nl.lumc.sasc.biopet.core.config.Configurable
 
 /**
  * Wrapper for the gsnap command line tool
  * Written based on gsnap version 2014-05-15
  */
-class Gsnap(val root: Configurable) extends BiopetCommandLineFunction {
+class Gsnap(val root: Configurable) extends BiopetCommandLineFunction with Reference {
 
   /** default executable */
   executable = config("exe", default = "gsnap", freeVar = false)

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Stampy.scala

@@ -17,12 +17,12 @@ package nl.lumc.sasc.biopet.extensions
 
 import java.io.File
 
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Reference, BiopetCommandLineFunction }
 import nl.lumc.sasc.biopet.core.config.Configurable
 import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
 
 /** Extension for stampy */
-class Stampy(val root: Configurable) extends BiopetCommandLineFunction {
+class Stampy(val root: Configurable) extends BiopetCommandLineFunction with Reference {
   @Input(doc = "FastQ file R1", shortName = "R1")
   var R1: File = _
 
@@ -30,7 +30,7 @@ class Stampy(val root: Configurable) extends BiopetCommandLineFunction {
   var R2: File = _
 
   @Input(doc = "The reference file for the bam files.", shortName = "ref")
-  var reference: File = config("reference")
+  var reference: File = null
 
   @Input(doc = "The genome prefix.")
   var genome: File = config("genome")
@@ -73,6 +73,7 @@ class Stampy(val root: Configurable) extends BiopetCommandLineFunction {
   override def beforeGraph: Unit = {
     super.beforeGraph
     require(readgroup != null)
+    if (reference == null) reference = referenceFasta()
   }
 
   /** Returns command to execute */

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Star.scala

@@ -17,16 +17,16 @@ package nl.lumc.sasc.biopet.extensions
 
 import java.io.File
 
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Reference, BiopetCommandLineFunction }
 import nl.lumc.sasc.biopet.core.config.Configurable
 import org.broadinstitute.gatk.utils.commandline.{ Argument, Input, Output }
 
 /**
  * Extension for STAR
  */
-class Star(val root: Configurable) extends BiopetCommandLineFunction {
+class Star(val root: Configurable) extends BiopetCommandLineFunction with Reference {
   @Input(doc = "The reference file for the bam files.", required = false)
-  var reference: File = new File(config("reference"))
+  var reference: File = null
 
   @Input(doc = "Fastq file R1", required = false)
   var R1: File = _
@@ -57,7 +57,7 @@ class Star(val root: Configurable) extends BiopetCommandLineFunction {
   @Argument(doc = "Output Directory")
   var outputDir: File = _
 
-  var genomeDir: File = config("genomeDir", new File(reference.getAbsoluteFile.getParent, "star"))
+  var genomeDir: File = null
   var runmode: String = _
   var sjdbOverhang: Int = _
   var outFileNamePrefix: String = _
@@ -68,6 +68,9 @@ class Star(val root: Configurable) extends BiopetCommandLineFunction {
 
   /** Sets output files for the graph */
   override def beforeGraph() {
+    super.beforeGraph
+    if (reference == null) reference = referenceFasta()
+    genomeDir = config("genomeDir", new File(reference.getAbsoluteFile.getParent, "star"))
     if (outFileNamePrefix != null && !outFileNamePrefix.endsWith(".")) outFileNamePrefix += "."
     val prefix = if (outFileNamePrefix != null) outputDir + outFileNamePrefix else outputDir
     if (runmode == null) {

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/VariantEffectPredictor.scala

@@ -17,7 +17,7 @@ package nl.lumc.sasc.biopet.extensions
 
 import java.io.File
 
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
+import nl.lumc.sasc.biopet.core.{ Reference, BiopetCommandLineFunction }
 import nl.lumc.sasc.biopet.core.config.Configurable
 import org.broadinstitute.gatk.utils.commandline.{ Output, Input }
 
@@ -25,7 +25,7 @@ import org.broadinstitute.gatk.utils.commandline.{ Output, Input }
  * Extension for VariantEffectPredictor
  * Created by ahbbollen on 15-1-15.
  */
-class VariantEffectPredictor(val root: Configurable) extends BiopetCommandLineFunction {
+class VariantEffectPredictor(val root: Configurable) extends BiopetCommandLineFunction with Reference {
 
   executable = config("exe", submodule = "perl", default = "perl")
   var vep_script: String = config("vep_script")

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/breakdancer/Breakdancer.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.breakdancer
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.config.Configurable
+import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
+import org.broadinstitute.gatk.queue.QScript
+
+/// Breakdancer is actually a mini pipeline executing binaries from the breakdancer package
+class Breakdancer(val root: Configurable) extends QScript with BiopetQScript {
+  def this() = this(null)
+
+  @Input(doc = "Input file (bam)")
+  var input: File = _
+
+  @Input(doc = "Reference Fasta file")
+  var reference: File = _
+
+  @Argument(doc = "Work directory")
+  var workdir: String = _
+
+  var deps: List[File] = Nil
+
+  @Output(doc = "Breakdancer config")
+  lazy val configfile: File = {
+    new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".breakdancer.cfg")
+  }
+  @Output(doc = "Breakdancer raw output")
+  lazy val outputraw: File = {
+    new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".breakdancer.tsv")
+  }
+  @Output(doc = "Breakdancer VCF output")
+  lazy val outputvcf: File = {
+    new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".breakdancer.vcf")
+  }
+
+  override def init() {
+  }
+
+  def biopetScript() {
+    // read config and set all parameters for the pipeline
+    logger.info("Starting Breakdancer configuration")
+
+    val bdcfg = BreakdancerConfig(this, input, this.configfile)
+    bdcfg.deps = this.deps
+    outputFiles += ("cfg" -> bdcfg.output)
+    add(bdcfg)
+
+    val breakdancer = BreakdancerCaller(this, bdcfg.output, this.outputraw)
+    add(breakdancer)
+    outputFiles += ("tsv" -> breakdancer.output)
+
+    val bdvcf = BreakdancerVCF(this, breakdancer.output, this.outputvcf)
+    add(bdvcf)
+    outputFiles += ("vcf" -> bdvcf.output)
+  }
+}
+
+object Breakdancer extends PipelineCommand {
+  def apply(root: Configurable, input: File, reference: File, runDir: String): Breakdancer = {
+    val breakdancer = new Breakdancer(root)
+    breakdancer.input = input
+    breakdancer.reference = reference
+    breakdancer.workdir = runDir
+    breakdancer.init
+    breakdancer.biopetScript
+    return breakdancer
+  }
+}
\ No newline at end of file

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Breakdancer.scala → public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/breakdancer/BreakdancerCaller.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.svcallers
+package nl.lumc.sasc.biopet.extensions.breakdancer
 
-import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction