diff --git a/biopet-framework/nb-configuration.xml b/biopet-framework/nb-configuration.xml
index 60b959e673d5805e869ae4f91a006ba5d81184a4..c2f0518e2a30c8af3fb854bd8e16e70f23679e5f 100644
--- a/biopet-framework/nb-configuration.xml
+++ b/biopet-framework/nb-configuration.xml
@@ -23,7 +23,6 @@ Any value defined here will override the pom.xml file value but is only applicab
<com-junichi11-netbeans-changelf.use-project>true</com-junichi11-netbeans-changelf.use-project>
<com-junichi11-netbeans-changelf.lf-kind>LF</com-junichi11-netbeans-changelf.lf-kind>
<com-junichi11-netbeans-changelf.use-global>false</com-junichi11-netbeans-changelf.use-global>
- <netbeans.checkstyle.format>true</netbeans.checkstyle.format>
<com-junichi11-netbeans-changelf.show-dialog>true</com-junichi11-netbeans-changelf.show-dialog>
<org-netbeans-modules-javascript2-requirejs.enabled>true</org-netbeans-modules-javascript2-requirejs.enabled>
<netbeans.hint.jdkPlatform>JDK_1.8</netbeans.hint.jdkPlatform>
diff --git a/biopet-framework/pom.xml b/biopet-framework/pom.xml
index f116688f95fc697f13afafa47dd191f347679c45..69c3c3ff4f7ac147c87ade7ec0c9a0c790090a33 100644
--- a/biopet-framework/pom.xml
+++ b/biopet-framework/pom.xml
@@ -216,6 +216,40 @@
<showDeprecation>true</showDeprecation>
</configuration>
</plugin>
+ <plugin>
+ <groupId>org.scalariform</groupId>
+ <artifactId>scalariform-maven-plugin</artifactId>
+ <version>0.1.4</version>
+ <executions>
+ <execution>
+ <phase>process-sources</phase>
+ <goals>
+ <goal>format</goal>
+ </goals>
+ <configuration>
+ <rewriteArrowSymbols>false</rewriteArrowSymbols>
+ <alignParameters>true</alignParameters>
+ <alignSingleLineCaseStatements_maxArrowIndent>40</alignSingleLineCaseStatements_maxArrowIndent>
+ <alignSingleLineCaseStatements>true</alignSingleLineCaseStatements>
+ <compactStringConcatenation>false</compactStringConcatenation>
+ <compactControlReadability>false</compactControlReadability>
+ <doubleIndentClassDeclaration>false</doubleIndentClassDeclaration>
+ <formatXml>true</formatXml>
+ <indentLocalDefs>false</indentLocalDefs>
+ <indentPackageBlocks>true</indentPackageBlocks>
+ <indentSpaces>2</indentSpaces>
+ <placeScaladocAsterisksBeneathSecondAsterisk>false</placeScaladocAsterisksBeneathSecondAsterisk>
+ <preserveDanglingCloseParenthesis>true</preserveDanglingCloseParenthesis>
+ <preserveSpaceBeforeArguments>false</preserveSpaceBeforeArguments>
+ <rewriteArrowSymbols>false</rewriteArrowSymbols>
+ <spaceBeforeColon>false</spaceBeforeColon>
+ <spaceInsideBrackets>false</spaceInsideBrackets>
+ <spaceInsideParentheses>false</spaceInsideParentheses>
+ <spacesWithinPatternBinders>true</spacesWithinPatternBinders>
+ </configuration>
+ </execution>
+ </executions>
+ </plugin>
</plugins>
</build>
</project>
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 e9243dc391454c77e22da875151039253220974e..921f07cfac1c3af94dd100ecc3793e96e1afa9ce 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
@@ -66,13 +66,13 @@ trait BiopetCommandLineFunctionTrait extends CommandLineFunction with Configurab
logger.error("executable: '" + executable + "' not found, please check config")
throw new QException("executable: '" + executable + "' not found, please check config")
}
-
+
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
+ val md5: String = MessageDigest.getInstance("MD5").digest(bytes).map("%02X".format(_)).mkString.toLowerCase
addJobReportBinding("md5sum_exe", md5)
} catch {
@@ -107,7 +107,7 @@ trait BiopetCommandLineFunctionTrait extends CommandLineFunction with Configurab
for (line <- stdout.toString.split("\n") ++ stderr.toString.split("\n")) {
line match {
case versionRegex(m) => return m
- case _ =>
+ case _ =>
}
}
logger.warn("getVersion give a exit code " + process.exitValue + " but no version was found, executable correct? \n" + outputLog)
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 80308d9f6393c38a5fb278c2fba39fb67fc2f6fe..ea0098b9f6a8dd4b79371a2317cf9c6f9ccf61fd 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
@@ -35,7 +35,7 @@ object BiopetExecutable {
nl.lumc.sasc.biopet.tools.SageCreateLibrary,
nl.lumc.sasc.biopet.tools.SageCreateTagCounts)
)
-
+
/**
* @param args the command line arguments
*/
@@ -83,7 +83,7 @@ object BiopetExecutable {
args match {
case Array("version") => {
- println("version: " + getVersion)
+ println("version: " + getVersion)
}
case Array(module, name, passArgs @ _*) => {
getCommand(module, name).main(passArgs.toArray)
@@ -98,11 +98,11 @@ object BiopetExecutable {
}
}
}
-
+
def getVersion = {
getClass.getPackage.getImplementationVersion + " (" + getCommitHash + ")"
}
-
+
def getCommitHash = {
val prop = new Properties()
prop.load(getClass.getClassLoader.getResourceAsStream("git.properties"))
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetJavaCommandLineFunction.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetJavaCommandLineFunction.scala
index a02c679e90ddf26c03c27fb3a143f8a98b599e27..1cbddafe6b999ded0579608de75c35e136f4a053 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetJavaCommandLineFunction.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetJavaCommandLineFunction.scala
@@ -8,7 +8,7 @@ trait BiopetJavaCommandLineFunction extends JavaCommandLineFunction with BiopetC
override def afterGraph {
memoryLimit = config("memory_limit")
}
-
+
override def commandLine: String = {
preCmdInternal
val cmd = super.commandLine
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQCommandLine.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQCommandLine.scala
index be66dabeb24369c32b50743f7e655c231b64aec6..02c17e2f8038f811423d34d6ddc0e864ba09c3f1 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQCommandLine.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/BiopetQCommandLine.scala
@@ -274,16 +274,16 @@ class BiopetQCommandLine extends CommandLineProgram with Logging {
}
private def createQueueHeader(): Seq[String] = {
- Seq("Biopet version: " + BiopetExecutable.getVersion,"",
- "Based on GATK Queue",
-// String.format("Queue v%s, Compiled %s", getQueueVersion, getBuildTimestamp),
- "Copyright (c) 2012 The Broad Institute",
- "For support and documentation go to http://www.broadinstitute.org/gatk")
+ Seq("Biopet version: " + BiopetExecutable.getVersion, "",
+ "Based on GATK Queue",
+ // String.format("Queue v%s, Compiled %s", getQueueVersion, getBuildTimestamp),
+ "Copyright (c) 2012 The Broad Institute",
+ "For support and documentation go to http://www.broadinstitute.org/gatk")
}
private def getQueueVersion: String = {
val stingResources: ResourceBundle = TextFormattingUtils.loadResourceBundle("StingText")
-
+
if (stingResources.containsKey("org.broadinstitute.sting.queue.QueueVersion.version")) {
stingResources.getString("org.broadinstitute.sting.queue.QueueVersion.version")
} else {
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 0ace5448d997012fd10548c2483a9d2fa1ff9a3a..015c48dd1525dde3e91d49099a7e48f89c709e69 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
@@ -23,15 +23,15 @@ trait BiopetQScript extends Configurable {
def biopetScript
var functions: Seq[QFunction]
-
+
final def script() {
for (file <- configfiles) globalConfig.loadConfigFile(file)
if (!outputDir.endsWith("/")) outputDir += "/"
init
biopetScript
for (function <- functions) function match {
- case f:BiopetCommandLineFunctionTrait => f.afterGraph
- case _ =>
+ case f: BiopetCommandLineFunctionTrait => f.afterGraph
+ case _ =>
}
val configReport = globalConfig.getReport
val configReportFile = new File(outputDir + qSettings.runName + ".configreport.txt")
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 e41764b46a59dfbc432303306637b3033deb4f47..97bc2e5e6b1d244ec8ee1b0fc3d96ad028421192 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
@@ -5,18 +5,18 @@ import nl.lumc.sasc.biopet.core.config.Configurable
trait MultiSampleQScript extends BiopetQScript {
type LibraryOutput <: AbstractLibraryOutput
type SampleOutput <: AbstractSampleOutput
-
+
abstract class AbstractLibraryOutput
abstract class AbstractSampleOutput {
var libraries: Map[String, LibraryOutput] = Map()
def getAllLibraries = libraries
- def getLibrary(key:String) = libraries(key)
+ def getLibrary(key: String) = libraries(key)
}
-
+
var samplesConfig: Map[String, Any] = Map()
var samplesOutput: Map[String, SampleOutput] = Map()
def globalSampleDir: String = outputDir + "samples/"
-
+
final def runSamplesJobs() {
samplesConfig = config("samples")
if (samplesConfig == null) samplesConfig = Map()
@@ -25,8 +25,7 @@ trait MultiSampleQScript extends BiopetQScript {
if (!sample.contains("ID")) sample += ("ID" -> key)
if (sample("ID") == key) {
samplesOutput += key -> runSingleSampleJobs(sample)
- }
- else logger.warn("Key is not the same as ID on value for sample")
+ } else logger.warn("Key is not the same as ID on value for sample")
}
else logger.warn("No Samples found in config")
}
@@ -46,8 +45,7 @@ trait MultiSampleQScript extends BiopetQScript {
if (!library.contains("ID")) library += ("ID" -> key)
if (library("ID") == key) {
output += key -> runSingleLibraryJobs(library, sampleConfig)
- }
- else logger.warn("Key is not the same as ID on value for run of sample: " + sampleID)
+ } else logger.warn("Key is not the same as ID on value for run of sample: " + sampleID)
}
} else logger.warn("No runs found in config for sample: " + sampleID)
return output
