diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunctionTrait.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunctionTrait.scala index 928f14329ef0747da3f1d7652c35beb560d9751d..e04af3d5b469330e9f0b72f0f265dd0d50004086 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunctionTrait.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunctionTrait.scala @@ -54,29 +54,43 @@ trait BiopetCommandLineFunctionTrait extends CommandLineFunction with Configurab } protected def checkExecutable { - try if (executable != null) { - val buffer = new StringBuffer() - val cmd = Seq("which", executable) - val process = Process(cmd).run(ProcessLogger(buffer.append(_))) - if (process.exitValue == 0) { - executable = buffer.toString - val file = new File(executable) - executable = file.getCanonicalPath - } else { - logger.error("executable: '" + executable + "' not found, please check config") - throw new QException("executable: '" + executable + "' not found, please check config") + if (!BiopetCommandLineFunctionTrait.executableMd5Cache.contains(executable)) { + try if (executable != null) { + if (!BiopetCommandLineFunctionTrait.executableCache.contains(executable)) { + val oldExecutable = executable + val buffer = new StringBuffer() + val cmd = Seq("which", executable) + val process = Process(cmd).run(ProcessLogger(buffer.append(_))) + if (process.exitValue == 0) { + executable = buffer.toString + val file = new File(executable) + executable = file.getCanonicalPath + } else { + logger.error("executable: '" + executable + "' not found, please check config") + throw new QException("executable: '" + executable + "' not found, please check config") + } + BiopetCommandLineFunctionTrait.executableCache += oldExecutable -> executable + BiopetCommandLineFunctionTrait.executableCache += executable -> executable + } else { + executable = BiopetCommandLineFunctionTrait.executableCache(executable) + } + + if (!BiopetCommandLineFunctionTrait.executableMd5Cache.contains(executable)) { + val is = new FileInputStream(executable) + val cnt = is.available + val bytes = Array.ofDim[Byte](cnt) + is.read(bytes) + is.close() + val temp = MessageDigest.getInstance("MD5").digest(bytes).map("%02X".format(_)).mkString.toLowerCase + BiopetCommandLineFunctionTrait.executableMd5Cache += executable -> temp + } + + addJobReportBinding("md5sum_exe", BiopetCommandLineFunctionTrait.executableMd5Cache(executable)) + } catch { + case ioe: java.io.IOException => logger.warn("Could not use 'which', check on executable skipped: " + ioe) } - - val is = new FileInputStream(executable) - val cnt = is.available - val bytes = Array.ofDim[Byte](cnt) - is.read(bytes) - is.close() - val md5: String = MessageDigest.getInstance("MD5").digest(bytes).map("%02X".format(_)).mkString.toLowerCase - - addJobReportBinding("md5sum_exe", md5) - } catch { - case ioe: java.io.IOException => logger.warn("Could not use 'which', check on executable skipped: " + ioe) + } else { + addJobReportBinding("md5sum_exe", BiopetCommandLineFunctionTrait.executableMd5Cache(executable)) } } @@ -138,4 +152,6 @@ trait BiopetCommandLineFunctionTrait extends CommandLineFunction with Configurab object BiopetCommandLineFunctionTrait { import scala.collection.mutable.Map private val versionCache: Map[String, String] = Map() + private val executableMd5Cache: Map[String, String] = Map() + private val executableCache: Map[String, String] = Map() } \ No newline at end of file diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetExecutable.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetExecutable.scala index 0acc5f348c65a878926d64e3482008ff037505f8..11e094c6c155cd08f8051238b047e7d1bba648af 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetExecutable.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetExecutable.scala @@ -1,6 +1,8 @@ package nl.lumc.sasc.biopet.core +import java.io.File import java.util.Properties +import nl.lumc.sasc.biopet.core.config.Config import org.apache.log4j.Logger object BiopetExecutable extends Logging { @@ -82,6 +84,11 @@ object BiopetExecutable extends Logging { return command.get } + // Read config files + for (t <- 0 until args.size) { + if (args(t) == "-config" || args(t) == "--config_ile") Config.global.loadConfigFile(new File(args(t + 1))) + } + args match { case Array("version") => { println("version: " + getVersion) diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala index 015c48dd1525dde3e91d49099a7e48f89c709e69..cf4ee286b0a7c40aa128f3d1fc807e8badce9515 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQScript.scala @@ -2,7 +2,7 @@ package nl.lumc.sasc.biopet.core import java.io.File import java.io.PrintWriter -import nl.lumc.sasc.biopet.core.config.Configurable +import nl.lumc.sasc.biopet.core.config.