Skip to content

GitLab

Commit bbe3ee3d authored by wyleung's avatar wyleung
Browse files

Splitout the sv caller classes over its over file

parent 961470fd
Hide whitespace changes
Inline Side-by-side
Showing with 284 additions and 259 deletions
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Breakdancer.scala
View file @ bbe3ee3d
package nl.lumc.sasc.biopet.extensions.svcallers
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import org.broadinstitute.gatk.queue.QScript
import nl.lumc.sasc.biopet.core.BiopetQScript
import nl.lumc.sasc.biopet.core.PipelineCommand
import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
import java.io.File
class BreakdancerConfig(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "bam2cfg.pl", freeVar = false)
@Input(doc = "Bam File")
var input: File = _
@Output(doc = "Output File")
var output: File = _
var min_mq: Option[Int] = config("min_mq", default = 20) // minimum of MQ to consider for taking read into histogram
var use_mq: Boolean = config("use_mq", default = false)
var min_insertsize: Option[Int] = config("min_insertsize", default = 450)
var solid_data: Boolean = config("solid", default = false)
var sd_cutoff: Option[Int] = config("sd_cutoff", default = 4) // Cutoff in unit of standard deviation [4]
// we set this to a higher number to avoid biases in small numbers in sorted bams
var min_observations: Option[Int] = config("min_observations", default = 10000) // Number of observation required to estimate mean and s.d. insert size [10_000]
var coefvar_cutoff: Option[Int] = config("coef_cutoff", default = 1) // Cutoff on coefficients of variation [1]
var histogram_bins: Option[Int] = config("histogram_bins", default = 50) // Number of bins in the histogram [50]
def cmdLine = required(executable) +
optional("-q", min_mq) +
conditional(use_mq, "-m") +
optional("-s", min_insertsize) +
conditional(solid_data, "-s") +
optional("-c", sd_cutoff) +
optional("-n", min_observations) +
optional("-v", coefvar_cutoff) +
optional("-b", histogram_bins) +
required(input) + " 1> " + required(output)
}
object BreakdancerConfig {
def apply(root: Configurable, input: File, output: File): BreakdancerConfig = {
val bdconf = new BreakdancerConfig(root)
bdconf.input = input
bdconf.output = output
return bdconf
}
def apply(root: Configurable, input: File, outputDir: String): BreakdancerConfig = {
val dir = if (outputDir.endsWith("/")) outputDir else outputDir + "/"
val outputFile = new File(dir + swapExtension(input.getName))
return apply(root, input, outputFile)
}
def apply(root: Configurable, input: File): BreakdancerConfig = {
return apply(root, input, new File(swapExtension(input.getAbsolutePath)))
}
private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".breakdancer.cfg"
}
/*
* The caller
*
**/
class BreakdancerCaller(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "breakdancer-max", freeVar = false)
override val defaultVmem = "6G"
override val defaultThreads = 1 // breakdancer can only work on 1 single thread
override val versionRegex = """.*[Vv]ersion:? (.*)""".r
override val versionExitcode = List(1)
override def versionCommand = executable
@Input(doc = "The breakdancer configuration file")
var input: File = _
// @Argument(doc = "Work directory")
// var workdir: String = _
@Output(doc = "Breakdancer TSV output")
var output: File = _
/*
Options:
-o STRING operate on a single chromosome [all chromosome]
-s INT minimum length of a region [7]
-c INT cutoff in unit of standard deviation [3]
-m INT maximum SV size [1000000000]
-q INT minimum alternative mapping quality [35]
-r INT minimum number of read pairs required to establish a connection [2]
-x INT maximum threshold of haploid sequence coverage for regions to be ignored [1000]
-b INT buffer size for building connection [100]
-t only detect transchromosomal rearrangement, by default off
-d STRING prefix of fastq files that SV supporting reads will be saved by library
-g STRING dump SVs and supporting reads in BED format for GBrowse
-l analyze Illumina long insert (mate-pair) library
-a print out copy number and support reads per library rather than per bam, by default off
-h print out Allele Frequency column, by default off
-y INT output score filter [30]
*/
var s: Option[Int] = config("s", default = 7)
var c: Option[Int] = config("c", default = 3)
var m: Option[Int] = config("m", default = 1000000000)
var q: Option[Int] = config("qs", default = 35)
var r: Option[Int] = config("r", default = 2)
var x: Option[Int] = config("x", default = 1000)
var b: Option[Int] = config("b", default = 100)
var t: Boolean = config("t", default = false)
var d: String = config("d")
var g: String = config("g")
var l: Boolean = config("l", default = false)
var a: Boolean = config("a", default = false)
var h: Boolean = config("h", default = false)
var y: Option[Int] = config("y", default = 30)
override def beforeCmd {
}
def cmdLine = required(executable) +
optional("-s", s) +
optional("-c", c) +
optional("-m", m) +
optional("-q", q) +
optional("-r", r) +
optional("-x", x) +
optional("-b", b) +
conditional(t, "-t") +
optional("-d", d) +
optional("-g", g) +
conditional(l, "-l") +
conditional(a, "-a") +
conditional(h, "-h") +
optional("-y", y) +
required(input) +
">" +
required(output)
}
import org.broadinstitute.gatk.queue.QScript
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
object BreakdancerCaller {
def apply(root: Configurable, input: File, output: File): BreakdancerCaller = {
val bdcaller = new BreakdancerCaller(root)
bdcaller.input = input
bdcaller.output = output
return bdcaller
}
}
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.core.BiopetQScript
import nl.lumc.sasc.biopet.core.PipelineCommand
/// Breakdancer is actually a mini pipeline executing binaries from the breakdancer package
class Breakdancer(val root: Configurable) extends QScript with BiopetQScript {
......
