From bd8a2a63b4fa4f268e4b67cb1547115ed1a01623 Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Tue, 17 Jun 2014 16:10:23 +0200
Subject: [PATCH] Added BiopetCommandlineFunction All commandlinefunctions now
extends from this trait
---
.../core/BiopetCommandLineFunction.scala | 116 ++++++++++++++++++
.../function/PythonCommandLineFunction.scala | 30 +++++
.../lumc/sasc/biopet/function/Sha1sum.scala | 17 ++-
.../nl/lumc/sasc/biopet/function/Zcat.scala | 18 +--
.../sasc/biopet/function/fastq/Cutadapt.scala | 57 ++++-----
.../sasc/biopet/function/fastq/Fastqc.scala | 75 ++++-------
.../sasc/biopet/function/fastq/Sickle.scala | 83 ++++++-------
.../flexiprep/scripts/FastqSync.scala | 16 +--
.../flexiprep/scripts/FastqcToContams.scala | 18 +--
.../flexiprep/scripts/FastqcToQualtype.scala | 16 +--
.../pipelines/flexiprep/scripts/Seqstat.scala | 17 +--
.../flexiprep/scripts/Summarize.scala | 17 +--
.../sasc/biopet/function/aligners/Bwa.scala | 61 ++++-----
.../sasc/biopet/function/aligners/Star.scala | 79 +++++++-----
14 files changed, 345 insertions(+), 275 deletions(-)
create mode 100644 biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala
create mode 100644 biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/PythonCommandLineFunction.scala
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala
new file mode 100644
index 000000000..bd7c3fb9e
--- /dev/null
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala
@@ -0,0 +1,116 @@
+package nl.lumc.sasc.biopet.core
+
+import java.io.File
+import org.broadinstitute.sting.queue.QException
+import org.broadinstitute.sting.queue.function.CommandLineFunction
+import org.broadinstitute.sting.commandline._
+import scala.sys.process._
+import scala.util.matching.Regex
+
+trait BiopetCommandLineFunction extends CommandLineFunction {
+ val globalConfig: Config
+ analysisName = getClass.getSimpleName
+ protected var config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName.toLowerCase), globalConfig)
+ logger.debug("config passed for " + analysisName)
+
+ @Input(doc="deps", required=false)
+ var deps: List[File] = Nil
+
+ @Argument(doc="Threads", required=false)
+ var threads = 0
+ val defaultThreads = 1
+
+ @Argument(doc="Vmem", required=false)
+ var vmem: String = _
+ val defaultVmem: String = ""
+
+ @Argument(doc="Executeble")
+ var executeble: String = _
+
+ protected def beforeCmd {
+ }
+
+ protected def afterGraph {
+ }
+
+ def setConfig(name:String) {
+ analysisName = name
+ config = Config.mergeConfigs(config.getAsConfig(analysisName.toLowerCase), config)
+ }
+
+ override def freezeFieldValues() {
+ checkExecuteble
+ afterGraph
+ jobOutputFile = new File(firstOutput.getParent + "/." + firstOutput.getName + "." + analysisName + ".out")
+
+ super.freezeFieldValues()
+ }
+
+ protected def checkExecuteble {
+ try if (executeble != null) {
+ val buffer = new StringBuffer()
+ val cmd = Seq("which", executeble)
+ val process = Process(cmd).run(ProcessLogger(buffer.append(_)))
+ if (process.exitValue == 0) {
+ executeble = buffer.toString
+ val file = new File(executeble)
+ executeble = file.getCanonicalPath
+ } else {
+ logger.error("executeble: '" + executeble + "' not found, please check config")
+ throw new QException("executeble: '" + executeble + "' not found, please check config")
+ }
+ } catch {
+ case ioe: java.io.IOException => logger.warn("Could not use 'which', check on executeble skipped: " + ioe)
+ }
+ }
+
+ final protected def preCmdInternal {
+ checkExecuteble
+ //for (input <- this.inputs) if (!input.exists) throw new IllegalStateException("Input: " + input + " for " + analysisName + " is missing")
+ logger.debug("Config for " + analysisName + ": " + config)
+
+ beforeCmd
+
+ addJobReportBinding("version", getVersion)
+
+ if (threads == 0) threads = config.getThreads(defaultThreads)
+ if (threads > 1) nCoresRequest = Option(threads)
+ addJobReportBinding("cores", if (nCoresRequest.get.toInt > 0) nCoresRequest.get.toInt else 1)