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 98e59c41372c1dfcb573faf5293300bbe6574701..067194d3175c91563c041fd3cec06e2fa2bd7678 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
@@ -11,51 +11,55 @@ import java.io.File
trait ToolCommand extends MainCommand {
abstract class AbstractArgs {
}
-
+
abstract class AbstractOptParser extends scopt.OptionParser[Args](commandName) {
opt[Unit]("log_nostderr") foreach { _ =>
- logger.removeAppender(stderrAppender) } text("No output to stderr")
+ logger.removeAppender(stderrAppender)
+ } text ("No output to stderr")
opt[File]("log_file") foreach { x =>
- logger.addAppender(new WriterAppender(logLayout, new java.io.PrintStream(x))) } text("Log file") valueName("<file>")
+ logger.addAppender(new WriterAppender(logLayout, new java.io.PrintStream(x)))
+ } text ("Log file") valueName ("<file>")
opt[String]('l', "log_level") foreach { x =>
- x.toLowerCase match {
- case "debug" => logger.setLevel(org.apache.log4j.Level.DEBUG)
- case "info" => logger.setLevel(org.apache.log4j.Level.INFO)
- case "warn" => logger.setLevel(org.apache.log4j.Level.WARN)
- case "error" => logger.setLevel(org.apache.log4j.Level.ERROR)
- case _ =>
- } } text("Log level") validate { x => x match {
- case "debug" | "info" | "warn" | "error" => success
- case _ => failure("Log level must be <debug/info/warn/error>")
- }
- }
+ x.toLowerCase match {
+ case "debug" => logger.setLevel(org.apache.log4j.Level.DEBUG)
+ case "info" => logger.setLevel(org.apache.log4j.Level.INFO)
+ case "warn" => logger.setLevel(org.apache.log4j.Level.WARN)
+ case "error" => logger.setLevel(org.apache.log4j.Level.ERROR)
+ case _ =>
+ }
+ } text ("Log level") validate { x =>
+ x match {
+ case "debug" | "info" | "warn" | "error" => success
+ case _ => failure("Log level must be <debug/info/warn/error>")
+ }
+ }
opt[Unit]('h', "help") foreach { _ =>
System.err.println(this.usage)
sys.exit(1)
- } text("Print usage")
+ } text ("Print usage")
opt[Unit]('v', "version") foreach { _ =>
System.err.println("Version: " + BiopetExecutable.getVersion)
sys.exit(1)
- } text("Print version")
+ } text ("Print version")
}
-
+
type Args <: AbstractArgs
type OptParser <: AbstractOptParser
-
+
protected val logger = Logger.getLogger(commandName)
-
+
private val logLayout = new DateLayout() {
- val ignoresThrowable = false
- def format(event:org.apache.log4j.spi.LoggingEvent): String = {
- val calendar: Calendar = Calendar.getInstance
- calendar.setTimeInMillis(event.getTimeStamp)
- val formatter: SimpleDateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
- 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 ignoresThrowable = false
+ def format(event: org.apache.log4j.spi.LoggingEvent): String = {
+ val calendar: Calendar = Calendar.getInstance
+ calendar.setTimeInMillis(event.getTimeStamp)
+ val formatter: SimpleDateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
+ val formattedDate: String = formatter.format(calendar.getTime)
+ var logLevel = event.getLevel.toString
+ while (logLevel.size < 6) logLevel += " "
+ logLevel + " [" + formattedDate + "] [" + event.getLoggerName + "] " + event.getMessage + "\n"
}
+ }
private val stderrAppender = new WriterAppender(logLayout, sys.process.stderr)
logger.setLevel(org.apache.log4j.Level.INFO)
logger.addAppender(stderrAppender)
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 fc7550ea9f52ebbd0712932ccac469da512ac908..c35a1fdd71501b3ecddd721185ee99a271de9434 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
@@ -44,9 +44,9 @@ class Config(var map: Map[String, Any]) extends Logging {
protected[config] var defaultCache: Map[ConfigValueIndex, ConfigValue] = Map()
def contains(s: String): Boolean = map.contains(s)
- def contains(requestedIndex: ConfigValueIndex, freeVar:Boolean): Boolean = contains(requestedIndex.module, requestedIndex.path, requestedIndex.key, freeVar)
+ def contains(requestedIndex: ConfigValueIndex, freeVar: Boolean): Boolean = contains(requestedIndex.module, requestedIndex.path, requestedIndex.key, freeVar)
def contains(requestedIndex: ConfigValueIndex): Boolean = contains(requestedIndex.module, requestedIndex.path, requestedIndex.key, true)
- def contains(module: String, path: List[String], key: String, freeVar:Boolean = true): Boolean = {
+ def contains(module: String, path: List[String], key: String, freeVar: Boolean = true): Boolean = {
val requestedIndex = ConfigValueIndex(module, path, key, freeVar)
if (notFoundCache.contains(requestedIndex)) return false
else if (foundCache.contains(requestedIndex)) return true
@@ -62,7 +62,7 @@ class Config(var map: Map[String, Any]) extends Logging {
}
}
- protected[config] def apply(module: String, path: List[String], key: String, default: Any = null, freeVar:Boolean = true): ConfigValue = {
+ protected[config] def apply(module: String, path: List[String], key: String, default: Any = null, freeVar: Boolean = true): ConfigValue = {
val requestedIndex = ConfigValueIndex(module, path, key)
if (contains(requestedIndex, freeVar)) return foundCache(requestedIndex)
else if (default != null) {
@@ -133,7 +133,7 @@ object Config {
}
def mergeConfigs(config1: Config, config2: Config): Config = new Config(mergeMaps(config1.map, config2.map))
-
+
private def jsonToMap(json: Json): Map[String, Any] = {
var output: Map[String, Any] = Map()
if (json.isObject) {
@@ -159,8 +159,8 @@ object Config {
else return num.toLong
} else throw new IllegalStateException("Config value type not supported, value: " + json)
}
-
- private def getMapFromPath(map:Map[String,Any], path: List[String]): Map[String, Any] = {
+
+ private def getMapFromPath(map: Map[String, Any], path: List[String]): Map[String, Any] = {
var returnMap: Map[String, Any] = map
for (m <- path) {
if (!returnMap.contains(m)) return Map()
@@ -168,8 +168,8 @@ object Config {
}
return returnMap
}
-
- def getValueFromMap(map:Map[String,Any], index:ConfigValueIndex): Option[ConfigValue] = {
+
+ def getValueFromMap(map: Map[String, Any], index: ConfigValueIndex): Option[ConfigValue] = {
var submodules = index.path.reverse
while (!submodules.isEmpty) {
var submodules2 = submodules
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/ConfigValueIndex.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/ConfigValueIndex.scala
index 4d515b347d9522d62facfa9c53dea7d43e27e5a0..348780c0dd01e48ff005d67134935d694d8bcc0d 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/ConfigValueIndex.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/core/config/ConfigValueIndex.scala
@@ -1,13 +1,13 @@
package nl.lumc.sasc.biopet.core.config
-class ConfigValueIndex(val module: String, val path: List[String], val key: String, val freeVar:Boolean = true) {
+class ConfigValueIndex(val module: String, val path: List[String], val key: String, val freeVar: Boolean = true) {
override def toString = "Module = " + module + ", path = " + path + ", key = " + key + ", freeVar = " + freeVar
}
object ConfigValueIndex {
private var cache: Map[(String, List[String], String), ConfigValueIndex] = Map()
- def apply(module: String, path: List[String], key: String, freeVar:Boolean = true): ConfigValueIndex = {
+ def apply(module: String, path: List[String], key: String, freeVar: Boolean = true): ConfigValueIndex = {
if (!cache.contains(module, path, key)) cache += ((module, path, key) -> new ConfigValueIndex(module, path, key, freeVar))
return cache(module, path, key)
}
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 9122a5946a276a794da52185163f2ace85b68b45..b9eb07879c75039fb347672c797661a145ad3b9a 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
@@ -9,13 +9,13 @@ trait Configurable extends Logging {
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()
-
+ 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
-
+
protected class ConfigFuntions {
- def apply(key: String, default: Any = null, submodule: String = null, required: Boolean = false, freeVar:Boolean = true): ConfigValue = {
+ 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
val d = {
@@ -31,15 +31,15 @@ trait Configurable extends Logging {
if (d == null) return globalConfig(m, p, key, freeVar)
else return globalConfig(m, p, key, d, freeVar)
}
-
- def contains(key: String, submodule: String = null, freeVar:Boolean = true) = {
+
+ 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)
}
}
-
+
implicit def configValue2file(value: ConfigValue): File = if (value != null) new File(Configurable.any2string(value.value)) else null
implicit def configValue2string(value: ConfigValue): String = if (value != null) Configurable.any2string(value.value) else null
implicit def configValue2long(value: ConfigValue): Long = if (value != null) Configurable.any2long(value.value) else 0
@@ -104,7 +104,7 @@ object Configurable extends Logging {
case _ => throw new IllegalStateException("Value '" + any + "' is not an int")
}
}
-
+
def any2float(any: Any): Float = {
any match {
case f: Double => return f.toFloat
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Cufflinks.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Cufflinks.scala
index dcf482ac502628e257c7f83bd98bc194a7be7d64..b0f0ba321b4934a7a3a0b3093058a9682ce60a73 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Cufflinks.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Cufflinks.scala
@@ -16,7 +16,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
* Written based on cufflinks version v2.2.1.