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/BreakdancerCaller.scala 0 → 100644
View file @ bbe3ee3d
package nl.lumc.sasc.biopet.extensions.svcallers
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.config.Configurable
class BreakdancerCaller(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "breakdancer-max", freeVar = false)
override val defaultVmem = "6G"
override val defaultThreads = 1 // breakdancer can only work on 1 single thread
override val versionRegex = """.*[Vv]ersion:? (.*)""".r
override val versionExitcode = List(1)
override def versionCommand = executable
@Input(doc = "The breakdancer configuration file")
var input: File = _
// @Argument(doc = "Work directory")
// var workdir: String = _
@Output(doc = "Breakdancer TSV output")
var output: File = _
/*
Options:
-o STRING operate on a single chromosome [all chromosome]
-s INT minimum length of a region [7]
-c INT cutoff in unit of standard deviation [3]
-m INT maximum SV size [1000000000]
-q INT minimum alternative mapping quality [35]
-r INT minimum number of read pairs required to establish a connection [2]
-x INT maximum threshold of haploid sequence coverage for regions to be ignored [1000]
-b INT buffer size for building connection [100]
-t only detect transchromosomal rearrangement, by default off
-d STRING prefix of fastq files that SV supporting reads will be saved by library
-g STRING dump SVs and supporting reads in BED format for GBrowse
-l analyze Illumina long insert (mate-pair) library
-a print out copy number and support reads per library rather than per bam, by default off
-h print out Allele Frequency column, by default off
-y INT output score filter [30]
*/
var s: Option[Int] = config("s", default = 7)
var c: Option[Int] = config("c", default = 3)
var m: Option[Int] = config("m", default = 1000000000)
var q: Option[Int] = config("qs", default = 35)
var r: Option[Int] = config("r", default = 2)
var x: Option[Int] = config("x", default = 1000)
var b: Option[Int] = config("b", default = 100)
var t: Boolean = config("t", default = false)
var d: String = config("d")
var g: String = config("g")
var l: Boolean = config("l", default = false)
var a: Boolean = config("a", default = false)
var h: Boolean = config("h", default = false)
var y: Option[Int] = config("y", default = 30)
override def beforeCmd {
}
def cmdLine = required(executable) +
optional("-s", s) +
optional("-c", c) +
optional("-m", m) +
optional("-q", q) +
optional("-r", r) +
optional("-x", x) +
optional("-b", b) +
conditional(t, "-t") +
optional("-d", d) +
optional("-g", g) +
conditional(l, "-l") +
conditional(a, "-a") +
conditional(h, "-h") +
optional("-y", y) +
required(input) +
">" +
required(output)
}
object BreakdancerCaller {
def apply(root: Configurable, input: File, output: File): BreakdancerCaller = {
val bdcaller = new BreakdancerCaller(root)
bdcaller.input = input
bdcaller.output = output
return bdcaller
}
}
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/BreakdancerConfig.scala 0 → 100644
View file @ bbe3ee3d
package nl.lumc.sasc.biopet.extensions.svcallers
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.config.Configurable
class BreakdancerConfig(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "bam2cfg.pl", freeVar = false)
@Input(doc = "Bam File")
var input: File = _
@Output(doc = "Output File")
var output: File = _
var min_mq: Option[Int] = config("min_mq", default = 20) // minimum of MQ to consider for taking read into histogram
var use_mq: Boolean = config("use_mq", default = false)
var min_insertsize: Option[Int] = config("min_insertsize", default = 450)
var solid_data: Boolean = config("solid", default = false)
var sd_cutoff: Option[Int] = config("sd_cutoff", default = 4) // Cutoff in unit of standard deviation [4]
// we set this to a higher number to avoid biases in small numbers in sorted bams
var min_observations: Option[Int] = config("min_observations", default = 10000) // Number of observation required to estimate mean and s.d. insert size [10_000]
var coefvar_cutoff: Option[Int] = config("coef_cutoff", default = 1) // Cutoff on coefficients of variation [1]
var histogram_bins: Option[Int] = config("histogram_bins", default = 50) // Number of bins in the histogram [50]
def cmdLine = required(executable) +
optional("-q", min_mq) +
conditional(use_mq, "-m") +
optional("-s", min_insertsize) +
conditional(solid_data, "-s") +
optional("-c", sd_cutoff) +
optional("-n", min_observations) +
optional("-v", coefvar_cutoff) +
optional("-b", histogram_bins) +
required(input) + " 1> " + required(output)
}
object BreakdancerConfig {
def apply(root: Configurable, input: File, output: File): BreakdancerConfig = {
