Added a benchmark pipeline for gvcf

gatk-benchmark-genotyping/.gitignore

+/target/
\ No newline at end of file

gatk-benchmark-genotyping/examples/test.json

+{
+    "gvcffiles": ["test4.vcf", "test5.vcf"],
+    "reference" : "/data/DIV5/SASC/common/gatk_bundle_2.8/hg19/ucsc.hg19.fasta",
+    "dbsnp": "bla",
+    "haplotypecaller": {
+            "stand_call_conf": 20,
+            "stand_emit_conf": 20
+        }
+}

gatk-benchmark-genotyping/pom.xml

+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+
+  <groupId>nl.lumc.sasc</groupId>
+  <artifactId>GatkBenchmarkGenotyping</artifactId>
+  <version>0.1.3</version>
+  <packaging>jar</packaging>
+
+  <name>GatkBenchmarkGenotyping</name>
+  <url>http://maven.apache.org</url>
+  
+  <parent>
+      <groupId>nl.lumc.sasc</groupId>
+      <artifactId>Biopet</artifactId>
+      <version>0.1.3</version>
+      <relativePath>../</relativePath>
+  </parent>
+  
+  <properties>
+    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+    <sting.unpack.phase>prepare-package</sting.unpack.phase>
+    <sting.shade.phase>package</sting.shade.phase>
+    <app.main.class>nl.lumc.sasc.biopet.pipelines.gatk.GatkBenchmarkGenotyping</app.main.class>
+  </properties>
+  
+    <dependencies>
+<!--        <dependency>
+          <groupId>junit</groupId>
+          <artifactId>junit</artifactId>
+          <version>3.8.1</version>
+          <scope>test</scope>
+        </dependency>-->
+        <dependency>
+            <groupId>org.scala-lang</groupId>
+            <artifactId>scala-compiler</artifactId>
+            <version>2.11.0</version>
+        </dependency>
+<!--        <dependency>
+            <groupId>org.scalatest</groupId>
+            <artifactId>scalatest_2.9.2</artifactId>
+            <version>2.0.M4</version>
+            <scope>test</scope>
+        </dependency>-->
+        <dependency>
+            <groupId>nl.lumc.sasc</groupId>
+            <artifactId>GatkGenotyping</artifactId>
+            <version>0.1.3</version>
+        </dependency>
+        <dependency>
+            <groupId>nl.lumc.sasc</groupId>
+            <artifactId>Biopet-Framework</artifactId>
+            <version>0.1.3</version>
+        </dependency>
+        <dependency>
+            <groupId>org.broadinstitute.gatk</groupId>
+            <artifactId>queue-package</artifactId>
+            <version>3.2-2</version>
+        </dependency>
+    </dependencies>
+    <build>
+        <resources>
+            <resource>
+                 <directory>scripts</directory>
+                 <includes>
+                     <include>**/*</include>
+                 </includes>
+            </resource>
+        </resources>
+        <plugins>
+            <plugin>
+                <groupId>org.scala-tools</groupId>
+                <artifactId>maven-scala-plugin</artifactId>
+                <version>2.15.2</version>
+                <executions>
+                    <execution>
+                        <id>scala-compile</id>
+                        <goals>
+                            <goal>compile</goal>
+                            <goal>testCompile</goal>
+                        </goals>
+                        <configuration>
+                            <args>
+                                <arg>-dependencyfile</arg>
+                                <arg>${project.build.directory}/.scala_dependencies</arg>
+                            </args>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+<!--            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-surefire-plugin</artifactId>
+                <version>2.7.2</version>
+                <executions>
+                    <execution>
+                        <id>default-test</id>
+                         Disable the default-test by putting it in phase none 
+                        <phase>none</phase>
+                    </execution>
+                </executions>
+            </plugin>-->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-shade-plugin</artifactId>
+                <version>2.3</version>
+                <configuration>
+                  <finalName>${project.artifactId}-${project.version}</finalName>
+                  <transformers>
+                    <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
+                      <manifestEntries>
+                        <Main-Class>${app.main.class}</Main-Class>
+                        <X-Compile-Source-JDK>${maven.compile.source}</X-Compile-Source-JDK>
+                        <X-Compile-Target-JDK>${maven.compile.target}</X-Compile-Target-JDK>
+                      </manifestEntries>
+                    </transformer>
+                  </transformers>
+                  <artifactSet>
+                    <excludes>
+                      <exclude>org.broadinstitute.gatk:queue-package</exclude>
+                      <exclude>junit:junit</exclude>
+                      <exclude>org.scala-lang:scala-compiler</exclude>
+                      <exclude>org.scala-lang:scala-library</exclude>
+                      <exclude>org.scala-lang:scala-reflect</exclude>
+                      <exclude>org.scala-lang.modules:*</exclude>
+                    </excludes>
+                  </artifactSet>
+                </configuration>
+            <executions>
+              <execution>
+                <phase>package</phase>
+                <goals>
+                  <goal>shade</goal>
+                </goals>
+              </execution>
+            </executions>
+          </plugin>
+        </plugins>
+    </build>
+</project>