*/
class Cufflinks(val root: Configurable) extends BiopetCommandLineFunction {
-
+
/** default executable */
executable = config("exe", default = "cufflinks")
@@ -177,7 +177,7 @@ class Cufflinks(val root: Configurable) extends BiopetCommandLineFunction {
override def versionCommand = executable
def cmdLine = {
- required(executable) +
+ required(executable) +
required("--output-dir", output_dir) +
optional("--num-threads", num_threads) +
optional("--seed", seed) +
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Fastqc.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Fastqc.scala
index b8ca496fc1ccb835fb04608ca7c35f26949a22f7..0f6b664a0d6f6c5aef9db2a90e7cc9d645a19fce 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Fastqc.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Fastqc.scala
@@ -11,7 +11,7 @@ class Fastqc(val root: Configurable) extends BiopetCommandLineFunction {
@Input(doc = "Contaminants", required = false)
var contaminants: File = _
-
+
@Input(doc = "Adapters", required = false)
var adapters: File = _
@@ -39,11 +39,11 @@ class Fastqc(val root: Configurable) extends BiopetCommandLineFunction {
val fastqcDir = executable.substring(0, executable.lastIndexOf("/"))
val defaultContams = getVersion match {
case "v0.11.2" => new File(fastqcDir + "/Configuration/contaminant_list.txt")
- case _ => new File(fastqcDir + "/Contaminants/contaminant_list.txt")
+ case _ => new File(fastqcDir + "/Contaminants/contaminant_list.txt")
}
val defaultAdapters = getVersion match {
case "v0.11.2" => new File(fastqcDir + "/Configuration/adapter_list.txt")
- case _ => null
+ case _ => null
}
contaminants = config("contaminants", default = defaultContams)
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala
index 0d8324338f012c30740aa0660188711ebad35b05..253cab16b78908eee3e236bc323e0ed437449690 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Ln.scala
@@ -83,12 +83,12 @@ class Ln(val root: Configurable) extends InProcessFunction with Configurable {
}
}
- object Ln {
- def apply(root: Configurable, input:File, output:File, relative:Boolean = true): Ln = {
- val ln = new Ln(root)
- ln.in = input
- ln.out = output
- ln.relative = relative
- return ln
- }
- }
+object Ln {
+ def apply(root: Configurable, input: File, output: File, relative: Boolean = true): Ln = {
+ val ln = new Ln(root)
+ ln.in = input
+ ln.out = output
+ ln.relative = relative
+ return ln
+ }
+}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Seqstat.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Seqstat.scala
index 1197448c42db71c23e3154987abbe9c88d3a490d..9a25a11cc30f85ae9c7d2f3ddf34e52116eb6627 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Seqstat.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/Seqstat.scala
@@ -27,7 +27,7 @@ class Seqstat(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "fastq-seqstat")
def cmdLine = required(executable) + required(input) + " > " + required(output)
-
+
def getSummary: Json = {
val json = Parse.parseOption(Source.fromFile(output).mkString)
if (json.isEmpty) return jNull
@@ -42,7 +42,7 @@ object Seqstat {
seqstat.output = output
return seqstat
}
-
+
def apply(root: Configurable, fastqfile: File, outDir: String): Seqstat = {
val seqstat = new Seqstat(root)
val ext = fastqfile.getName.substring(fastqfile.getName.lastIndexOf("."))
@@ -52,7 +52,7 @@ object Seqstat {
}
def mergeSummaries(jsons: List[Json]): Json = {
- def addJson(json:Json, total:Map[String, Long]) {
+ def addJson(json: Json, total: Map[String, Long]) {
for (key <- json.objectFieldsOrEmpty) {
if (json.field(key).get.isObject) addJson(json.field(key).get, total)
else if (json.field(key).get.isNumber) {
@@ -63,53 +63,52 @@ object Seqstat {
} else if (key == "len_max") {
if (total(key) < number) total(key) = number
} else total(key) += number
- }
- else total += (key -> number)
+ } else total += (key -> number)
}
}
}
-
+
var basesTotal: Map[String, Long] = Map()
var readsTotal: Map[String, Long] = Map()
var encoding: Set[Json] = Set()
for (json <- jsons) {
encoding += json.fieldOrEmptyString("qual_encoding")
-
+
val bases = json.fieldOrEmptyObject("bases")
addJson(bases, basesTotal)
-
+
val reads = json.fieldOrEmptyObject("reads")
addJson(reads, readsTotal)
}
return ("bases" := (
- ("num_n" := basesTotal("num_n")) ->:
- ("num_total" := basesTotal("num_total")) ->:
- ("num_qual_gte" := (
- ("1" := basesTotal("1")) ->:
- ("10" := basesTotal("10")) ->:
- ("20" := basesTotal("20")) ->:
- ("30" := basesTotal("30")) ->:
- ("40" := basesTotal("40")) ->:
- ("50" := basesTotal("50")) ->:
- ("60" := basesTotal("60")) ->:
- jEmptyObject
- ) ) ->: jEmptyObject)) ->:
- ("reads" := (
- ("num_with_n" := readsTotal("num_with_n")) ->:
- ("num_total" := readsTotal("num_total")) ->:
- ("len_min" := readsTotal("len_min")) ->:
- ("len_max" := readsTotal("len_max")) ->:
- ("num_mean_qual_gte" := (
- ("1" := readsTotal("1")) ->:
- ("10" := readsTotal("10")) ->:
- ("20" := readsTotal("20")) ->:
- ("30" := readsTotal("30")) ->:
- ("40" := readsTotal("40")) ->:
- ("50" := readsTotal("50")) ->:
- ("60" := readsTotal("60")) ->:
- jEmptyObject
- ) ) ->: jEmptyObject)) ->:
- ("qual_encoding" := encoding.head) ->:
- jEmptyObject
+ ("num_n" := basesTotal("num_n")) ->:
+ ("num_total" := basesTotal("num_total")) ->:
+ ("num_qual_gte" := (
+ ("1" := basesTotal("1")) ->:
+ ("10" := basesTotal("10")) ->:
+ ("20" := basesTotal("20")) ->:
+ ("30" := basesTotal("30")) ->:
+ ("40" := basesTotal("40")) ->:
+ ("50" := basesTotal("50")) ->:
+ ("60" := basesTotal("60")) ->:
+ jEmptyObject
+ )) ->: jEmptyObject)) ->:
+ ("reads" := (
+ ("num_with_n" := readsTotal("num_with_n")) ->:
+ ("num_total" := readsTotal("num_total")) ->:
+ ("len_min" := readsTotal("len_min")) ->:
+ ("len_max" := readsTotal("len_max")) ->:
+ ("num_mean_qual_gte" := (
+ ("1" := readsTotal("1")) ->:
+ ("10" := readsTotal("10")) ->:
+ ("20" := readsTotal("20")) ->:
+ ("30" := readsTotal("30")) ->:
+ ("40" := readsTotal("40")) ->:
+ ("50" := readsTotal("50")) ->:
+ ("60" := readsTotal("60")) ->:
+ jEmptyObject
+ )) ->: jEmptyObject)) ->:
+ ("qual_encoding" := encoding.head) ->:
+ jEmptyObject
}
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Bowtie.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Bowtie.scala
index 285e960f5b79a2c4ece37b0a259b4f7395c1caa8..dc80575b9d274ff659aa35b75ce6cdc54a3df690 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Bowtie.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Bowtie.scala
@@ -22,7 +22,7 @@ class Bowtie(val root: Configurable) extends BiopetCommandLineFunction {
override val versionRegex = """.*[Vv]ersion:? (.*)""".r
override val versionExitcode = List(0, 1)
override def versionCommand = executable + " --version"
-
+
override val defaultVmem = "6G"
override val defaultThreads = 8
@@ -36,7 +36,7 @@ class Bowtie(val root: Configurable) extends BiopetCommandLineFunction {
var maxbts: Option[Int] = config("maxbts")
var strata: Boolean = config("strata")
var maqerr: Option[Int] = config("maqerr")
-
+
def cmdLine = {
required(executable) +
optional("--threads", nCoresRequest) +
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Star.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Star.scala
index 82bb495298b71f45e988be30eae3960ad4e775da..01cab5aaff9e69224addd9b79f2370cd0c152e82 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Star.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/aligners/Star.scala
@@ -81,7 +81,7 @@ class Star(val root: Configurable) extends BiopetCommandLineFunction {
}
object Star {
- def apply(configurable: Configurable, R1: File, R2: File, outputDir: String, isIntermediate: Boolean = false, deps:List[File] = Nil): Star = {
+ def apply(configurable: Configurable, R1: File, R2: File, outputDir: String, isIntermediate: Boolean = false, deps: List[File] = Nil): Star = {
val star = new Star(configurable)
star.R1 = R1
if (R2 != null) star.R2 = R2
@@ -92,7 +92,7 @@ object Star {
return star
}
- def _2pass(configurable: Configurable, R1: File, R2: File, outputDir: String, isIntermediate: Boolean = false, deps:List[File] = Nil): (File, List[Star]) = {
+ def _2pass(configurable: Configurable, R1: File, R2: File, outputDir: String, isIntermediate: Boolean = false, deps: List[File] = Nil): (File, List[Star]) = {
val outDir = if (outputDir.endsWith("/")) outputDir else outputDir + "/"
val starCommand_pass1 = Star(configurable, R1, if (R2 != null) R2 else null, outDir + "aln-pass1/")
starCommand_pass1.isIntermediate = isIntermediate
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/bedtools/BedtoolsCoverage.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/bedtools/BedtoolsCoverage.scala