{ Config, Configurable } import org.broadinstitute.gatk.utils.commandline.Argument import org.broadinstitute.gatk.queue.QSettings import org.broadinstitute.gatk.queue.function.QFunction @@ -25,7 +25,6 @@ trait BiopetQScript extends Configurable { var functions: Seq[QFunction] final def script() { - for (file <- configfiles) globalConfig.loadConfigFile(file) if (!outputDir.endsWith("/")) outputDir += "/" init biopetScript @@ -33,7 +32,7 @@ trait BiopetQScript extends Configurable { case f: BiopetCommandLineFunctionTrait => f.afterGraph case _ => } - val configReport = globalConfig.getReport + val configReport = Config.global.getReport val configReportFile = new File(outputDir + qSettings.runName + ".configreport.txt") configReportFile.getParentFile.mkdir val writer = new PrintWriter(configReportFile) diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/Logging.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/Logging.scala index 9b8197de1acdc1ca492760b931180e09176068bb..32977c6f615aa3cfda69539afee31c330d8e418a 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/Logging.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/Logging.scala @@ -7,9 +7,13 @@ import org.apache.log4j.WriterAppender import org.apache.log4j.helpers.DateLayout trait Logging { - protected val logger = Logger.getLogger(getClass.getSimpleName.split("\\$").last) + def logger = Logging.logger +} + +object Logging { + val logger = Logger.getLogger("Logging") - private[core] val logLayout = new DateLayout() { + val logLayout = new DateLayout() { val ignoresThrowable = false def format(event: org.apache.log4j.spi.LoggingEvent): String = { val calendar: Calendar = Calendar.getInstance @@ -18,10 +22,13 @@ trait Logging { val formattedDate: String = formatter.format(calendar.getTime) var logLevel = event.getLevel.toString while (logLevel.size < 6) logLevel += " " - logLevel + " [" + formattedDate + "] [" + event.getLoggerName + "] " + event.getMessage + "\n" + val className = event.getLocationInformation.getClassName.split("\\.").last.split("\\$").head + logLevel + " [" + formattedDate + "] [" + className + "] " + event.getMessage + "\n" } } - private[core] val stderrAppender = new WriterAppender(logLayout, sys.process.stderr) + + val stderrAppender = new WriterAppender(logLayout, sys.process.stderr) + logger.setLevel(org.apache.log4j.Level.INFO) - logger.addAppender(stderrAppender) -} + logger.addAppender(Logging.stderrAppender) +} \ No newline at end of file diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/MultiSampleQScript.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/MultiSampleQScript.scala index 97bc2e5e6b1d244ec8ee1b0fc3d96ad028421192..81f81f26aafed8ba2126217acec768232077084d 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/MultiSampleQScript.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/MultiSampleQScript.scala @@ -1,6 +1,6 @@ package nl.lumc.sasc.biopet.core -import nl.lumc.sasc.biopet.core.config.Configurable +import nl.lumc.sasc.biopet.core.config.{ Config, Configurable } trait MultiSampleQScript extends BiopetQScript { type LibraryOutput <: AbstractLibraryOutput @@ -20,7 +20,7 @@ trait MultiSampleQScript extends BiopetQScript { final def runSamplesJobs() { samplesConfig = config("samples") if (samplesConfig == null) samplesConfig = Map() - if (globalConfig.contains("samples")) for ((key, value) <- samplesConfig) { + if (Config.global.contains("samples")) for ((key, value) <- samplesConfig) { var sample = Configurable.any2map(value) if (!sample.contains("ID")) sample += ("ID" -> key) if (sample("ID") == key) { diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/ToolCommand.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/ToolCommand.scala index 0a5dc8428cec541fd6cf1b967893e7266bcb1575..6cbef5b674f11d7bdffd7e5e9f766214932a8ba2 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/ToolCommand.