+
+ if (vmem == null) {
+ if (config.contains("vmem")) vmem = config.getAsString("vmem")
+ else if (!defaultVmem.isEmpty) vmem = defaultVmem
+ }
+ if (vmem != null) jobResourceRequests :+= "h_vmem=" + vmem
+ jobName = this.analysisName + ":" + firstOutput.getName
+ }
+
+ protected def cmdLine: String
+ final def commandLine: String = {
+ preCmdInternal
+ val cmd = cmdLine
+ addJobReportBinding("command", cmd)
+ cmd
+ }
+
+ protected var versionCommand: String = _
+ protected val versionRegex: Regex = null
+ def getVersion : String = {
+ if (versionCommand == null || versionRegex == null) return "N/A"
+ val buffer = new StringBuffer()
+ val process = Process(versionCommand).run(ProcessLogger(buffer append _))
+ if (process.exitValue != 0) {
+ logger.warn("Version command: '" + versionCommand + "' give exit code " + process.exitValue + ", version not found")
+ return "N/A"
+ }
+ val lines = versionCommand lines_! ProcessLogger(buffer append _)
+ for (line <- lines) {
+ line match {
+ case versionRegex(m) => return m
+ case _ =>
+ }
+ }
+ logger.warn("Version command: '" + versionCommand + "' give a exit code 0 but no version was found, executeble oke?")
+ return "N/A"
+ }
+}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/PythonCommandLineFunction.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/PythonCommandLineFunction.scala
new file mode 100644
index 000000000..ea2945642
--- /dev/null
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/PythonCommandLineFunction.scala
@@ -0,0 +1,30 @@
+package nl.lumc.sasc.biopet.function
+
+import java.io.FileOutputStream
+import nl.lumc.sasc.biopet.core._
+import org.broadinstitute.sting.commandline._
+import java.io.File
+import scala.collection.JavaConversions._
+
+trait PythonCommandLineFunction extends BiopetCommandLineFunction {
+ executeble = config.getAsString("python_exe", "python")
+
+ @Input(doc="Python script", required=false)
+ var python_script: File = _
+
+ protected var python_script_name : String = _
+ def setPythonScript(script:String) { setPythonScript(script,"") }
+ def setPythonScript(script:String, subpackage:String) {
+ python_script_name = script
+ python_script = new File(".queue/tmp/" + subpackage + python_script_name)
+ if (!python_script.getParentFile.exists) python_script.getParentFile.mkdirs
+ val is = getClass.getResourceAsStream(subpackage + python_script_name)
+ val os = new FileOutputStream(python_script)
+ org.apache.commons.io.IOUtils.copy(is, os)
+ os.close()
+ }
+
+ def getPythonCommand() : String = {
+ required(executeble) + required(python_script)
+ }
+}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Sha1sum.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Sha1sum.scala
index a3b546a5e..fb43a126a 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Sha1sum.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Sha1sum.scala
@@ -1,18 +1,17 @@
package nl.lumc.sasc.biopet.function
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class Sha1sum(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- this.analysisName = "sha1sum"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
+class Sha1sum(val globalConfig: Config) extends BiopetCommandLineFunction {
+ @Input(doc="Zipped file")
+ var input: File = _
- @Input(doc="Zipped file") var in: File = _
- @Output(doc="Unzipped file") var out: File = _
+ @Output(doc="Unzipped file")
+ var output: File = _
- def commandLine = "sha1sum %s > %s".format(in, out)
+ executeble = config.getAsString("exe","sha1sum")
+
+ def cmdLine = required(executeble) + required(input) + " > " + required(output)
}
\ No newline at end of file
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Zcat.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Zcat.scala
index 33b407671..95f3095d0 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Zcat.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/function/Zcat.scala
@@ -1,18 +1,18 @@
package nl.lumc.sasc.biopet.function