index 916ead166b617f78667dc6c40563214bfa8f24e5..aebf9d3637261abdd2f08fc69f8141e0e7ad2e5f 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/bedtools/BedtoolsCoverage.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/bedtools/BedtoolsCoverage.scala
@@ -16,10 +16,10 @@ class BedtoolsCoverage(val root: Configurable) extends Bedtools {
@Argument(doc = "dept", required = false)
var depth: Boolean = false
-
+
@Argument(doc = "sameStrand", required = false)
var sameStrand: Boolean = false
-
+
@Argument(doc = "diffStrand", required = false)
var diffStrand: Boolean = false
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
index a3b8fcf942408dff7c9166e3301f66d706df7071..525c357a9b7ef31e72f43adf5a50b98304bf858f 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/AnalyzeCovariates.scala
@@ -5,9 +5,9 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class AnalyzeCovariates(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.AnalyzeCovariates with GatkGeneral {
}
-
+
object AnalyzeCovariates {
- def apply(root: Configurable, before:File, after:File, plots:File): AnalyzeCovariates = {
+ def apply(root: Configurable, before: File, after: File, plots: File): AnalyzeCovariates = {
val ac = new AnalyzeCovariates(root)
ac.before = before
ac.after = after
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
index 2e1d5de232ee1c9e2412e1605ddb0dab6e36f021..b0e3a71fcdeab46f3add6e93c3943a38a3303ceb 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/ApplyRecalibration.scala
@@ -6,21 +6,22 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class ApplyRecalibration(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.ApplyRecalibration with GatkGeneral {
override def afterGraph {
super.afterGraph
-
+
if (config.contains("scattercount")) scatterCount = config("scattercount")
-
+
nt = Option(getThreads(3))
memoryLimit = Option(nt.getOrElse(1) * 2)
ts_filter_level = config("ts_filter_level")
}
}
-
+
object ApplyRecalibration {
- def apply(root: Configurable, input:File, output:File, recal_file:File, tranches_file:File, indel: Boolean = false): ApplyRecalibration = {
+ def apply(root: Configurable, input: File, output: File, recal_file: File, tranches_file: File, indel: Boolean = false): ApplyRecalibration = {
val ar = if (indel) new ApplyRecalibration(root) {
mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.INDEL
defaults ++= Map("ts_filter_level" -> 99.0)
- } else new ApplyRecalibration(root) {
+ }
+ else new ApplyRecalibration(root) {
mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.SNP
defaults ++= Map("ts_filter_level" -> 99.5)
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
index 0be0c04bfc63db068c4d286e8d24bc3b3edda898..8c736f955f7fd155ad3bce8f625503078b542869 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/BaseRecalibrator.scala
@@ -6,18 +6,18 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class BaseRecalibrator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.BaseRecalibrator with GatkGeneral {
memoryLimit = Option(4)
override val defaultVmem = "8G"
-
+
override def afterGraph {
super.afterGraph
-
+
if (config.contains("scattercount")) scatterCount = config("scattercount")
if (config.contains("dbsnp")) knownSites :+= new File(config("dbsnp").getString)
if (config.contains("known_sites")) knownSites :+= new File(config("known_sites").getString)
}
}
-
+
object BaseRecalibrator {
- def apply(root: Configurable, input:File, output:File): BaseRecalibrator = {
+ def apply(root: Configurable, input: File, output: File): BaseRecalibrator = {
val br = new BaseRecalibrator(root)
br.input_file :+= input
br.out = output
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
index 21986b24731d76521fd22c538c5f6bd45463ae7f..5b3e4df4b2fd661d249a881255001d342078e12c 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineGVCFs.scala
@@ -6,7 +6,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class CombineGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.CombineGVCFs with GatkGeneral {
if (config.contains("scattercount")) scatterCount = config("scattercount")
}
-
+
object CombineGVCFs {
def apply(root: Configurable, input: List[File], output: File): CombineGVCFs = {
val cg = new CombineGVCFs(root)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
index ab97ad82d09b95d8bbc16eaeb0a1467febb39472..1ad7e42e705c2b3064604d06c3c1dc047330df27 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/CombineVariants.scala
@@ -6,9 +6,9 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class CombineVariants(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.CombineVariants with GatkGeneral {
if (config.contains("scattercount")) scatterCount = config("scattercount")
}
-
+
object CombineVariants {
- def apply(root: Configurable, input:List[File], output:File): CombineVariants = {
+ def apply(root: Configurable, input: List[File], output: File): CombineVariants = {
val cv = new CombineVariants(root)
cv.variant = input
cv.out = output
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala
index 28e4e4953f4c8d64ec4d583191885c03ef730e9a..44e5e62fed7ab5319ee24c92fe313082157621fd 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GatkGeneral.scala
@@ -5,9 +5,9 @@ import org.broadinstitute.gatk.queue.extensions.gatk.CommandLineGATK
trait GatkGeneral extends CommandLineGATK with BiopetJavaCommandLineFunction {
memoryLimit = Option(3)
-
+
override val defaultVmem = "7G"
-
+
if (config.contains("intervals", submodule = "gatk")) intervals = config("intervals", submodule = "gatk").getFileList
if (config.contains("exclude_intervals", submodule = "gatk")) excludeIntervals = config("exclude_intervals", submodule = "gatk").getFileList
reference_sequence = config("reference", submodule = "gatk")
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
index f44043208df1ea086f4a560fae296a8a566c8d68..d1ee959743d22ba09296db9ebbdada53adeaba9e 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/GenotypeGVCFs.scala
@@ -5,10 +5,10 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class GenotypeGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.GenotypeGVCFs with GatkGeneral {
annotation ++= config("annotation", default = Seq("FisherStrand", "QualByDepth", "ChromosomeCounts")).getStringList
-
+
if (config.contains("dbsnp")) dbsnp = config("dbsnp")
if (config.contains("scattercount", "genotypegvcfs")) scatterCount = config("scattercount")
-
+
if (config("inputtype", default = "dna").getString == "rna") {
stand_call_conf = config("stand_call_conf", default = 20)
stand_emit_conf = config("stand_emit_conf", default = 0)
@@ -17,9 +17,9 @@ class GenotypeGVCFs(val root: Configurable) extends org.broadinstitute.gatk.queu
stand_emit_conf = config("stand_emit_conf", default = 0)
}
}
-
+
object GenotypeGVCFs {
- def apply(root: Configurable, gvcfFiles:List[File], output:File): GenotypeGVCFs = {
+ def apply(root: Configurable, gvcfFiles: List[File], output: File): GenotypeGVCFs = {
val gg = new GenotypeGVCFs(root)
gg.variant = gvcfFiles
gg.out = output
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
index a83ee965e86207e1a0e73d48cdeb8ba86426ce8b..f9d1dd1467630060f9cb162511eddf9044fec8a3 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/HaplotypeCaller.scala
@@ -6,7 +6,7 @@ import org.broadinstitute.gatk.utils.variant.GATKVCFIndexType
class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.HaplotypeCaller with GatkGeneral {
override def afterGraph {
super.afterGraph
-
+
min_mapping_quality_score = config("minMappingQualityScore", default = 20)
if (config.contains("scattercount")) scatterCount = config("scattercount")
if (config.contains("dbsnp")) this.dbsnp = config("dbsnp")
@@ -15,13 +15,13 @@ class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.qu
bamOutput = config("bamOutput")
memoryLimit = Option(nct.getOrElse(1) * 2)
if (config.contains("allSitePLs")) this.allSitePLs = config("allSitePLs")
- if (config.contains("output_mode")){
+ if (config.contains("output_mode")) {
import org.broadinstitute.gatk.tools.walkers.genotyper.OutputMode._
config("output_mode").getString match {
case "EMIT_ALL_CONFIDENT_SITES" => output_mode = EMIT_ALL_CONFIDENT_SITES
- case "EMIT_ALL_SITES" => output_mode = EMIT_ALL_SITES
- case "EMIT_VARIANTS_ONLY" => output_mode = EMIT_VARIANTS_ONLY
- case e => logger.warn("output mode '" + e + "' does not exist")
+ case "EMIT_ALL_SITES" => output_mode = EMIT_ALL_SITES
+ case "EMIT_VARIANTS_ONLY" => output_mode = EMIT_VARIANTS_ONLY
+ case e => logger.warn("output mode '" + e + "' does not exist")
}
}
@@ -39,7 +39,7 @@ class HaplotypeCaller(val root: Configurable) extends org.broadinstitute.gatk.qu