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/ToolCommand.scala @@ -9,10 +9,10 @@ trait ToolCommand extends MainCommand with Logging { abstract class AbstractOptParser extends scopt.OptionParser[Args](commandName) { opt[Unit]("log_nostderr") foreach { _ => - logger.removeAppender(stderrAppender) + logger.removeAppender(Logging.stderrAppender) } text ("No output to stderr") opt[File]("log_file") foreach { x => - logger.addAppender(new WriterAppender(logLayout, new java.io.PrintStream(x))) + logger.addAppender(new WriterAppender(Logging.logLayout, new java.io.PrintStream(x))) } text ("Log file") valueName ("<file>") opt[String]('l', "log_level") foreach { x => x.toLowerCase match { diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Config.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Config.scala index c35a1fdd71501b3ecddd721185ee99a271de9434..e373d7b5332651cb45006643a60d61ef1a24a438 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Config.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Config.scala @@ -1,7 +1,7 @@ package nl.lumc.sasc.biopet.core.config import java.io.File -import org.broadinstitute.gatk.queue.util.Logging +import nl.lumc.sasc.biopet.core.Logging import argonaut._, Argonaut._ import scalaz._, Scalaz._ @@ -104,7 +104,9 @@ class Config(var map: Map[String, Any]) extends Logging { override def toString(): String = map.toString } -object Config { +object Config extends Logging { + val global = new Config + def valueToMap(input: Any): Map[String, Any] = { input match { case m: Map[_, _] => return m.asInstanceOf[Map[String, Any]] diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Configurable.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Configurable.scala index 62cd27d6bc12f12283a43e065441306c6eecc178..7f6f6cb8e3e958a3ad121411dbe133603f45fdb4 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Configurable.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/Configurable.scala @@ -6,16 +6,16 @@ import scala.language.implicitConversions trait Configurable extends Logging { val root: Configurable - val globalConfig: Config = if (root != null) root.globalConfig else new Config() + //val globalConfig: Config = if (root != null) root.globalConfig else new Config() def configPath: List[String] = if (root != null) root.configFullPath else List() protected lazy val configName = getClass.getSimpleName.toLowerCase protected lazy val configFullPath = configName :: configPath var defaults: scala.collection.mutable.Map[String, Any] = if (root != null) scala.collection.mutable.Map(root.defaults.toArray: _*) else scala.collection.mutable.Map() - val config = new ConfigFuntions + val config = new ConfigFunctions - protected class ConfigFuntions { + protected class ConfigFunctions { def apply(key: String, default: Any = null, submodule: String = null, required: Boolean = false, freeVar: Boolean = true): ConfigValue = { val m = if (submodule != null) submodule else configName val p = if (submodule != null) configName :: configPath else configPath @@ -29,15 +29,15 @@ trait Configurable extends Logging { throw new IllegalStateException("Value in config could not be found but it is required, key: " + key + " module: " + m + " path: " + p) } else return null } - if (d == null) return globalConfig(m, p, key, freeVar) - else return globalConfig(m, p, key, d, freeVar) + if (d == null) return Config.global(m, p, key, freeVar) + else return Config.global(m, p, key, d, freeVar) } def contains(key: String, submodule: String = null, freeVar: Boolean = true) = { val m = if (submodule != null) submodule else configName val p = if (submodule != null) configName :: configPath else configPath - globalConfig.contains(m, p, key, freeVar) || !(Config.getValueFromMap(defaults.toMap, ConfigValueIndex(m, p, key, freeVar)) == None) + Config.global.contains(m, p, key, freeVar) || !(Config.getValueFromMap(defaults.toMap, ConfigValueIndex(m, p, key, freeVar)) == None) } } diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala index fdb2493a6b48e05f3bca9d7f79760887016a81b6..f30960a2b0932e59dc6cf3ba3881cf5291fda62d 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetrics.scala @@ -26,7 +26,6 @@ class BamMetrics(val root: Configurable) extends QScript with BiopetQScript { var wholeGenome = false def init() { - for (file <- configfiles) globalConfig.loadConfigFile(file) if (outputDir == null) throw new IllegalStateException("Missing Output directory on BamMetrics module") else if (!outputDir.endsWith("/")) outputDir += "/" if (config.contains("target_bed")) { diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala index b0366e5f5bcf0036ed5e64c8ee5c7f3dcb87c8ef..a120a1374f82b2b748571c15e9b40750730192a9 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Flexiprep.scala @@ -18,10 +18,10 