val bdconf = new BreakdancerConfig(root)
bdconf.input = input
bdconf.output = output
return bdconf
}
def apply(root: Configurable, input: File, outputDir: String): BreakdancerConfig = {
val dir = if (outputDir.endsWith("/")) outputDir else outputDir + "/"
val outputFile = new File(dir + swapExtension(input.getName))
return apply(root, input, outputFile)
}
def apply(root: Configurable, input: File): BreakdancerConfig = {
return apply(root, input, new File(swapExtension(input.getAbsolutePath)))
}
private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".breakdancer.cfg"
}
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/BreakdancerVCF.scala
View file @ bbe3ee3d
......@@ -4,9 +4,6 @@ import java.io.File
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import argonaut._, Argonaut._
import scalaz._, Scalaz._
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.extensions.PythonCommandLineFunction
......
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Clever.scala
View file @ bbe3ee3d
package nl.lumc.sasc.biopet.extensions.svcallers
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import org.broadinstitute.gatk.queue.QScript
import nl.lumc.sasc.biopet.core.BiopetQScript
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.core.PipelineCommand
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
import java.io.File
class Clever(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "clever")
private lazy val versionexecutable: File = config("version_exe", default = (new File(executable).getParent + "/ctk-version"))
override val defaultVmem = "4G"
override val defaultThreads = 8
override def versionCommand = versionexecutable.getAbsolutePath
override val versionRegex = """(.*)""".r
override val versionExitcode = List(0, 1)
@Input(doc = "Input file (bam)")
var input: File = _
@Input(doc = "Reference")
var reference: File = _
@Argument(doc = "Work directory")
var workdir: String = _
var cwd: String = _
@Output(doc = "Clever VCF output")
lazy val outputvcf: File = {
new File(cwd + "predictions.vcf")
}
@Output(doc = "Clever raw output")
lazy val outputraw: File = {
new File(workdir + "predictions.raw.txt")
}
// var T: Option[Int] = config("T", default = defaultThreads)
var f: Boolean = config("f", default = true) // delete work directory before running
// var w: String = config("w", default = workdir + "/work")
var a: Boolean = config("a", default = false) // don't recompute AS tags
var k: Boolean = config("k", default = false) // keep working directory
var r: Boolean = config("r", default = false) // take read groups into account
override def beforeCmd {
if (workdir == null) throw new Exception("Clever :: Workdirectory is not defined")
// if (input.getName.endsWith(".sort.bam")) sorted = true
}
def cmdLine = required(executable) +
" --sorted " +
" --use_xa " +
optional("-T", nCoresRequest) +
conditional(f, "-f") +
conditional(a, "-a") +
conditional(k, "-k") +
conditional(r, "-r") +
required(this.input) +
required(this.reference) +
required(this.workdir)
}
import org.broadinstitute.gatk.queue.QScript
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
object Clever {
def apply(root: Configurable, input: File, reference: File, svDir: String, runDir: String): Clever = {
val clever = new Clever(root)
clever.input = input
clever.reference = reference
clever.cwd = svDir
clever.workdir = runDir
return clever
}
}
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.core.BiopetQScript
import nl.lumc.sasc.biopet.core.PipelineCommand
class CleverPipeline(val root: Configurable) extends QScript with BiopetQScript {
class Clever(val root: Configurable) extends QScript with BiopetQScript {
def this() = this(null)
@Input(doc = "Input file (bam)")
......@@ -100,17 +32,17 @@ class CleverPipeline(val root: Configurable) extends QScript with BiopetQScript
logger.info("Starting Clever Pipeline")
/// start clever and then copy the vcf into the root directory "<sample>.clever/"
val clever = Clever(this, input, reference, cwd, workdir)
val clever = CleverCaller(this, input, reference, cwd, workdir)
outputFiles += ("clever_vcf" -> clever.outputvcf)
add(clever)
}
}
object CleverPipeline extends PipelineCommand {
object Clever extends PipelineCommand {
override val pipeline = "/nl/lumc/sasc/biopet/extensions/svcallers/Clever/Clever.class"
def apply(root: Configurable, input: File, runDir: String): CleverPipeline = {
val cleverpipeline = new CleverPipeline(root)
def apply(root: Configurable, input: File, runDir: String): Clever = {
val cleverpipeline = new Clever(root)
cleverpipeline.input = input
cleverpipeline.workdir = runDir
cleverpipeline.init
......