logger.warn("BamOutput is on, nct/threads is forced to set on 1, this option is only for debug")
}
}
-
+
def useGvcf() {
emitRefConfidence = org.broadinstitute.gatk.tools.walkers.haplotypecaller.ReferenceConfidenceMode.GVCF
variant_index_type = GATKVCFIndexType.LINEAR
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
index 4ead517edcaa6313ebaedea39ddc10fb7c5dca6f..f9f06daacb9c97f8e73058838b392f318d192205 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/IndelRealigner.scala
@@ -6,9 +6,9 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class IndelRealigner(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.IndelRealigner with GatkGeneral {
if (config.contains("scattercount")) scatterCount = config("scattercount")
}
-
+
object IndelRealigner {
- def apply(root: Configurable, input:File, targetIntervals:File, outputDir:String): IndelRealigner = {
+ def apply(root: Configurable, input: File, targetIntervals: File, outputDir: String): IndelRealigner = {
val ir = new IndelRealigner(root)
ir.input_file :+= input
ir.targetIntervals = targetIntervals
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
index b9650eb7feff1889e3e9c425406ff7f656f904ed..6f039932b001ea2f6dde5c4559b1fe952bcadef1 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/PrintReads.scala
@@ -5,14 +5,14 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class PrintReads(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.PrintReads with GatkGeneral {
memoryLimit = Option(4)
-
+
override val defaultVmem = "8G"
-
+
if (config.contains("scattercount")) scatterCount = config("scattercount")
}
-
+
object PrintReads {
- def apply(root: Configurable, input:File, output:File): PrintReads = {
+ def apply(root: Configurable, input: File, output: File): PrintReads = {
val br = new PrintReads(root)
br.input_file :+= input
br.out = output
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
index 4339760ad6e542f373e83ac712e42b4901d96fa4..da1fe1197194a85010db483759e5ef645e575bb6 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/RealignerTargetCreator.scala
@@ -6,14 +6,14 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class RealignerTargetCreator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.RealignerTargetCreator with GatkGeneral {
override val defaultVmem = "6G"
memoryLimit = Some(2.5)
-
+
if (config.contains("scattercount")) scatterCount = config("scattercount")
if (config.contains("known")) known ++= config("known").getFileList
}
-
+
object RealignerTargetCreator {
- def apply(root: Configurable, input:File, outputDir:String): RealignerTargetCreator = {
+ def apply(root: Configurable, input: File, outputDir: String): RealignerTargetCreator = {
val re = new RealignerTargetCreator(root)
re.input_file :+= input
re.out = new File(outputDir, input.getName.stripSuffix(".bam") + ".realign.intervals")
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
index e32f9807ef5d21bd5a9fbed1f7b544d4a40d05d6..cd056c4293df7cc16b0442ff217fd931b3bc30e4 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/SelectVariants.scala
@@ -6,9 +6,9 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class SelectVariants(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.SelectVariants with GatkGeneral {
if (config.contains("scattercount")) scatterCount = config("scattercount")
}
-
+
object SelectVariants {
- def apply(root: Configurable, input:File, output:File): SelectVariants = {
+ def apply(root: Configurable, input: File, output: File): SelectVariants = {
val sv = new SelectVariants(root)
sv.variant = input
sv.out = output
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
index 0a70e4465af57e7c8ecd082c806027a57cff2db4..96cc081492fd65b350d8f28b2e75e7d776779811 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/UnifiedGenotyper.scala
@@ -5,7 +5,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
class UnifiedGenotyper(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.UnifiedGenotyper with GatkGeneral {
override def afterGraph {
super.afterGraph
-
+
genotype_likelihoods_model = org.broadinstitute.gatk.tools.walkers.genotyper.GenotypeLikelihoodsCalculationModel.Model.BOTH
if (config.contains("scattercount")) scatterCount = config("scattercount")
if (config.contains("dbsnp")) this.dbsnp = config("dbsnp")
@@ -13,13 +13,13 @@ class UnifiedGenotyper(val root: Configurable) extends org.broadinstitute.gatk.q
nct = config("threads", default = 3)
memoryLimit = Option(nct.getOrElse(1) * 2)
if (config.contains("allSitePLs")) this.allSitePLs = config("allSitePLs")
- if (config.contains("output_mode")){
+ if (config.contains("output_mode")) {
import org.broadinstitute.gatk.tools.walkers.genotyper.OutputMode._
config("output_mode").getString match {
case "EMIT_ALL_CONFIDENT_SITES" => output_mode = EMIT_ALL_CONFIDENT_SITES
- case "EMIT_ALL_SITES" => output_mode = EMIT_ALL_SITES
- case "EMIT_VARIANTS_ONLY" => output_mode = EMIT_VARIANTS_ONLY
- case e => logger.warn("output mode '" + e + "' does not exist")
+ case "EMIT_ALL_SITES" => output_mode = EMIT_ALL_SITES
+ case "EMIT_VARIANTS_ONLY" => output_mode = EMIT_VARIANTS_ONLY
+ case e => logger.warn("output mode '" + e + "' does not exist")
}
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
index d5f0474f1dd24bc64a5f340c528c93cd0e1acf6d..3a829421cc9122ba14b8ba639d0d7b457ea91705 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantAnnotator.scala
@@ -7,9 +7,9 @@ class VariantAnnotator(val root: Configurable) extends org.broadinstitute.gatk.q
if (config.contains("scattercount")) scatterCount = config("scattercount")
dbsnp = config("dbsnp")
}
-
+
object VariantAnnotator {
- def apply(root: Configurable, input:File, bamFiles:List[File], output:File): VariantAnnotator = {
+ def apply(root: Configurable, input: File, bamFiles: List[File], output: File): VariantAnnotator = {
val va = new VariantAnnotator(root)
va.variant = input
va.input_file = bamFiles
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
index 2045caba3c7c6bad0f2b3fd0f805db7eddc3e86a..25df9f92eb962d021b215d4f8588ca356cee9cab 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/gatk/VariantRecalibrator.scala
@@ -7,24 +7,24 @@ import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
class VariantRecalibrator(val root: Configurable) extends org.broadinstitute.gatk.queue.extensions.gatk.VariantRecalibrator with GatkGeneral {
nt = Option(getThreads(4))
memoryLimit = Option(nt.getOrElse(1) * 2)
-
+
if (config.contains("dbsnp")) resource :+= new TaggedFile(config("dbsnp").getString, "known=true,training=false,truth=false,prior=2.0")
-
+
an = config("annotation", default = List("QD", "DP", "FS", "ReadPosRankSum", "MQRankSum")).getStringList
minNumBadVariants = config("minnumbadvariants")
maxGaussians = config("maxgaussians")
}
-
+
object VariantRecalibrator {
- def apply(root: Configurable, input:File, recal_file:File, tranches_file:File, indel: Boolean = false): VariantRecalibrator = {
+ def apply(root: Configurable, input: File, recal_file: File, tranches_file: File, indel: Boolean = false): VariantRecalibrator = {
val vr = new VariantRecalibrator(root) {
override lazy val configName = "variantrecalibrator"
- override def configPath: List[String] = (if (indel) "indel" else "snp") :: super.configPath
+ override def configPath: List[String] = (if (indel) "indel" else "snp") :: super.configPath
if (indel) {
mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.INDEL
defaults ++= Map("ts_filter_level" -> 99.0)
if (config.contains("mills")) resource :+= new TaggedFile(config("mills").getString, "known=false,training=true,truth=true,prior=12.0")
- } else {
+ } else {
mode = org.broadinstitute.gatk.tools.walkers.variantrecalibration.VariantRecalibratorArgumentCollection.Mode.SNP
defaults ++= Map("ts_filter_level" -> 99.5)
if (config.contains("hapmap")) resource +:= new TaggedFile(config("hapmap").getString, "known=false,training=true,truth=true,prior=15.0")
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/AddOrReplaceReadGroups.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/AddOrReplaceReadGroups.scala
index 2cd6b073a81e63c444c8e5bad6f8d8525ded12dc..ef76520f8fec26724900aacd39b350e398a368d8 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/AddOrReplaceReadGroups.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/AddOrReplaceReadGroups.scala
@@ -12,37 +12,37 @@ class AddOrReplaceReadGroups(val root: Configurable) extends Picard {
@Output(doc = "The output file to bam file to", required = true)
var output: File = _
-
+
@Output(doc = "The output file to bam file to", required = true)
lazy val outputIndex: File = new File(output.getAbsolutePath.stripSuffix(".bam") + ".bai")