gatk-benchmark-genotyping/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala

+package nl.lumc.sasc.biopet.pipelines.gatk
+
+import nl.lumc.sasc.biopet.core._
+import nl.lumc.sasc.biopet.core.config._
+import nl.lumc.sasc.biopet.function._
+import org.broadinstitute.gatk.queue.QScript
+import org.broadinstitute.gatk.queue.extensions.gatk.{CommandLineGATK, GenotypeGVCFs, SelectVariants}
+import org.broadinstitute.gatk.queue.function._
+import org.broadinstitute.gatk.utils.commandline.{Input, Output, Argument}
+import scala.util.Random
+
+class GatkBenchmarkGenotyping(val root:Configurable) extends QScript with BiopetQScript {
+  def this() = this(null)
+  
+  @Input(doc="Sample gvcf file")
+  var sampleGvcf: File = _
+  
+  @Argument(doc="SampleName", required=true)
+  var sampleName: String = _
+  
+  @Input(doc="Gvcf files", shortName="I", required=false)
+  var gvcfFiles: List[File] = Nil
+  
+  @Argument(doc="Reference", shortName="R", required=false)
+  var reference: File = _
+  
+  @Argument(doc="Dbsnp", shortName="dbsnp", required=false)
+  var dbsnp: File = _
+    
+  def init() {
+    if (configContains("gvcffiles")) for (file <- config("gvcffiles").getList) {
+      gvcfFiles ::= file.toString
+    }
+    if (reference == null) reference = config("reference")
+    if (dbsnp == null && configContains("dbsnp")) dbsnp = config("dbsnp")
+    if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
+    else if (!outputDir.endsWith("/")) outputDir += "/"
+  }
+  
+  def biopetScript() {
+    var todoGvcfs = gvcfFiles
+    var gvcfPool: List[File] = Nil
+    addGenotypingPipeline(gvcfPool)
+    
+    while (todoGvcfs.size > 0) {
+      val index = Random.nextInt(todoGvcfs.size)
+      gvcfPool ::= todoGvcfs(index)
+      addGenotypingPipeline(gvcfPool)
+      todoGvcfs = todoGvcfs.filter(b => b != todoGvcfs(index))
+    }
+  }
+  
+  trait gatkArguments extends CommandLineGATK {
+    this.reference_sequence = reference
+    this.memoryLimit = 2
+    this.jobResourceRequests :+= "h_vmem=4G"
+  }
+  
+  def addGenotypingPipeline(gvcfPool: List[File]) {
+    val gatkGenotyping = new GatkGenotyping(this)
+    gatkGenotyping.inputGvcfs = sampleGvcf :: gvcfPool
+    gatkGenotyping.samples :+= sampleName
+    gatkGenotyping.outputDir = outputDir + "samples_" + gvcfPool.size + "/"
+    gatkGenotyping.init
+    gatkGenotyping.biopetScript
+    addAll(gatkGenotyping.functions)
+  }
+}
+
+object GatkBenchmarkGenotyping extends PipelineCommand {
+  override val pipeline = "/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.class"
+}