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/CleverCaller.scala 0 → 100644
View file @ bbe3ee3d
package nl.lumc.sasc.biopet.extensions.svcallers
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.config.Configurable
class CleverCaller(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "clever")
private lazy val versionexecutable: File = config("version_exe", default = (new File(executable).getParent + "/ctk-version"))
override val defaultVmem = "4G"
override val defaultThreads = 8
override def versionCommand = versionexecutable.getAbsolutePath
override val versionRegex = """(.*)""".r
override val versionExitcode = List(0, 1)
@Input(doc = "Input file (bam)")
var input: File = _
@Input(doc = "Reference")
var reference: File = _
@Argument(doc = "Work directory")
var workdir: String = _
var cwd: String = _
@Output(doc = "Clever VCF output")
lazy val outputvcf: File = {
new File(cwd + "predictions.vcf")
}
@Output(doc = "Clever raw output")
lazy val outputraw: File = {
new File(workdir + "predictions.raw.txt")
}
// var T: Option[Int] = config("T", default = defaultThreads)
var f: Boolean = config("f", default = true) // delete work directory before running
// var w: String = config("w", default = workdir + "/work")
var a: Boolean = config("a", default = false) // don't recompute AS tags
var k: Boolean = config("k", default = false) // keep working directory
var r: Boolean = config("r", default = false) // take read groups into account
override def beforeCmd {
if (workdir == null) throw new Exception("Clever :: Workdirectory is not defined")
// if (input.getName.endsWith(".sort.bam")) sorted = true
}
def cmdLine = required(executable) +
" --sorted " +
" --use_xa " +
optional("-T", nCoresRequest) +
conditional(f, "-f") +
conditional(a, "-a") +
conditional(k, "-k") +
conditional(r, "-r") +
required(this.input) +
required(this.reference) +
required(this.workdir)
}
object CleverCaller {
def apply(root: Configurable, input: File, reference: File, svDir: String, runDir: String): CleverCaller = {
val clever = new CleverCaller(root)
clever.input = input
clever.reference = reference
clever.cwd = svDir
clever.workdir = runDir
return clever
}
}
\ No newline at end of file
biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Delly.scala
View file @ bbe3ee3d
......@@ -6,40 +6,11 @@ import org.broadinstitute.gatk.queue.QScript
import org.broadinstitute.gatk.queue.extensions.gatk.CatVariants
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import nl.lumc.sasc.biopet.core.BiopetQScript
import nl.lumc.sasc.biopet.core.PipelineCommand
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.extensions.Ln
class DellyCaller(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "delly")
private lazy val versionexecutable: File = new File(executable)
override val defaultVmem = "8G"
override val defaultThreads = 1
override def versionCommand = versionexecutable.getAbsolutePath
override val versionRegex = """DELLY \(Version: (.*)\)""".r
override val versionExitcode = List(0, 1)
@Input(doc = "Input file (bam)")
var input: File = _
@Output(doc = "Delly VCF output")
var outputvcf: File = _
@Argument(doc = "What kind of analysis to run: DEL,DUP,INV,TRA")
var analysistype: String = _
def cmdLine = required(executable) +
"-t" + required(analysistype) +
"-o" + required(outputvcf) +
required(input)
}