@Argument(doc = "Sort order of output file Required. Possible values: {unsorted, queryname, coordinate} ", required = true)
var sortOrder: String = _
-
+
@Argument(doc = "RGID", required = true)
var RGID: String = _
-
+
@Argument(doc = "RGLB", required = true)
var RGLB: String = _
-
+
@Argument(doc = "RGPL", required = true)
var RGPL: String = _
-
+
@Argument(doc = "RGPU", required = true)
var RGPU: String = _
-
+
@Argument(doc = "RGSM", required = true)
var RGSM: String = _
-
+
@Argument(doc = "RGCN", required = false)
var RGCN: String = _
-
+
@Argument(doc = "RGDS", required = false)
var RGDS: String = _
-
+
@Argument(doc = "RGDT", required = false)
var RGDT: String = _
-
+
@Argument(doc = "RGPI", required = false)
var RGPI: Option[Int] = _
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MergeSamFiles.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MergeSamFiles.scala
index 8d31cfc7b4663730142d403a45929ac3094031c2..d9daa4e25badebfcf53167bf5fb76412b7254308 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MergeSamFiles.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MergeSamFiles.scala
@@ -18,16 +18,16 @@ class MergeSamFiles(val root: Configurable) extends Picard {
@Argument(doc = "ASSUME_SORTED", required = false)
var assumeSorted: Boolean = config("assumesorted", default = false)
-
+
@Argument(doc = "MERGE_SEQUENCE_DICTIONARIES", required = false)
var mergeSequenceDictionaries: Boolean = config("merge_sequence_dictionaries", default = false)
-
+
@Argument(doc = "USE_THREADING", required = false)
var useThreading: Boolean = config("use_threading", default = false)
-
+
@Argument(doc = "COMMENT", required = false)
var comment: String = config("comment")
-
+
override def commandLine = super.commandLine +
repeat("INPUT=", input, spaceSeparated = false) +
required("OUTPUT=", output, spaceSeparated = false) +
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/Picard.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/Picard.scala
index 135ca3b5b56d38931104983452e832022afdb9e6..caf1a3e9c0b52d89f666c32d44c02215613b03ca 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/Picard.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/Picard.scala
@@ -25,9 +25,9 @@ trait Picard extends BiopetJavaCommandLineFunction {
@Argument(doc = "CREATE_MD5_FILE", required = false)
var createMd5: Boolean = config("createmd5", default = false, submodule = "picard")
-// override def versionCommand = executable + " " + javaOpts + " " + javaExecutable + " -h"
-// override val versionRegex = """Version: (.*)""".r
-// override val versionExitcode = List(0, 1)
+ // override def versionCommand = executable + " " + javaOpts + " " + javaExecutable + " -h"
+ // override val versionRegex = """Version: (.*)""".r
+ // override val versionExitcode = List(0, 1)
override val defaultVmem = "8G"
memoryLimit = Option(3.0)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SamToFastq.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SamToFastq.scala
index 5733c8b7331742164e03af896c7045e14948226c..398393f98605cffea9df5804f90d06932080324f 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SamToFastq.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SamToFastq.scala
@@ -12,46 +12,46 @@ class SamToFastq(val root: Configurable) extends Picard {
@Output(doc = "R1", required = true)
var fastqR1: File = _
-
+
@Output(doc = "R1", required = false)
var fastqR2: File = _
-
+
@Output(doc = "Unpaired", required = false)
var fastqUnpaired: File = _
-
+
@Argument(doc = "Output per readgroup", required = false)
var outputPerRg: Boolean = config("outputPerRg", default = false)
-
+
@Argument(doc = "Output dir", required = false)
var outputDir: String = config("outputDir")
-
+
@Argument(doc = "re reverse", required = false)
var reReverse: Boolean = config("reReverse", default = false)
-
+
@Argument(doc = "The output file to bam file to", required = false)
var interleave: Boolean = config("interleave", default = false)
-
+
@Argument(doc = "includeNonPjReads", required = false)
var includeNonPjReads: Boolean = config("includeNonPjReads", default = false)
-
+
@Argument(doc = "clippingAtribute", required = false)
var clippingAtribute: String = config("clippingAtribute")
-
+
@Argument(doc = "clippingAction", required = false)
var clippingAction: String = config("clippingAction")
-
+
@Argument(doc = "read1Trim", required = false)
var read1Trim: Option[Int] = config("read1Trim")
-
+
@Argument(doc = "read1MaxBasesToWrite", required = false)
var read1MaxBasesToWrite: Option[Int] = config("read1MaxBasesToWrite")
-
+
@Argument(doc = "read2Trim", required = false)
var read2Trim: Option[Int] = config("read2Trim")
-
+
@Argument(doc = "read2MaxBasesToWrite", required = false)
var read2MaxBasesToWrite: Option[Int] = config("read2MaxBasesToWrite")
-
+
@Argument(doc = "includeNonPrimaryAlignments", required = false)
var includeNonPrimaryAlignments: Boolean = config("includeNonPrimaryAlignments", default = false)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaFlagstat.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaFlagstat.scala
index 0a250a4893f86d5d1a2b7ee31bb44a9473d32ecf..177d1a6d1c92e2f9d294d6df75b04a005a6f51a7 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaFlagstat.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaFlagstat.scala
@@ -13,12 +13,12 @@ class SambambaFlagstat(val root: Configurable) extends Sambamba {
@Output(doc = "output File")
var output: File = _
- def cmdLine = required(executable) +
- required("flagstat") +
- optional("-t", nCoresRequest) +
- required(input) +
- " > " +
- required(output)
+ def cmdLine = required(executable) +
+ required("flagstat") +
+ optional("-t", nCoresRequest) +
+ required(input) +
+ " > " +
+ required(output)
}
object SambambaFlagstat {
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaIndex.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaIndex.scala
index a0988a8f5d09c8ce5ef5aca7ed50fa4883cdf081..a90ca7a29ccf34c57b6ccf427ad1c52a40c6ed95 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaIndex.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaIndex.scala
@@ -13,11 +13,11 @@ class SambambaIndex(val root: Configurable) extends Sambamba {
@Output(doc = "Output .bai file to")
var output: File = _
- def cmdLine = required(executable) +
- required("index") +
- optional("-t", nCoresRequest) +
- required(input) +
- required(output)
+ def cmdLine = required(executable) +
+ required("index") +
+ optional("-t", nCoresRequest) +
+ required(input) +
+ required(output)
}
object SambambaIndex {
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMarkdup.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMarkdup.scala
index 3ae6939c5184f3f4ee537ef89403bdf856c1c118..5db6f67aa799564522ce907f6ca1c2b980c8c393 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMarkdup.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMarkdup.scala
@@ -13,26 +13,24 @@ class SambambaMarkdup(val root: Configurable) extends Sambamba {
@Output(doc = "Markdup output bam")
var output: File = _
-
var remove_duplicates: Boolean = config("remove_duplicates", default = false)
-
+
// @doc: compression_level 6 is average, 0 = no compression, 9 = best
- val compression_level: Option[Int] = config("compression_level", default=6)
- val hash_table_size: Option[Int] = config("hash-table-size", default=262144)
- val overflow_list_size: Option[Int] = config("overflow-list-size", default=200000)
- val io_buffer_size: Option[Int] = config("io-buffer-size", default=128)
-
-
- def cmdLine = required(executable) +
- required("markdup") +
- conditional(remove_duplicates, "--remove-duplicates") +
- optional("-t", nCoresRequest) +
- optional("-l", compression_level) +
- optional("--hash-table-size=", hash_table_size, spaceSeparated=false ) +
- optional("--overflow-list-size=", overflow_list_size, spaceSeparated=false ) +
- optional("--io-buffer-size=", io_buffer_size, spaceSeparated=false ) +
- required(input) +
- required(output)
+ val compression_level: Option[Int] = config("compression_level", default = 6)
+ val hash_table_size: Option[Int] = config("hash-table-size", default = 262144)
+ val overflow_list_size: Option[Int] = config("overflow-list-size", default = 200000)
+ val io_buffer_size: Option[Int] = config("io-buffer-size", default = 128)
+
+ def cmdLine = required(executable) +
+ required("markdup") +
+ conditional(remove_duplicates, "--remove-duplicates") +
+ optional("-t", nCoresRequest) +
+ optional("-l", compression_level) +
+ optional("--hash-table-size=", hash_table_size, spaceSeparated = false) +