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript { var input_R2: File = _ @Argument(doc = "Skip Trim fastq files", shortName = "skiptrim", required = false) - var skipTrim: Boolean = false + var skipTrim: Boolean = config("skiptrim", default = false) @Argument(doc = "Skip Clip fastq files", shortName = "skipclip", required = false) - var skipClip: Boolean = false + var skipClip: Boolean = config("skipclip", default = false) @Argument(doc = "Sample name", shortName = "sample", required = true) var sampleName: String = _ @@ -43,9 +43,6 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript { val summary = new FlexiprepSummary(this) def init() { - for (file <- configfiles) globalConfig.loadConfigFile(file) - if (!skipTrim) skipTrim = config("skiptrim", default = false) - if (!skipClip) skipClip = config("skipclip", default = false) if (input_R1 == null) throw new IllegalStateException("Missing R1 on flexiprep module") if (outputDir == null) throw new IllegalStateException("Missing Output directory on flexiprep module") if (sampleName == null) throw new IllegalStateException("Missing Sample name on flexiprep module") diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala index d26f27e9c07fbc2fb5c6df5117fb89c6f7c8b470..23740daf48fd2f7c4e04e17d7aafe01b24950781 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkBenchmarkGenotyping.scala @@ -18,18 +18,15 @@ class GatkBenchmarkGenotyping(val root: Configurable) extends QScript with Biope @Input(doc = "Gvcf files", shortName = "I", required = false) var gvcfFiles: List[File] = Nil - @Argument(doc = "Reference", shortName = "R", required = false) - var reference: File = _ + var reference: File = config("reference") @Argument(doc = "Dbsnp", shortName = "dbsnp", required = false) - var dbsnp: File = _ + var dbsnp: File = config("dbsnp") def init() { if (config.contains("gvcffiles")) for (file <- config("gvcffiles").getList) { gvcfFiles ::= file.toString } - if (reference == null) reference = config("reference") - if (dbsnp == null) dbsnp = config("dbsnp") if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module") else if (!outputDir.endsWith("/")) outputDir += "/" } diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala index 37adabdc507c686256fbd732d39e72558e079d0b..5ed4f062982c6b64516d651b50c9008953f4b7a2 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkGenotyping.scala @@ -13,10 +13,10 @@ class GatkGenotyping(val root: Configurable) extends QScript with BiopetQScript var inputGvcfs: List[File] = Nil @Argument(doc = "Reference", shortName = "R", required = false) - var reference: File = _ + var reference: File = config("reference") @Argument(doc = "Dbsnp", shortName = "dbsnp", required = false) - var dbsnp: File = _ + var dbsnp: File = config("dbsnp") @Argument(doc = "OutputName", required = false) var outputName: String = "genotype" @@ -28,8 +28,6 @@ class GatkGenotyping(val root: Configurable) extends QScript with BiopetQScript var samples: List[String] = Nil def init() { - if (reference == null) reference = config("reference") - if (dbsnp == null) dbsnp = config("dbsnp") if (outputFile == null) outputFile = outputDir + outputName + ".vcf.gz" if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module") else if (!outputDir.endsWith("/")) outputDir += "/" diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala index 9af84cbbba2212472450b94aefdbe49bc457fd43..c5bb656d039e5bb2b9b19792d03f7a7d2cfaa75c 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkPipeline.scala @@ -27,17 +27,17 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri var mergeGvcfs: Boolean = false @Argument(doc = "Joint variantcalling", shortName = "jointVariantCalling", required = false) - var jointVariantcalling = false + var jointVariantcalling: Boolean = config("joint_variantcalling", default = false) @Argument(doc = "Joint genotyping", shortName = "jointGenotyping", required = false) - var jointGenotyping = false + var jointGenotyping: Boolean = config("joint_genotyping", default = false) - var singleSampleCalling = true - var reference: File = _ - var dbsnp: File = _ + var singleSampleCalling = config("single_sample_calling", default = true) + var reference: File = config("reference", required = true) + var dbsnp: File = config("dbsnp") var gvcfFiles: List[File] = Nil var finalBamFiles: List[File] = Nil - var useAllelesOption: Boolean = _ + var useAllelesOption: Boolean = config("use_alleles_option", default = false) class LibraryOutput extends AbstractLibraryOutput { var mappedBamFile: File = _ @@ -49,15 +49,9 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri } def init() { - useAllelesOption = config("use_alleles_option", default = false) - reference = config("reference", required = true) - dbsnp = config("dbsnp") if (config.contains("target_bed")) { defaults ++= Map("gatk" -> Map(("intervals" -> config("target_bed").getStringList))) } - jointVariantcalling = config("joint_variantcalling", default = false) - jointGenotyping = config("joint_genotyping", default = false) - singleSampleCalling = config("single_sample_calling", default = true) if (config.contains("gvcfFiles")) for (file <- config("gvcfFiles").getList) gvcfFiles :+= file.toString diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala index e4899798f13141998c9f8f81fe4988c31f4f9660..23e6c81b6bb93156f237e3d0bd8bd198dda753b7 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantcalling.scala @@ -24,10 +24,10 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr var rawVcfInput: File = _ @Argument(doc = "Reference", shortName = "R", required = false) - var reference: File = _ + var reference: File = config("reference", required = true) @Argument(doc = "Dbsnp", shortName = "dbsnp", required = false) - var dbsnp: File = _ + var dbsnp: File = config("dbsnp") @Argument(doc = "OutputName", required = false) var outputName: String = _ @@ -35,21 +35,14 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr @Argument(doc = "Sample name", required = false) var sampleID: String = _ - var preProcesBams: Option[Boolean] = None + var preProcesBams: Option[Boolean] = config("pre_proces_bams", default = true) var variantcalling: Boolean = true - var doublePreProces: Option[Boolean] = None - var useHaplotypecaller: Option[Boolean] = None - var useUnifiedGenotyper: Option[Boolean] = None - var useAllelesOption: Option[Boolean] = None + var doublePreProces: Option[Boolean] = config("double_pre_proces", default = true) + var useHaplotypecaller: Option[Boolean] = config("use_haplotypecaller", default = true) + var useUnifiedGenotyper: Option[Boolean] = config("use_unifiedgenotyper", default = false) + var useAllelesOption: Option[Boolean] = config("use_alleles_option", default = false) def init() { - if (useAllelesOption == None) useAllelesOption = config("use_alleles_option", default = false) - if (preProcesBams == None) preProcesBams = config("pre_proces_bams", default = true) - if (doublePreProces == None) doublePreProces = config("double_pre_proces", default = true) - if (useHaplotypecaller == None) useHaplotypecaller = config("use_haplotypecaller", default = true) - if (useUnifiedGenotyper == None) useUnifiedGenotyper = config("use_unifiedgenotyper", default = false) - if (reference == null) reference = config("reference", required = true) - if (dbsnp == null) dbsnp = config("dbsnp") if (outputName == null && sampleID != null) outputName = sampleID else if (outputName == null) outputName = "noname" if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module") diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala index 067012e443ee81958910e07fa0eb8c8361293bd8..2669dc2b38ce5751f14208e41ca64714f1489759 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVcfSampleCompare.scala @@ -16,7 +16,7 @@ class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQS var vcfFiles: List[File] = _ @Argument(doc = "Reference", shortName = "R", required = false) - var reference: File = _ + var reference: File = config("reference") @Argument(doc = "Target bed", shortName = "targetBed", required = false) var targetBed: List[File] = Nil @@ -29,7 +29,6 @@ class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQS def generalSampleDir = outputDir + "samples/" def init() { - if (reference == null) reference = config("reference") if (config.contains("target_bed")) for (bed <- config("target_bed").getList) targetBed :+= bed.toString diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala index fb159e9b8b05b83e5f08fa0664a6ae9ecdd41b7a..d254b51d7baabafbbb7cc0302f8abb5c25a660b2 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala @@ -69,7 +69,7 @@ class Gentrap(val root: Configurable) extends QScript with BiopetQScript { var cExonBase: Boolean = _ def init() { - for (file <- configfiles) globalConfig.loadConfigFile(file) + } def biopetScript() { diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala index ad1406f566dab1c061e7cb52f7feae8e9c260df9..68194858396b0e34b35ed85cc04d31c369d39e03 