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
+//import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class Zcat(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- this.analysisName = "zcat"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
+class Zcat(val globalConfig: Config) extends BiopetCommandLineFunction {
+ @Input(doc="Zipped file")
+ var input: File = _
- @Input(doc="Zipped file") var in: File = _
- @Output(doc="Unzipped file") var out: File = _
+ @Output(doc="Unzipped file")
+ var output: File = _
- def commandLine = "zcat %s > %s".format(in, out)
+ executeble = config.getAsString("exe", "zcat")
+
+ def cmdLine = required(executeble) + required(input) + " > " + required(output)
}
\ No newline at end of file
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Cutadapt.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Cutadapt.scala
index ca436d089..50334d606 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Cutadapt.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Cutadapt.scala
@@ -1,23 +1,22 @@
package nl.lumc.sasc.biopet.function.fastq
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
import scala.io.Source._
import scala.sys.process._
-class Cutadapt(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- analysisName = "cutadapt"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
+class Cutadapt(val globalConfig: Config) extends BiopetCommandLineFunction {
+ @Input(doc="Input fastq file")
+ var fastq_input: File = _
- @Input(doc="Cutadapt exe", required=false)
- var cutadapt_exe: File = new File(config.getAsString("exe","/usr/local/bin/cutadapt"))
- @Input(doc="Input fastq file") var fastq_input: File = _
- @Input(doc="Fastq contams file", required=false) var contams_file: File = _
- @Output(doc="Output fastq file") var fastq_output: File = _
+ @Input(doc="Fastq contams file", required=false)
+ var contams_file: File = _
+
+ @Output(doc="Output fastq file")
+ var fastq_output: File = _
+
+ executeble = config.getAsString("exe","cutadapt")
var default_clip_mode = config.getAsString("default_clip_mode", "3")
var opt_adapter: Set[String] = config.getAsListOfStrings("adapter", Nil).to[Set]
@@ -28,15 +27,20 @@ class Cutadapt(val globalConfig: Config) extends CommandLineFunction {
var opt_minimum_length: String = config.getAsInt("minimum_length", 1).toString
var opt_maximum_length: String = config.getAsString("maximum_length", null)
- def init() {
- this.addJobReportBinding("version", getVersion)
+ override val versionRegex = """(.*)""".r
+
+ override def afterGraph() {
+ versionCommand = executeble + " --version"
+ }
+
+ override def beforeCmd() {
this.getContamsFromFile
}
- def commandLine = {
- init()
+ def cmdLine = {
if (!opt_adapter.isEmpty || !opt_anywhere.isEmpty || !opt_front.isEmpty) {
- required(cutadapt_exe) +
+ analysisName = getClass.getName
+ required(executeble) +
// options
repeat("-a", opt_adapter) +
repeat("-b", opt_anywhere) +
@@ -48,6 +52,7 @@ class Cutadapt(val globalConfig: Config) extends CommandLineFunction {
required(fastq_input) +
" > " + required(fastq_output)
} else {
+ analysisName = getClass.getName + "-ln"
"ln -sf " +
required(fastq_input) +
required(fastq_output)
@@ -71,24 +76,4 @@ class Cutadapt(val globalConfig: Config) extends CommandLineFunction {
} else logger.warn("File : " + contams_file + " does not exist")
}
}
-
- private var version: String = _
- var versionCommand = cutadapt_exe + " --version"
- var versionRegex = """(.*)"""
- def getVersion: String = getVersion(versionCommand, versionRegex)
- def getVersion(cmd:String, regex:String) : String = {
- val REG = regex.r
- if (cmd.! != 0) {
- logger.warn("Version command: '" + cmd + "' give a none-zero exit code, version not found")
- return "NA"
- }
- for (line <- cmd.!!.split("\n")) {
- line match {
- case REG(m) => return m
- case _ =>
- }
- }
- logger.warn("Version command: '" + cmd + "' give a exit code 0 but no version was found, executeble oke?")
