From b35535282b0396962e483dd7572a8c9a69d70e35 Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Mon, 26 May 2014 19:25:18 +0200
Subject: [PATCH] Gatk now uses the mapping module
---
gatk/examples/test.json | 28 +++++++
gatk/nbactions.xml | 6 +-
gatk/pom.xml | 2 +-
.../sasc/biopet/pipelines/gatk/Gatk.scala | 83 +++++++------------
.../biopet/pipelines/mapping/Mapping.scala | 6 +-
5 files changed, 65 insertions(+), 60 deletions(-)
create mode 100644 gatk/examples/test.json
diff --git a/gatk/examples/test.json b/gatk/examples/test.json
new file mode 100644
index 000000000..a7a018eb3
--- /dev/null
+++ b/gatk/examples/test.json
@@ -0,0 +1,28 @@
+{
+ "fastqc": { "exe": "/home/pjvan_thof/Downloads/FastQC/fastqc" },
+ "bwa" : {"exe":"/home/pjvan_thof/pipelines/test/test"},
+ "flexiprep": {
+ "fastqc": {"exe":"/home/pjvan_thof/pipelines/test/test"},
+ "cutadapt": {"exe":"/home/pjvan_thof/pipelines/test/test"},
+ "sickle": {"exe":"/home/pjvan_thof/pipelines/test/test"}
+ },
+ "gatk": {
+ "referenceFile" : "/home/pjvan_thof/pipelines/test/test",
+ "dbsnp": "/home/pjvan_thof/pipelines/test/test",
+ "hapmap": "/home/pjvan_thof/pipelines/test/test",
+ "omni": "/home/pjvan_thof/pipelines/test/test",
+ "1000G": "/home/pjvan_thof/pipelines/test/test",
+ "mills": "/home/pjvan_thof/pipelines/test/test"
+ },
+ "Samples": {
+ "test": {
+ "ID": "test",
+ "Runs": {
+ "1" : {
+ "ID": "1",
+ "R1" : "/home/pjvan_thof/pipelines/test/test.fastq"
+ }
+ }
+ }
+ }
+}
diff --git a/gatk/nbactions.xml b/gatk/nbactions.xml
index 531ad188f..fa72b2b19 100644
--- a/gatk/nbactions.xml
+++ b/gatk/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.gatk.Gatk</exec.args>
+ <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.Gatk -config /home/pjvan_thof/pipelines/biopet/gatk/examples/test.json -outputDir /home/pjvan_thof/pipelines/test -l debug</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=${jpda.address} -classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.Gatk</exec.args>
+ <exec.args>-Xdebug -Xrunjdwp:transport=dt_socket,server=n,address=${jpda.address} -classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.Gatk -config /home/pjvan_thof/pipelines/biopet/gatk/examples/test.json -outputDir /home/pjvan_thof/pipelines/test -l debug</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.gatk.Gatk</exec.args>
+ <exec.args>-classpath %classpath nl.lumc.sasc.biopet.pipelines.gatk.Gatk -config /home/pjvan_thof/pipelines/biopet/gatk/examples/test.json -outputDir /home/pjvan_thof/pipelines/test -l debug</exec.args>
<exec.executable>java</exec.executable>
<exec.workingdir>/home/pjvan_thof/pipelines/test</exec.workingdir>
</properties>
diff --git a/gatk/pom.xml b/gatk/pom.xml
index 133eb8070..5c1f239b0 100644
--- a/gatk/pom.xml
+++ b/gatk/pom.xml
@@ -49,7 +49,7 @@
</dependency>
<dependency>
<groupId>nl.lumc.sasc</groupId>
- <artifactId>Flexiprep</artifactId>
+ <artifactId>Mapping</artifactId>
<version>0.1.0</version>
</dependency>
<dependency>
diff --git a/gatk/src/main/java/nl/lumc/sasc/biopet/pipelines/gatk/Gatk.scala b/gatk/src/main/java/nl/lumc/sasc/biopet/pipelines/gatk/Gatk.scala
index 1d0b49b6e..daabf90b9 100644
--- a/gatk/src/main/java/nl/lumc/sasc/biopet/pipelines/gatk/Gatk.scala