+ optional("--overflow-list-size=", overflow_list_size, spaceSeparated = false) +
+ optional("--io-buffer-size=", io_buffer_size, spaceSeparated = false) +
+ required(input) +
+ required(output)
}
object SambambaMarkdup {
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMerge.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMerge.scala
index 638b6071faa31b692b519ad68f3bc048e79fd76b..57c227bab8fc91fc1031150e9869362889c76b57 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMerge.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/sambamba/SambambaMerge.scala
@@ -14,14 +14,14 @@ class SambambaMerge(val root: Configurable) extends Sambamba {
var output: File = _
// @doc: compression_level 6 is average, 0 = no compression, 9 = best
- val compression_level: Option[Int] = config("compression_level", default=6)
-
- def cmdLine = required(executable) +
- required("merge") +
- optional("-t", nCoresRequest) +
- optional("-l", compression_level) +
- required(output) +
- repeat("", input)
+ val compression_level: Option[Int] = config("compression_level", default = 6)
+
+ def cmdLine = required(executable) +
+ required("merge") +
+ optional("-t", nCoresRequest) +
+ optional("-l", compression_level) +
+ required(output) +
+ repeat("", input)
}
object SambambaMerge {
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsMpileup.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsMpileup.scala
index 739fd0176c2622a52f6524aa8d7c59646e9b3e41..7ce404762cfde868926d565e88081eba060aa905 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsMpileup.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsMpileup.scala
@@ -13,21 +13,21 @@ class SamtoolsMpileup(val root: Configurable) extends Samtools {
@Input(doc = "Reference fasta")
var reference: File = config("reference")
-
+
@Input(doc = "Interval bed")
var intervalBed: File = config("interval_bed")
-
+
var disableBaq: Boolean = config("disable_baq")
var minMapQuality: Option[Int] = config("min_map_quality")
var minBaseQuality: Option[Int] = config("min_base_quality")
-
- def cmdBase = required(executable) +
- required("mpileup") +
- optional("-f", reference) +
- optional("-l", intervalBed) +
- optional("-q", minMapQuality) +
- optional("-Q", minBaseQuality) +
- conditional(disableBaq, "-B")
+
+ def cmdBase = required(executable) +
+ required("mpileup") +
+ optional("-f", reference) +
+ optional("-l", intervalBed) +
+ optional("-q", minMapQuality) +
+ optional("-Q", minBaseQuality) +
+ conditional(disableBaq, "-B")
def cmdPipeInput = cmdBase + "-"
def cmdPipe = cmdBase + required(input)
def cmdLine = cmdPipe + " > " + required(output)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsView.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsView.scala
index d9f1dd2db98028a0e51d71751f722587131ed05b..e2e108de0792897b2caadfb2ac8978c2e3448e03 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsView.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/samtools/SamtoolsView.scala
@@ -10,16 +10,16 @@ class SamtoolsView(val root: Configurable) extends Samtools {
@Output(doc = "output File")
var output: File = _
-
+
var quality: Option[Int] = config("quality")
var b: Boolean = config("b")
var h: Boolean = config("h")
-
- def cmdBase = required(executable) +
- required("view") +
- optional("-q", quality) +
- conditional(b, "-b") +
- conditional(h, "-h")
+
+ def cmdBase = required(executable) +
+ required("view") +
+ optional("-q", quality) +
+ conditional(b, "-b") +
+ conditional(h, "-h")
def cmdPipeInput = cmdBase + "-"
def cmdPipe = cmdBase + required(input)
def cmdLine = cmdPipe + " > " + required(output)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Clever.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Clever.scala
index a46dd1e1abaecd2db7a5b0b368a106b88e19c619..4feeae576607c613c4d22d01036bf51f1d8468c5 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Clever.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/Clever.scala
@@ -1,6 +1,5 @@
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
@@ -9,63 +8,62 @@ 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 {
+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 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 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
+ // 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)
+ " --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 Clever {
@@ -79,47 +77,45 @@ object Clever {
}
}
-
-
class CleverPipeline(val root: Configurable) extends QScript with BiopetQScript {
def this() = this(null)
-
+
@Input(doc = "Input file (bam)")
var input: File = _
@Input(doc = "Reference")
var reference: File = _
-
+
@Argument(doc = "Work directory")
var workdir: String = _
-
+
@Argument(doc = "Current working directory")
var cwd: String = _
-
+
override def init() {
}
def biopetScript() {
// write the pipeline here
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 )
- outputFiles += ("clever_vcf" -> clever.outputvcf )
- add( clever )
+ val clever = Clever(this, input, reference, cwd, workdir)
+ outputFiles += ("clever_vcf" -> clever.outputvcf)
+ add(clever)
}
}
object CleverPipeline 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 )
+ val cleverpipeline = new CleverPipeline(root)
cleverpipeline.input = input
cleverpipeline.workdir = runDir
cleverpipeline.init
cleverpipeline.biopetScript
return cleverpipeline
}
-
+
}
\ No newline at end of file
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/Pindel.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/Pindel.scala
index 20d7c5f4660c8291218447338fa3b5386ed0e828..3fb73023bc7ffeec9330e6aadf06838e2d483886 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/Pindel.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/Pindel.scala
@@ -1,6 +1,5 @@
package nl.lumc.sasc.biopet.extensions.svcallers.pindel
-
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import org.broadinstitute.gatk.queue.QScript
import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
@@ -13,21 +12,21 @@ import java.io.File
/// Pindel is actually a mini pipeline executing binaries from the pindel package
class Pindel(val root: Configurable) extends QScript with BiopetQScript {
def this() = this(null)
-
+
@Input(doc = "Input file (bam)")
var input: File = _
@Input(doc = "Reference Fasta file")
var reference: File = _
-
+
@Argument(doc = "Work directory")
var workdir: String = _
-
-// @Output(doc = "Pindel VCF output")
-// lazy val outputvcf: File = {
-// new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.vcf")
-// }
-
+
+ // @Output(doc = "Pindel VCF output")
+ // lazy val outputvcf: File = {
+ // new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.vcf")
+ // }
+
@Output(doc = "Pindel config")
lazy val configfile: File = {
new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.cfg")
@@ -36,34 +35,33 @@ class Pindel(val root: Configurable) extends QScript with BiopetQScript {
lazy val outputvcf: File = {
new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.vcf")
}
-
+
override def init() {
}
def biopetScript() {
// read config and set all parameters for the pipeline
logger.info("Starting Pindel configuration")
-
+
val cfg = PindelConfig(this, input, this.configfile)
- outputFiles += ("pindel_cfg" -> cfg.output )
- add( cfg )
-
+ outputFiles += ("pindel_cfg" -> cfg.output)
+ add(cfg)
+
val output: File = this.outputvcf
- val pindel = PindelCaller( this, cfg.output, output )
- add( pindel )
- outputFiles += ("pindel_tsv" -> pindel.output )
+ val pindel = PindelCaller(this, cfg.output, output)
+ add(pindel)
+ outputFiles += ("pindel_tsv" -> pindel.output)
-// val output_vcf: File = this.outputvcf
+ // val output_vcf: File = this.outputvcf
// convert this tsv to vcf using the python script
-
-
+
}
-
-// private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".pindel.tsv"
+
+ // private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".pindel.tsv"
}
object Pindel extends PipelineCommand {
- def apply(root: Configurable, input: File, reference: File, runDir: String): Pindel = {
+ def apply(root: Configurable, input: File, reference: File, runDir: String): Pindel = {
val pindel = new Pindel(root)
pindel.input = input
pindel.reference = reference
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelCaller.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelCaller.scala
index 69bd555e956df2c269ea516a636024f8f145f7ca..cdf3b88038f7151b8f47ddd9a0c9046a9ff62305 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelCaller.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelCaller.scala
@@ -21,19 +21,19 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
