Added Vcf sample compare module

bam-metrics/examples/test.json

 {
     "reference": "bla",
     "bedtools": { "exe": "test"},
-    "samtools": { "exe": "test"}
+    "samtools": { "exe": "test"},
+    "targetBed": ["target_1", "target_2"]
 }

bam-metrics/nbactions.xml

@@ -10,7 +10,7 @@
                 <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
             </goals>
             <properties>
-                <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics -BAM test.bam -outputDir /home/pjvan_thof/pipelines/test -config /home/pjvan_thof/pipelines/biopet/bam-metrics/examples/test.json</exec.args>
+                <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics -BAM test.bam -outDir /home/pjvan_thof/pipelines/test -config /home/pjvan_thof/pipelines/biopet/bam-metrics/examples/test.json</exec.args>
                 <exec.executable>java</exec.executable>
                 <exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
             </properties>
@@ -25,7 +25,7 @@
                 <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
             </goals>
             <properties>
-                <exec.args>-Xdebug -Xrunjdwp:transport=dt_socket,server=n,address=${jpda.address} -classpath %classpath nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics -BAM test.bam -outputDir /home/pjvan_thof/pipelines/test -config /home/pjvan_thof/pipelines/biopet/bam-metrics/examples/test.json</exec.args>
+                <exec.args>-Xdebug -Xrunjdwp:transport=dt_socket,server=n,address=${jpda.address} -classpath %classpath nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics -BAM test.bam -outDir /home/pjvan_thof/pipelines/test -config /home/pjvan_thof/pipelines/biopet/bam-metrics/examples/test.json</exec.args>
                 <exec.executable>java</exec.executable>
                 <jpda.listen>true</jpda.listen>
                 <exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
@@ -41,7 +41,7 @@
                 <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
             </goals>
             <properties>
-                <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics -BAM test.bam -outputDir /home/pjvan_thof/pipelines/test -config /home/pjvan_thof/pipelines/biopet/bam-metrics/examples/test.json</exec.args>
+                <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics -BAM test.bam -outDir /home/pjvan_thof/pipelines/test -config /home/pjvan_thof/pipelines/biopet/bam-metrics/examples/test.json</exec.args>
                 <exec.executable>java</exec.executable>
                 <exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
             </properties>

flexiprep/examples/test.json

 {
-    "fastqc": { "exe": "/home/pjvan_thof/Downloads/FastQC/fastqc" },
+    "fastqc": { "exe": "/data/DIV5/SASC/common/programs/FastQC/fastqc_v0.11.2/fastqc" },
     "flexiprep": {
         "seqtk": {"exe":"/data/DIV5/SASC/common/programs/seqtk/seqtk/seqtk"},
         "cutadapt": {"exe":"/home/pjvan_thof/.local/bin/cutadapt"},

gatk/gatk-vcf-sample-compare/.gitignore

+/target/
\ No newline at end of file

gatk/gatk-vcf-sample-compare/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/gatk-vcf-sample-compare/nbactions.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<actions>
+        <action>
+            <actionName>run</actionName>
+            <packagings>
+                <packaging>jar</packaging>
+            </packagings>
+            <goals>
+                <goal>process-classes</goal>
+                <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
+            </goals>
+            <properties>
+                <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.GatkVcfSampleCompare -config /home/pjvan_thof/pipelines/biopet/gatk/gatk-vcf-sample-compare/examples/test.json -outDir /home/pjvan_thof/pipelines/test -l debug -V test.vcf -sample bla1 -sample bla2 -sample bla3 -sample bla4</exec.args>
+                <exec.executable>java</exec.executable>
+                <exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
+            </properties>
+        </action>
+        <action>
+            <actionName>debug</actionName>
+            <packagings>
+                <packaging>jar</packaging>
+            </packagings>
+            <goals>
+                <goal>process-classes</goal>
+                <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
+            </goals>
+            <properties>
+                <exec.args>-Xdebug -Xrunjdwp:transport=dt_socket,server=n,address=${jpda.address} -classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.GatkVcfSampleCompare -config /home/pjvan_thof/pipelines/biopet/gatk/gatk-vcf-sample-compare/examples/test.json -outDir /home/pjvan_thof/pipelines/test -l debug -V test.vcf -sample bla1 -sample bla2 -sample bla3 -sample bla4</exec.args>
+                <exec.executable>java</exec.executable>
+                <jpda.listen>true</jpda.listen>
+                <exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
+            </properties>
+        </action>
+        <action>
+            <actionName>profile</actionName>
+            <packagings>
+                <packaging>jar</packaging>
+            </packagings>
+            <goals>
+                <goal>process-classes</goal>
+                <goal>org.codehaus.mojo:exec-maven-plugin:1.2.1:exec</goal>
+            </goals>
+            <properties>
+                <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.GatkVcfSampleCompare -config /home/pjvan_thof/pipelines/biopet/gatk/gatk-vcf-sample-compare/examples/test.json -outDir /home/pjvan_thof/pipelines/test -l debug -V test.vcf -sample bla1 -sample bla2 -sample bla3 -sample bla4</exec.args>
+                <exec.executable>java</exec.executable>
+                <exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
+            </properties>
+        </action>
+    </actions>