+++ b/gatk/src/main/java/nl/lumc/sasc/biopet/pipelines/gatk/Gatk.scala
@@ -1,7 +1,9 @@
package nl.lumc.sasc.biopet.pipelines.gatk
import nl.lumc.sasc.biopet.wrappers._
+import nl.lumc.sasc.biopet.wrappers.aligners._
import nl.lumc.sasc.biopet.core._
+import nl.lumc.sasc.biopet.pipelines.mapping._
import nl.lumc.sasc.biopet.pipelines.flexiprep._
import org.broadinstitute.sting.queue.QScript
import org.broadinstitute.sting.queue.extensions.gatk._
@@ -120,8 +122,6 @@ class Gatk(private var globalConfig: Config) extends QScript {
}
add(indelApplyRecalibration)
} else logger.warn("No gVCFs to genotype")
-
-
}
}
@@ -179,67 +179,40 @@ class Gatk(private var globalConfig: Config) extends QScript {
if (fastq_R1 != null) {
val runDir: String = outputDir + sampleID + "/run_" + runID + "/"
- val flexiprep = new Flexiprep(config)
- flexiprep.input_R1 = fastq_R1
- if (paired) flexiprep.input_R2 = fastq_R2
- flexiprep.outputDir = runDir + "flexiprep/"
- flexiprep.script
- addAll(flexiprep.functions) // Add functions of flexiprep to curent function pool
-
- val bwaCommand = new Bwa(config)
- bwaCommand.R1 = flexiprep.outputFiles("output_R1")
- if (paired) bwaCommand.R2 = flexiprep.outputFiles("output_R2")
- //bwaCommand.referenceFile = qscript.referenceFile
- //bwaCommand.nCoresRequest = 8
- bwaCommand.jobResourceRequests :+= "h_vmem=6G"
- bwaCommand.RG = "@RG\\t" +
- "ID:" + sampleID + "_" + runID + "\\t" +
- "LB:" + sampleID + "_" + runID + "\\t" +
- "PL:illumina\\t" +
- "CN:SASC\\t" +
- "SM:" + sampleID + "\\t" +
- "PU:na"
- bwaCommand.output = new File(runDir + sampleID + "-run_" + runID + ".sam")
- add(bwaCommand)
+ val mapping = new Mapping(config)
+ mapping.input_R1 = fastq_R1
+ if (paired) mapping.input_R2 = fastq_R2
+ mapping.outputDir = runDir + "mapping/"
+ mapping.RGSM = sampleID
+ mapping.RGLB = runID
+ if (runConfig.contains("PL")) mapping.RGPL = runConfig.getAsString("PL")
+ if (runConfig.contains("PU")) mapping.RGPU = runConfig.getAsString("PU")
+ if (runConfig.contains("CN")) mapping.RGCN = runConfig.getAsString("CN")
+ mapping.script
+ addAll(mapping.functions) // Add functions of mapping to curent function pool
- var bamFile:File = addSortSam(List(bwaCommand.output), swapExt(runDir,bwaCommand.output,".sam",".bam"), runDir)
- bamFile = addMarkDuplicates(List(bamFile), swapExt(runDir,bamFile,".bam",".dedup.bam"), runDir)
- bamFile = addIndelRealign(bamFile,runDir) // Indel realigner
+ var bamFile:File = addIndelRealign(mapping.outputFiles("finalBamFile"),runDir) // Indel realigner
bamFile = addBaseRecalibrator(bamFile,runDir) // Base recalibrator
outputFiles += ("FinalBam" -> bamFile)
} else this.logger.error("Sample: " + sampleID + ": No R1 found for runs: " + runConfig)
return outputFiles
}
-
- def addSortSam(inputSam:List[File], outputFile:File, dir:String) : File = {
- val sortSam = new SortSam {
- this.input = inputSam
- this.createIndex = true
- this.output = outputFile
- this.memoryLimit = 2
- this.nCoresRequest = 2
- this.jobResourceRequests :+= "h_vmem=4G"
- }
- add(sortSam)
-
- return sortSam.output
- }
-
- def addMarkDuplicates(inputBams:List[File], outputFile:File, dir:String) : File = {