- return "NA"
- }
}
\ No newline at end of file
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Fastqc.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Fastqc.scala
index 16c4b9d9e..6303ef3a6 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Fastqc.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Fastqc.scala
@@ -1,44 +1,39 @@
package nl.lumc.sasc.biopet.function.fastq
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
import scala.sys.process._
-class Fastqc(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- this.analysisName = "fastqc"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
-
- @Input(doc="fastqc executeble", shortName="Fastqc_Exe")
- var fastqc_exe: File = new File(config.getAsString("exe","/usr/local/FastQC/FastQC_v0.10.1/fastqc"))
- @Argument(doc="java vm executeble", shortName="Java_Exe", required=false)
- var java_exe: String = globalConfig.getAsConfig("java").getAsString("exe", "java")
- @Argument(doc="kmers", required=false) var kmers: Int = config.getAsInt("kmers", 5)
- @Argument(doc="threads", required=false) var threads: Int = config.getAsInt("threads", 4)
- @Argument(doc="quiet", required=false) var quiet: Boolean = config.getAsBoolean("quiet", false)
- @Argument(doc="noextract", required=false) var noextract: Boolean = config.getAsBoolean("noextract", false)
- @Argument(doc="nogroup", required=false) var nogroup: Boolean = config.getAsBoolean("nogroup", false)
+class Fastqc(val globalConfig: Config) extends BiopetCommandLineFunction {
@Input(doc="Contaminants", required=false)
- var contaminants: File = new File(config.getAsString("contaminants",fastqc_exe.getParent() + "/Contaminants/contaminant_list.txt"))
- @Input(doc="Fastq file", shortName="FQ") var fastqfile: File = _
- @Output(doc="Output", shortName="out") var output: File = _
+ var contaminants: File = _
+
+ @Input(doc="Fastq file", shortName="FQ")
+ var fastqfile: File = _
- if (config.contains("vmem")) jobResourceRequests :+= "h_vmem=" + config.getAsString("vmem")
+ @Output(doc="Output", shortName="out")
+ var output: File = _
+
+ executeble = config.getAsString("exe","fastqc")
+ var java_exe: String = config.getAsConfig("java").getAsString("exe", "java")
+ var kmers: Int = config.getAsInt("kmers", 5)
+ var quiet: Boolean = config.getAsBoolean("quiet", false)
+ var noextract: Boolean = config.getAsBoolean("noextract", false)
+ var nogroup: Boolean = config.getAsBoolean("nogroup", false)
- def init() {
- this.addJobReportBinding("version", getVersion)
- var maxThreads: Int = config.getAsInt("maxthreads", 24)
- if (threads > maxThreads) threads = maxThreads
- nCoresRequest = Option(threads)
- this.jobNativeArgs :+= "-l h_vmem="+config.getAsString("vmem", "4G")
- }
+ override val versionRegex = """FastQC (.*)""".r
+ override val defaultThreads = 4
- def commandLine = {
- init()
- required(fastqc_exe) +
+ override def afterGraph {
+ this.checkExecuteble
+ val fastqcDir = executeble.substring(0, executeble.lastIndexOf("/"))
+ if (contaminants == null) contaminants = new File(fastqcDir + "/Contaminants/contaminant_list.txt")
+ versionCommand = executeble + " --version"
+ }
+
+ def cmdLine = {
+ required(executeble) +
optional("--java", java_exe) +
optional("--threads",threads) +
optional("--contaminants",contaminants) +
@@ -50,24 +45,4 @@ class Fastqc(val globalConfig: Config) extends CommandLineFunction {
required(fastqfile) +
required(" > ", output, escape=false)
}
-
- private var version: String = _
- var versionCommand = fastqc_exe + " --version"
- var versionRegex = """FastQC (.*)"""
- def getVersion: String = getVersion(versionCommand, versionRegex)
- def getVersion(cmd:String, regex:String) : String = {
- val REG = regex.r
- if (cmd.! != 0) {
- logger.warn("Version command: '" + cmd + "' give a none-zero exit code, version not found")
- return "NA"
- }
- for (line <- cmd.!!.split("\n")) {
- line match {
- case REG(m) => return m
- case _ =>
- }
- }
- logger.warn("Version command: '" + cmd + "' give a exit code 0 but no version was found, executeble oke?")