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala @@ -36,13 +36,13 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript { var skipMetrics: Boolean = false @Argument(doc = "Aligner", shortName = "ALN", required = false) - var aligner: String = _ + var aligner: String = config("aligner", default = "bwa") @Argument(doc = "Reference", shortName = "R", required = false) - var reference: File = _ + var reference: File = config("reference") @Argument(doc = "Chunking", shortName = "chunking", required = false) - var chunking: Boolean = false + var chunking: Boolean = config("chunking", false) @ClassType(classOf[Int]) @Argument(doc = "Number of chunks, when not defined pipeline will automatic calculate number of chunks", shortName = "numberChunks", required = false) @@ -50,62 +50,48 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript { // Readgroup items @Argument(doc = "Readgroup ID", shortName = "RGID", required = false) - var RGID: String = _ + var RGID: String = config("RGID") @Argument(doc = "Readgroup Library", shortName = "RGLB", required = false) - var RGLB: String = _ + var RGLB: String = config("RGLB") @Argument(doc = "Readgroup Platform", shortName = "RGPL", required = false) - var RGPL: String = _ + var RGPL: String = config("RGPL", default = "illumina") @Argument(doc = "Readgroup platform unit", shortName = "RGPU", required = false) - var RGPU: String = _ + var RGPU: String = config("RGPU", default = "na") @Argument(doc = "Readgroup sample", shortName = "RGSM", required = false) - var RGSM: String = _ + var RGSM: String = config("RGSM") @Argument(doc = "Readgroup sequencing center", shortName = "RGCN", required = false) - var RGCN: String = _ + var RGCN: String = config("RGCN") @Argument(doc = "Readgroup description", shortName = "RGDS", required = false) - var RGDS: String = _ + var RGDS: String = config("RGDS") @Argument(doc = "Readgroup sequencing date", shortName = "RGDT", required = false) var RGDT: Date = _ @Argument(doc = "Readgroup predicted insert size", shortName = "RGPI", required = false) - var RGPI: Int = _ + var RGPI: Int = config("RGPI") var paired: Boolean = false - var defaultAligner = "bwa" val flexiprep = new Flexiprep(this) def init() { - for (file <- configfiles) globalConfig.loadConfigFile(file) - if (aligner == null) aligner = config("aligner", default = defaultAligner) - if (reference == null) reference = config("reference") if (outputDir == null) throw new IllegalStateException("Missing Output directory on mapping module") else if (!outputDir.endsWith("/")) outputDir += "/" if (input_R1 == null) throw new IllegalStateException("Missing FastQ R1 on mapping module") paired = (input_R2 != null) - if (RGLB == null && config.contains("RGLB")) RGLB = config("RGLB") - else if (RGLB == null) throw new IllegalStateException("Missing Readgroup library on mapping module") - if (RGSM == null && config.contains("RGSM")) RGSM = config("RGSM") - else if (RGLB == null) throw new IllegalStateException("Missing Readgroup sample on mapping module") - if (RGID == null && config.contains("RGID")) RGID = config("RGID") - else if (RGID == null && RGSM != null && RGLB != null) RGID = RGSM + "-" + RGLB + if (RGLB == null) throw new IllegalStateException("Missing Readgroup library on mapping module") + if (RGLB == null) throw new IllegalStateException("Missing Readgroup sample on mapping module") + if (RGID == null && RGSM != null && RGLB != null) RGID = RGSM + "-" + RGLB else if (RGID == null) throw new IllegalStateException("Missing Readgroup ID on mapping module") - if (RGPL == null) RGPL = config("RGPL", "illumina") - if (RGPU == null) RGPU = config("RGPU", "na") - if (RGCN == null && config.contains("RGCN")) RGCN = config("RGCN") - if (RGDS == null && config.contains("RGDS")) RGDS = config("RGDS") - if (outputName == null) outputName = RGID - if (!chunking && numberChunks.isDefined) chunking = true - if (!chunking) chunking = config("chunking", false) if (chunking) { if (numberChunks.isEmpty) { if (config.contains("numberchunks")) numberChunks = config("numberchunks", default = None) @@ -311,10 +297,6 @@ object Mapping extends PipelineCommand { val mapping = new Mapping(root) logger.debug("Mapping runconfig: " + runConfig) - var inputType = "" - if (runConfig.contains("inputtype")) inputType = runConfig("inputtype").toString - else inputType = root.config("inputtype", "dna").getString - if (inputType == "rna") mapping.defaultAligner = "star-2pass" if (runConfig.contains("R1")) mapping.input_R1 = new File(runConfig("R1").toString) if (runConfig.contains("R2")) mapping.input_R2 = new File(runConfig("R2").toString) mapping.paired = (mapping.input_R2 != null) diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/sage/Sage.