- val markDuplicates = new MarkDuplicates {
- this.input = inputBams
- this.output = outputFile
- this.REMOVE_DUPLICATES = false
- this.metrics = swapExt(dir,outputFile,".bam",".metrics")
- this.outputIndex = swapExt(dir,this.output,".bam",".bai")
- this.memoryLimit = 2
- this.jobResourceRequests :+= "h_vmem=4G"
- }
- add(markDuplicates)
- return markDuplicates.output
- }
+// def addMarkDuplicates(inputBams:List[File], outputFile:File, dir:String) : File = {
+// val markDuplicates = new MarkDuplicates {
+// this.input = inputBams
+// this.output = outputFile
+// this.REMOVE_DUPLICATES = false
+// this.metrics = swapExt(dir,outputFile,".bam",".metrics")
+// this.outputIndex = swapExt(dir,this.output,".bam",".bai")
+// this.memoryLimit = 2
+// this.jobResourceRequests :+= "h_vmem=4G"
+// }
+// add(markDuplicates)
+//
+// return markDuplicates.output
+// }
def addIndelRealign(inputBam:File, dir:String): File = {
val realignerTargetCreator = new RealignerTargetCreator with gatkArguments {
diff --git a/mapping/src/main/java/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala b/mapping/src/main/java/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
index 73b181452..5a1b5960d 100644
--- a/mapping/src/main/java/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
+++ b/mapping/src/main/java/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
@@ -1,6 +1,7 @@
package nl.lumc.sasc.biopet.pipelines.mapping
import nl.lumc.sasc.biopet.wrappers._
+import nl.lumc.sasc.biopet.wrappers.aligners._
import java.util.Date
import nl.lumc.sasc.biopet.core._
import nl.lumc.sasc.biopet.pipelines.flexiprep._
@@ -19,7 +20,7 @@ class Mapping(private var globalConfig: Config) extends QScript {
@Input(doc="R1 fastq file", shortName="R1",required=true) var input_R1: File = _
@Input(doc="R2 fastq file", shortName="R2", required=false) var input_R2: File = _
@Argument(doc="Output directory", shortName="outputDir", required=true) var outputDir: String = _
- @Argument(doc="Output name", shortName="outputName", required=true) var outputName: String = _
+ @Argument(doc="Output name", shortName="outputName", required=false) var outputName: String = _
@Argument(doc="Skip flexiprep", shortName="skipflexiprep", required=false) var skipFlexiprep: Boolean = false
@Argument(doc="Skip mark duplicates", shortName="skipmarkduplicates", required=false) var skipMarkduplicates: Boolean = false
@Argument(doc="Alginer", shortName="ALN", required=false) var aligner: String = _
@@ -64,6 +65,8 @@ class Mapping(private var globalConfig: Config) extends QScript {
if (RGPU == null) RGPU = config.getAsString("RGPU", "na")
if (RGCN == null && config.contains("RGCN")) RGCN = config.getAsString("RGCN")
if (RGDS == null && config.contains("RGDS")) RGDS = config.getAsString("RGDS")
+
+ if (outputName == null) outputName = RGID
}
def script() {
@@ -94,6 +97,7 @@ class Mapping(private var globalConfig: Config) extends QScript {
}
if (!skipMarkduplicates) bamFile = addMarkDuplicates(List(bamFile), swapExt(outputDir,bamFile,".bam",".dedup.bam"), outputDir)
+ outputFiles += ("finalBamFile" -> bamFile)
}
def addSortSam(inputSam:List[File], outputFile:File, dir:String) : File = {
--
GitLab