- return "NA"
- }
}
\ No newline at end of file
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Sickle.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Sickle.scala
index 92a098a50..2cef9e3e2 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Sickle.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/function/fastq/Sickle.scala
@@ -1,40 +1,52 @@
package nl.lumc.sasc.biopet.function.fastq
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
import scala.io.Source._
import scala.sys.process._
-class Sickle(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- this.analysisName = "sickle"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
+class Sickle(val globalConfig: Config) extends BiopetCommandLineFunction {
+ @Input(doc="R1 input")
+ var input_R1: File = null
- @Input(doc="Sickle exe", required=false) var sickle_exe: File = new File(config.getAsString("exe", "/usr/local/bin/sickle"))
- @Input(doc="R1 input") var input_R1: File = null
- @Input(doc="R2 input", required=false) var input_R2: File = null
- @Output(doc="R1 output") var output_R1: File = null
- @Output(doc="R2 output", required=false) var output_R2: File = null
- @Output(doc="singles output", required=false) var output_singles: File = null
- @Output(doc="stats output") var output_stats: File = null
- @Input(doc="qualityType file", required=false) var qualityTypeFile: File = null
- @Argument(doc="Quality Type", required=false) var qualityType: String = config.getAsString("qualitytype", null)
- @Input(doc="deps", required=false) var deps: List[File] = Nil
+ @Input(doc="R2 input", required=false)
+ var input_R2: File = null
- var defaultQualityType: String = config.getAsString("defaultqualitytype", "sanger")
+ @Input(doc="qualityType file", required=false)
+ var qualityTypeFile: File = _
- def init() {
- this.addJobReportBinding("version", getVersion)
- this.getQualityTypeFromFile
+ @Output(doc="R1 output")
+ var output_R1: File = null
+
+ @Output(doc="R2 output", required=false)
+ var output_R2: File = null
+
+ @Output(doc="singles output", required=false)
+ var output_singles: File = null
+
+ @Output(doc="stats output")
+ var output_stats: File = null
+
+ executeble = config.getAsString("exe", "sickle")
+ var qualityType: String = config.getAsString("qualitytype", null)
+
+ var defaultQualityType: String = _
+ override val versionRegex = """sickle version (.*)""".r
+
+ override def afterGraph {
+ if (defaultQualityType == null) defaultQualityType = config.getAsString("defaultqualitytype", "sanger")
if (qualityType == null && defaultQualityType != null) qualityType = defaultQualityType
+
+ versionCommand = executeble + " --version"
}
- def commandLine = {
- init()
- var cmd: String = required(sickle_exe)
+ override def beforeCmd {
+ qualityType = getQualityTypeFromFile
+ }
+
+ def cmdLine = {
+ var cmd: String = required(executeble)
if (input_R2 != null) {
cmd += required("pe") +
required("-r", input_R2) +
@@ -49,34 +61,15 @@ class Sickle(val globalConfig: Config) extends CommandLineFunction {
" > " + required(output_stats)
}
- def getQualityTypeFromFile {
+ def getQualityTypeFromFile: String = {
if (qualityType == null && qualityTypeFile != null) {
if (qualityTypeFile.exists()) {
for (line <- fromFile(qualityTypeFile).getLines) {
var s: String = line.substring(0,line.lastIndexOf("\t"))
- qualityType = s
+ return s
}
} else logger.warn("File : " + qualityTypeFile + " does not exist")
}
- }
-
- private var version: String = _
- var versionCommand = sickle_exe + " --version"
- var versionRegex = """sickle version (.*)"""
- def getVersion: String = getVersion(versionCommand, versionRegex)
- def getVersion(cmd:String, regex:String) : String = {
- val REG = regex.r
- if (cmd.! != 0) {
- logger.warn("Version command: '" + cmd + "' give a none-zero exit code, version not found")
- return "NA"
- }
- for (line <- cmd.!!.split("\n")) {
- line match {
- case REG(m) => return m
- case _ =>
- }
- }
- logger.warn("Version command: '" + cmd + "' give a exit code 0 but no version was found, executeble oke?")
- return "NA"
+ return null
}
}
\ No newline at end of file
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqSync.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqSync.scala
index 3180785a3..5f7803b3f 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqSync.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqSync.scala
@@ -2,19 +2,13 @@ package nl.lumc.sasc.biopet.pipelines.flexiprep.scripts
//import java.io.FileOutputStream
import nl.lumc.sasc.biopet.core._
-import nl.lumc.sasc.biopet.function._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
+import nl.lumc.sasc.biopet.function.PythonCommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class FastqSync(val globalConfig: Config) extends Python {
- def this() = this(new Config(Map()))