gatk/gatk-vcf-sample-compare/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>GatkVcfSampleCompare</artifactId>
+  <version>0.1.3</version>
+  <packaging>jar</packaging>
+
+  <name>GatkVcfSampleCompare</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.GatkVcfSampleCompare</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>Biopet-Framework</artifactId>
+            <version>0.1.3</version>
+        </dependency>
+        <dependency>
+            <groupId>org.broadinstitute.gatk</groupId>
+            <artifactId>gatk-queue-package-distribution</artifactId>
+            <version>3.2</version>
+        </dependency>
+    </dependencies>
+    <build>
+        <resources>
+            <resource>
+                 <directory>src/main/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:gatk-queue-package-distribution</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/gatk-vcf-sample-compare/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala

+package nl.lumc.sasc.biopet.pipelines.gatk
+
+import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
+import java.io.File
+import nl.lumc.sasc.biopet.core.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+import org.broadinstitute.gatk.queue.extensions.gatk.CommandLineGATK
+import org.broadinstitute.gatk.queue.extensions.gatk.SelectVariants
+import org.broadinstitute.gatk.queue.extensions.gatk.VariantEval
+import org.broadinstitute.gatk.utils.commandline.{ Input, Argument }
+
+class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQScript {
+  def this() = this(null)
+
+  @Input(doc = "Sample vcf file(s)", shortName = "V")
+  var vcfFiles: List[File] = _
+
+  @Argument(doc = "Reference", shortName = "R", required = false)
+  var reference: File = _
+
+  @Argument(doc = "Target bed", shortName = "targetBed", required = false)
+  var targetBed: File = _
+  
+  @Argument(doc = "Samples", shortName = "sample", required = false)
+  var samples: List[String] = Nil
+  
+  var vcfFile: File = _
+  var sampleVcfs:Map[String, File] = Map()
+  
+  trait gatkArguments extends CommandLineGATK {
+    this.reference_sequence = reference
+    this.memoryLimit = 2
+    this.jobResourceRequests :+= "h_vmem=4G"
+  }
+  
+  def init() {
+    if (reference == null) reference = config("reference")
+    if (targetBed == null) targetBed = config("targetBed")
+    if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
+    else if (!outputDir.endsWith("/")) outputDir += "/"
+  }
+
+  def biopetScript() {
+    vcfFile = vcfFiles.head
+    if (vcfFiles.size > 1) {
+      
+    } else vcfFile = vcfFiles.head
+    
+    for (sample <- samples) {
+      sampleVcfs += (sample -> new File(outputDir + sample + File.separator + sample + ".vcf"))
+      val selectVariants = new SelectVariants with gatkArguments
+      selectVariants.variant = vcfFile
+      selectVariants.out = sampleVcfs(sample)
+      selectVariants.sample_name = Seq(sample)
+      selectVariants.excludeNonVariants = true
+      add(selectVariants)
+    }
+    
+    for ((sample,sampleVcf) <- sampleVcfs) {
+      val sampleDir = outputDir + sample + File.separator
+      for ((compareSample,compareSampleVcf) <- sampleVcfs) {
+        val variantEval = new VariantEval with gatkArguments
+        variantEval.eval = Seq(sampleVcf)
+        variantEval.comp = Seq(compareSampleVcf)
+        variantEval.out = new File(sampleDir + sample + "-" + compareSample + ".eval.txt")
+        variantEval.noST = true
+        variantEval.ST = Seq("VariantType", "CompRod")
+        variantEval.noEV = true
+        variantEval.EV = Seq("CompOverlap")
+        if (targetBed != null) variantEval.L = Seq(targetBed)
+        add(variantEval)
+      }
+    }
+  }
+}
+
+object GatkVcfSampleCompare extends PipelineCommand {
+  override val pipeline = "/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.class"
+}

gatk/pom.xml

@@ -17,5 +17,6 @@
         <module>gatk-old</module>
         <module>gatk-pipeline</module>
         <module>gatk-variantcalling</module>
+        <module>gatk-vcf-sample-compare</module>
     </modules>
 </project>