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/sage/Sage.scala index 937b84261a20935025aeb79c4f555a7fdfb6827b..7a826e9bb6412d053ff240b1c7e5bc08e9258388 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/sage/Sage.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/sage/Sage.scala @@ -20,15 +20,15 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript { def this() = this(null) @Input(doc = "countBed", required = false) - var countBed: File = _ + var countBed: File = config("count_bed") @Input(doc = "squishedCountBed, by suppling this file the auto squish job will be skipped", required = false) - var squishedCountBed: File = _ + var squishedCountBed: File = config("squished_count_bed") @Input(doc = "Transcriptome, used for generation of tag library", required = false) - var transcriptome: File = _ + var transcriptome: File = config("transcriptome") - var tagsLibrary: File = _ + var tagsLibrary: File = config("tags_library") defaults ++= Map("bowtie" -> Map( "m" -> 1, @@ -50,10 +50,6 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript { def init() { if (!outputDir.endsWith("/")) outputDir += "/" - if (countBed == null) countBed = config("count_bed") - if (squishedCountBed == null) squishedCountBed = config("squished_count_bed") - if (tagsLibrary == null) tagsLibrary = config("tags_library") - if (transcriptome == null) transcriptome = config("transcriptome") if (transcriptome == null && tagsLibrary == null) throw new IllegalStateException("No transcriptome or taglib found") if (countBed == null && squishedCountBed == null) @@ -140,7 +136,7 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript { val mapping = new Mapping(this) mapping.skipFlexiprep = true mapping.skipMarkduplicates = true - mapping.defaultAligner = "bowtie" + mapping.aligner = config("aligner", default = "bowtie") mapping.input_R1 = prefixFastq.output mapping.RGLB = runConfig("ID").toString mapping.RGSM = sampleConfig("ID").toString diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/yamsvp/Yamsvp.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/yamsvp/Yamsvp.scala index 10aef464b610c43571398d6285d3ddd7bc9c5b3c..a428eb693211f1787c72990a7f68ef8df225cc95 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/yamsvp/Yamsvp.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/yamsvp/Yamsvp.scala @@ -21,7 +21,7 @@ import org.broadinstitute.gatk.queue.engine.JobRunInfo class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript { def this() = this(null) - var reference: File = _ + var reference: File = config("reference", required = true) var finalBamFiles: List[File] = Nil class LibraryOutput extends AbstractLibraryOutput { @@ -34,8 +34,6 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript { } override def init() { - for (file <- configfiles) globalConfig.loadConfigFile(file) - reference = config("reference", required = true) if (outputDir == null) throw new IllegalStateException("Output directory is not specified in the config / argument") else if (!outputDir.endsWith("/")) @@ -124,7 +122,7 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript { if (runConfig.contains("R1")) { val mapping = new Mapping(this) - mapping.defaultAligner = "stampy" + mapping.aligner = config("aligner", default = "stampy") mapping.skipFlexiprep = false mapping.skipMarkduplicates = true // we do the dedup marking using Sambamba diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala index 9c364cf62da705beaa94cb682b59a33c7e3329ef..3d11e5452d63b6c87a472ec22ee05454a66d7496 100644 --- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala +++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala @@ -74,16 +74,16 @@ object MpileupToVcf extends ToolCommand { opt[String]('s', "sample") required () action { (x, c) => c.copy(sample = x) } - opt[Int]("minDP") required () action { (x, c) => + opt[Int]("minDP") action { (x, c) => c.copy(minDP = x) } - opt[Int]("minAP") required () action { (x, c) => + opt[Int]("minAP") action { (x, c) => c.copy(minAP = x) } - opt[Double]("homoFraction") required () action { (x, c) => + opt[Double]("homoFraction") action { (x, c) => c.copy(homoFraction = x) } - opt[Int]("ploidy") required () action { (x, c) => + opt[Int]("ploidy") action { (x, c) => c.copy(ploidy = x) } }