- analysisName = "fastqsync"
- val config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName.toLowerCase), globalConfig)
- logger.debug("Config for " + analysisName + ": " + config)
-
- setPythonScript("__init__.py", "scripts/pyfastqc/")
- setPythonScript("sync_paired_end_reads.py", "scripts/")
+class FastqSync(val globalConfig: Config) extends PythonCommandLineFunction {
+ setPythonScript("__init__.py", "pyfastqc/")
+ setPythonScript("sync_paired_end_reads.py")
@Input(doc="Start fastq") var input_start_fastq: File = _
@Input(doc="R1 input") var input_R1: File = _
@@ -23,7 +17,7 @@ class FastqSync(val globalConfig: Config) extends Python {
@Output(doc="R2 output") var output_R2: File = _
var output_stats: File = _
- def commandLine = {
+ def cmdLine = {
getPythonCommand +
required(input_start_fastq) +
required(input_R1) +
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToContams.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToContams.scala
index 1ab9b00b5..45515458e 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToContams.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToContams.scala
@@ -1,25 +1,19 @@
package nl.lumc.sasc.biopet.pipelines.flexiprep.scripts
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
-import nl.lumc.sasc.biopet.function.Python
+import nl.lumc.sasc.biopet.function.PythonCommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class FastqcToContams(val globalConfig: Config) extends CommandLineFunction with Python {
- def this() = this(new Config(Map()))
- analysisName = "getcontams"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + analysisName + ": " + config)
-
- setPythonScript("__init__.py", "scripts/pyfastqc/")
- setPythonScript("fastqc_contam.py", "scripts/")
+class FastqcToContams(val globalConfig: Config) extends PythonCommandLineFunction {
+ setPythonScript("__init__.py", "pyfastqc/")
+ setPythonScript("fastqc_contam.py")
@Input(doc="Fastqc output", shortName="fastqc", required=true) var fastqc_output: File = _
- @Input(doc="Contams input", shortName="fastqc", required=true) var contams_file: File = _
+ @Input(doc="Contams input", shortName="fastqc", required=false) var contams_file: File = _
@Output(doc="Output file", shortName="out", required=true) var out: File = _
- def commandLine = {
+ def cmdLine = {
getPythonCommand +
required(fastqc_output.getParent()) +
required("-c",contams_file) +
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToQualtype.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToQualtype.scala
index da7594b5c..e3a7cf7b2 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToQualtype.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/FastqcToQualtype.scala
@@ -1,24 +1,18 @@
package nl.lumc.sasc.biopet.pipelines.flexiprep.scripts
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
-import nl.lumc.sasc.biopet.function.Python
+import nl.lumc.sasc.biopet.function.PythonCommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class FastqcToQualtype(val globalConfig: Config) extends CommandLineFunction with Python {
- def this() = this(new Config(Map()))
- analysisName = "getqualtype"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + analysisName + ": " + config)
-
- setPythonScript("__init__.py", "scripts/pyfastqc/")
- setPythonScript("qual_type_sickle.py", "scripts/")
+class FastqcToQualtype(val globalConfig: Config) extends PythonCommandLineFunction {
+ setPythonScript("__init__.py", "pyfastqc/")
+ setPythonScript("qual_type_sickle.py")
@Input(doc="Fastqc output", shortName="fastqc", required=true) var fastqc_output: File = _
@Output(doc="Output file", shortName="out", required=true) var out: File = _
- def commandLine = {
+ def cmdLine = {
getPythonCommand +
required(fastqc_output.getParent()) +
" > " +
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Seqstat.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Seqstat.scala
index 7e6a4c094..3ed1a7bec 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Seqstat.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Seqstat.scala
@@ -1,27 +1,20 @@
package nl.lumc.sasc.biopet.pipelines.flexiprep.scripts
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
-import nl.lumc.sasc.biopet.function.Python
+import nl.lumc.sasc.biopet.function.PythonCommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class Seqstat(val globalConfig: Config) extends CommandLineFunction with Python {
- def this() = this(new Config(Map()))
- analysisName = "seqstat"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + analysisName + ": " + config)
-
- setPythonScript("__init__.py", "scripts/pyfastqc/")
- setPythonScript("seq_stat.py", "scripts/")
+class Seqstat(val globalConfig: Config) extends PythonCommandLineFunction {
+ setPythonScript("__init__.py", "pyfastqc/")
+ setPythonScript("seq_stat.py")
@Input(doc="Fastq input", shortName="fastqc", required=true) var input_fastq: File = _
- @Input(doc="Dep", shortName="dep", required=false) var deps: List[File] = Nil
@Output(doc="Output file", shortName="out", required=true) var out: File = _
var fmt: String = _
- def commandLine = {
+ def cmdLine = {
getPythonCommand +
optional("--fmt", fmt) +
required("-o", out) +
diff --git a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Summarize.scala b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Summarize.scala
index a25832abe..afbb9f53b 100644
--- a/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Summarize.scala
+++ b/flexiprep/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/scripts/Summarize.scala
@@ -1,21 +1,14 @@
package nl.lumc.sasc.biopet.pipelines.flexiprep.scripts
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
-import nl.lumc.sasc.biopet.function.Python
+import nl.lumc.sasc.biopet.function.PythonCommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
-class Summarize(val globalConfig: Config) extends CommandLineFunction with Python {
- def this() = this(new Config(Map()))
- analysisName = "flexiprep_sumarize"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + analysisName + ": " + config)
+class Summarize(val globalConfig: Config) extends PythonCommandLineFunction {
+ setPythonScript("__init__.py", "pyfastqc/")
+ setPythonScript("summarize_flexiprep.py")
- setPythonScript("__init__.py", "scripts/pyfastqc/")
- setPythonScript("summarize_flexiprep.py", "scripts/")
-
- @Input(doc="Dep", shortName="dep", required=false) var deps: List[File] = Nil
@Output(doc="Output file", shortName="out", required=true) var out: File = _
var samplea: String = _
@@ -25,7 +18,7 @@ class Summarize(val globalConfig: Config) extends CommandLineFunction with Pytho
var trim: Boolean = true
var clip: Boolean = true
- def commandLine = {
+ def cmdLine = {
var mode: String = ""
if (clip) mode += "clip"
if (trim) mode += "trim"
diff --git a/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Bwa.scala b/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Bwa.scala
index d1dae66e3..699e082c9 100644
--- a/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Bwa.scala
+++ b/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Bwa.scala
@@ -1,40 +1,38 @@
package nl.lumc.sasc.biopet.function.aligners
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
import scala.sys.process._
-class Bwa(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- this.analysisName = "bwa"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
-
- @Argument(doc="Bwa executeble", shortName="bwa_exe", required=false) var bwa_exe: String = config.getAsString("exe", "/usr/local/bin/bwa")
- @Input(doc="The reference file for the bam files.", shortName="R") var referenceFile: File = new File(config.getAsString("referenceFile"))
- @Input(doc="Fastq file R1", shortName="R1") var R1: File = _
- @Input(doc="Fastq file R2", shortName="R2", required=false) var R2: File = _
- @Output(doc="Output file SAM", shortName="output") var output: File = _
+class Bwa(val globalConfig: Config) extends BiopetCommandLineFunction {
+ @Input(doc="Fastq file R1", shortName="R1")
+ var R1: File = _
+
+ @Input(doc="Fastq file R2", shortName="R2", required=false)
+ var R2: File = _
+
+ @Input(doc="The reference file for the bam files.", shortName="R")
+ var referenceFile: File = new File(config.getAsString("referenceFile"))
- @Argument(doc="Readgroup header", shortName="RG", required=false) var RG: String = _
- @Argument(doc="M", shortName="M", required=false) var M: Boolean = config.getAsBoolean("M", true)
+ @Output(doc="Output file SAM", shortName="output")
+ var output: File = _
- jobResourceRequests :+= "h_vmem=" + config.getAsString("vmem", "6G")
+ executeble = config.getAsString("exe", "bwa")
- var threads: Int = config.getAsInt("threads", 8)
- var maxThreads: Int = config.getAsInt("maxthreads", 24)
- if (threads > maxThreads) threads = maxThreads
- nCoresRequest = Option(threads)
+ var RG: String = _
+ var M = config.getAsBoolean("M", true)
- def init() {
- this.addJobReportBinding("version", getVersion)
+ override val defaultVmem = "6G"
+ override val defaultThreads = 8
+ override val versionRegex = """Version: (.*)""".r
+
+ override def beforeCmd() {
+ versionCommand = executeble
}
- def commandLine = {
- init()
- required(bwa_exe) +
+ def cmdLine = {
+ required(executeble) +
required("mem") +
optional("-t", nCoresRequest) +
optional("-R", RG) +
@@ -44,19 +42,4 @@ class Bwa(val globalConfig: Config) extends CommandLineFunction {
optional(R2) +
" > " + required(output)
}
-
- private var version: String = ""
- def getVersion : String = {
- val REG = """Version: (.*)""".r
- if (version == null) for (line <- bwa_exe.!!.split("\n")) {
- line match {
- case REG(m) => {
- version = m
- return version
- }
- case _ =>
- }
- }
- return version
- }
}
diff --git a/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Star.scala b/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Star.scala
index 492c0413b..8df9e20b4 100644
--- a/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Star.scala
+++ b/mapping/src/main/scala/nl/lumc/sasc/biopet/function/aligners/Star.scala
@@ -1,40 +1,52 @@
package nl.lumc.sasc.biopet.function.aligners
import nl.lumc.sasc.biopet.core._
-import org.broadinstitute.sting.queue.function.CommandLineFunction
import org.broadinstitute.sting.commandline._
import java.io.File
import scala.sys.process._
-class Star(val globalConfig: Config) extends CommandLineFunction {
- def this() = this(new Config(Map()))
- this.analysisName = "star"
- val config: Config = Config.mergeConfigs(globalConfig.getAsConfig(analysisName), globalConfig)
- logger.debug("Config for " + this.analysisName + ": " + config)
+class Star(val globalConfig: Config) extends BiopetCommandLineFunction {
+ @Input(doc="The reference file for the bam files.", required=false)
+ var referenceFile: File = new File(config.getAsString("referenceFile"))
- @Argument(doc="STAR executeble", required=false) var star_exe: String = config.getAsString("exe", "/usr/local/bin/STAR")
- @Input(doc="The reference file for the bam files.", required=false) var referenceFile: File = new File(config.getAsString("referenceFile"))
- @Input(doc="Fastq file R1", required=false) var R1: File = _
- @Input(doc="Fastq file R2", required=false) var R2: File = _
- @Argument(doc="Output Directory") var outputDir: String = _
- @Argument(doc="GenomeDir", required=false) var genomeDir: String = config.getAsString("genomeDir", referenceFile.getParent + "/star/")
- @Argument(doc="STAR runmode", shortName="runmode", required=false) var runmode: String = _
- @Output(doc="Output SAM file", required=false) var outputSam: File = _
- @Output(doc="Output tab file", required=false) var outputTab: File = _
- @Input(doc="sjdbFileChrStartEnd file", required=false) var sjdbFileChrStartEnd: File = _
- @Argument(doc="sjdbOverhang", required=false) var sjdbOverhang: Int = _
- @Argument(doc="outFileNamePrefix", required=false) var outFileNamePrefix: String = _
- @Input(doc="deps", required=false) var deps: List[File] = Nil
+ @Input(doc="Fastq file R1", required=false)
+ var R1: File = _
- @Output(doc="Output genome file", required=false) var outputGenome: File = _
- @Output(doc="Output SA file", required=false) var outputSA: File = _
- @Output(doc="Output SAindex file", required=false) var outputSAindex: File = _
+ @Input(doc="Fastq file R2", required=false)
+ var R2: File = _
- jobResourceRequests :+= "h_vmem=" + config.getAsString("vmem", "6G")
- nCoresRequest = Option(config.getThreads(8))
- addJobReportBinding("version", "NA")
+ @Output(doc="Output SAM file", required=false)
+ var outputSam: File = _
- def init() {
+ @Output(doc="Output tab file", required=false)
+ var outputTab: File = _
+
+ @Input(doc="sjdbFileChrStartEnd file", required=false)
+ var sjdbFileChrStartEnd: File = _
+
+ @Output(doc="Output genome file", required=false)
+ var outputGenome: File = _
+
+ @Output(doc="Output SA file", required=false)
+ var outputSA: File = _
+
+ @Output(doc="Output SAindex file", required=false)
+ var outputSAindex: File = _
+
+ executeble = config.getAsString("exe", "STAR")
+
+ @Argument(doc="Output Directory")
+ var outputDir: String = _
+
+ var genomeDir: String = config.getAsString("genomeDir", referenceFile.getParent + "/star/")
+ var runmode: String = _
+ var sjdbOverhang: Int = _
+ var outFileNamePrefix: String = _
+
+ override val defaultVmem = "6G"
+ override val defaultThreads = 8
+
+ override def afterGraph() {
if (outFileNamePrefix != null && !outFileNamePrefix.endsWith(".")) outFileNamePrefix +="."
if (!outputDir.endsWith("/")) outputDir += "/"
val prefix = if (outFileNamePrefix != null) outputDir+outFileNamePrefix else outputDir
@@ -49,9 +61,8 @@ class Star(val globalConfig: Config) extends CommandLineFunction {
}
}
- def commandLine : String= {
- init()
- var cmd: String = required("cd",outputDir) + "&&" + required(star_exe)
+ def cmdLine : String = {
+ var cmd: String = required("cd",outputDir) + "&&" + required(executeble)
if (runmode != null && runmode == "genomeGenerate") { // Create index
cmd += required("--runMode", runmode) +
required("--genomeFastaFiles", referenceFile)
@@ -66,4 +77,14 @@ class Star(val globalConfig: Config) extends CommandLineFunction {
return cmd
}
+}
+
+object Star {
+ def apply(config:Config, R1:File, R2:File, outputDir:String): Star = {
+ val star = new Star(config)
+ star.R1 = R1
+ if (R2 != null) star.R2 = R2
+ star.outputDir = outputDir
+ return star
+ }
}
\ No newline at end of file
--
GitLab