import java.io.File
-class PindelCaller(val root: Configurable) extends BiopetCommandLineFunction {
+class PindelCaller(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "pindel", freeVar = false)
-
+
override val defaultVmem = "8G"
override val defaultThreads = 8
-
+
override val versionRegex = """Pindel version:? (.*)""".r
override val versionExitcode = List(1)
override def versionCommand = executable
-
+
@Input(doc = "The pindel configuration file")
var input: File = _
-
+
@Input(doc = "Fasta reference")
var reference: File = config("reference")
@@ -45,21 +45,21 @@ class PindelCaller(val root: Configurable) extends BiopetCommandLineFunction {
// <prefix>_TR
@Argument(doc = "Work directory")
var workdir: String = _
-
+
@Output(doc = "Pindel VCF output")
var output: File = _
-
+
var window_size: Option[Int] = config("window_size", default = 5)
-
+
override def beforeCmd {
}
- def cmdLine = required(executable) +
- "-i " + required(input) +
- "-f " + required(reference) +
- "-o " + required(output) +
- optional("-w", window_size) +
- optional("-T", nCoresRequest)
+ def cmdLine = required(executable) +
+ "-i " + required(input) +
+ "-f " + required(reference) +
+ "-o " + required(output) +
+ optional("-w", window_size) +
+ optional("-T", nCoresRequest)
}
object PindelCaller {
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelConfig.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelConfig.scala
index 850b9adaa200f028bfeede7587b697400f0fca5e..ad64a2fabf02023ffceea7531f4cafffd85ed0db 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelConfig.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/svcallers/pindel/PindelConfig.scala
@@ -23,7 +23,6 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
import java.io.File
-
class PindelConfig(val root: Configurable) extends BiopetJavaCommandLineFunction {
javaMainClass = getClass.getName
@Input(doc = "Bam File")
@@ -31,13 +30,13 @@ class PindelConfig(val root: Configurable) extends BiopetJavaCommandLineFunction
@Output(doc = "Output Config file")
var output: File = _
-
- @Argument(doc="Insertsize")
+
+ @Argument(doc = "Insertsize")
var insertsize: Option[Int] = _
-
- override def commandLine = super.commandLine +
- "-i" + required(input) +
- "-s" + required(insertsize) +
+
+ override def commandLine = super.commandLine +
+ "-i" + required(input) +
+ "-s" + required(insertsize) +
"-o" + required(output)
}
@@ -60,28 +59,30 @@ object PindelConfig extends ToolCommand {
}
private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".pindel.cfg"
-
- case class Args (inputbam:File = null, samplelabel:Option[String] = None, insertsize:Option[Int] = None) extends AbstractArgs
+
+ case class Args(inputbam: File = null, samplelabel: Option[String] = None, insertsize: Option[Int] = None) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('i', "inputbam") required() valueName("<bamfile/path>") action { (x, c) =>
- c.copy(inputbam = x) } text("Please specify the input bam file")
- opt[String]('l', "samplelabel") valueName("<sample label>") action { (x, c) =>
- c.copy(samplelabel = Some(x)) } text("Sample label is missing")
- opt[Int]('s', "insertsize") valueName("<insertsize>") action { (x, c) =>
- c.copy(insertsize = Some(x)) } text("Insertsize is missing")
+ opt[File]('i', "inputbam") required () valueName ("<bamfile/path>") action { (x, c) =>
+ c.copy(inputbam = x)
+ } text ("Please specify the input bam file")
+ opt[String]('l', "samplelabel") valueName ("<sample label>") action { (x, c) =>
+ c.copy(samplelabel = Some(x))
+ } text ("Sample label is missing")
+ opt[Int]('s', "insertsize") valueName ("<insertsize>") action { (x, c) =>
+ c.copy(insertsize = Some(x))
+ } text ("Insertsize is missing")
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
val input: File = commandArgs.inputbam
}
}
-
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala
index 2d36a805816402ea8157806718641bd1d3e78c41..93539997e35e4c31bef7acc6e82c3abe7fcd79b6 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/basty/Basty.scala
@@ -6,51 +6,51 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.pipelines.gatk.GatkPipeline
import org.broadinstitute.gatk.queue.QScript
-class Basty (val root: Configurable) extends QScript with MultiSampleQScript {
+class Basty(val root: Configurable) extends QScript with MultiSampleQScript {
def this() = this(null)
-
+
class LibraryOutput extends AbstractLibraryOutput {
}
-
+
class SampleOutput extends AbstractSampleOutput {
}
-
+
defaults ++= Map("ploidy" -> 1, "use_haplotypecaller" -> false, "use_unifiedgenotyper" -> true)
-
+
var gatkPipeline: GatkPipeline = _
-
+
def init() {
gatkPipeline = new GatkPipeline(this)
gatkPipeline.outputDir = outputDir
gatkPipeline.init
}
-
+
def biopetScript() {
gatkPipeline.biopetScript
addAll(gatkPipeline.functions)
-
+
runSamplesJobs()
}
-
+
// Called for each sample
def runSingleSampleJobs(sampleConfig: Map[String, Any]): SampleOutput = {
val sampleOutput = new SampleOutput
val sampleID: String = sampleConfig("ID").toString
val sampleDir = globalSampleDir + sampleID
-
+
sampleOutput.libraries = runLibraryJobs(sampleConfig)
-
+
return sampleOutput
}
-
+
// Called for each run from a sample
def runSingleLibraryJobs(runConfig: Map[String, Any], sampleConfig: Map[String, Any]): LibraryOutput = {
val libraryOutput = new LibraryOutput
-
+
val runID: String = runConfig("ID").toString
val sampleID: String = sampleConfig("ID").toString
val runDir: String = globalSampleDir + sampleID + "/run_" + runID + "/"
-
+
return libraryOutput
}
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala
index 268586ab64a5ec1f0f7597407057dbbca0f36356..9c549e4b8db6e991917e9deca8659d10f3f86e8f 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Cutadapt.scala
@@ -15,12 +15,12 @@ import scala.collection.mutable.Map
class Cutadapt(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Cutadapt(root) {
@Input(doc = "Fastq contams file", required = false)
var contams_file: File = _
-
+
override def beforeCmd() {
super.beforeCmd
getContamsFromFile
}
-
+
override def cmdLine = {
if (!opt_adapter.isEmpty || !opt_anywhere.isEmpty || !opt_front.isEmpty) {
analysisName = getClass.getSimpleName
@@ -30,7 +30,7 @@ class Cutadapt(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Cutada
Ln(this, fastq_input, fastq_output, relative = true).cmd
}
}
-
+
def getContamsFromFile {
if (contams_file != null) {
if (contams_file.exists()) {
@@ -48,23 +48,23 @@ class Cutadapt(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Cutada
} else logger.warn("File : " + contams_file + " does not exist")
}
}
-
+
def getSummary: Json = {
val trimR = """.*Trimmed reads: *(\d*) .*""".r
val tooShortR = """.*Too short reads: *(\d*) .*""".r
val tooLongR = """.*Too long reads: *(\d*) .*""".r
val adapterR = """Adapter '([C|T|A|G]*)'.*trimmed (\d*) times.""".r
-
+
var stats: Map[String, Int] = Map("trimmed" -> 0, "tooshort" -> 0, "toolong" -> 0)
var adapter_stats: Map[String, Int] = Map()
-
+
if (stats_output.exists) for (line <- Source.fromFile(stats_output).getLines) {
line match {
- case trimR(m) => stats += ("trimmed" -> m.toInt)
- case tooShortR(m) => stats += ("tooshort" -> m.toInt)
- case tooLongR(m) => stats += ("toolong" -> m.toInt)
- case adapterR(adapter, count) => adapter_stats += (adapter -> count.toInt)
- case _ =>
+ case trimR(m) => stats += ("trimmed" -> m.toInt)
+ case tooShortR(m) => stats += ("tooshort" -> m.toInt)
+ case tooLongR(m) => stats += ("toolong" -> m.toInt)
+ case adapterR(adapter, count) => adapter_stats += (adapter -> count.toInt)
+ case _ =>
}
}
return ("num_reads_affected" := stats("trimmed")) ->:
@@ -76,25 +76,25 @@ class Cutadapt(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Cutada
}
object Cutadapt {
- def apply(root: Configurable, input:File, output:File): Cutadapt = {
+ def apply(root: Configurable, input: File, output: File): Cutadapt = {
val cutadapt = new Cutadapt(root)
cutadapt.fastq_input = input
cutadapt.fastq_output = output
cutadapt.stats_output = new File(output.getAbsolutePath.substring(0, output.getAbsolutePath.lastIndexOf(".")) + ".stats")
return cutadapt
}
-
+
def mergeSummaries(jsons: List[Json]): Json = {
var affected = 0
var tooShort = 0
var tooLong = 0
var adapter_stats: Map[String, Int] = Map()
-
+
for (json <- jsons) {
affected += json.field("num_reads_affected").get.numberOrZero.toInt
tooShort += json.field("num_reads_discarded_too_short").get.numberOrZero.toInt
tooLong += json.field("num_reads_discarded_too_long").get.numberOrZero.toInt
-
+
val adapters = json.fieldOrEmptyObject("adapters")
for (key <- adapters.objectFieldsOrEmpty) {
val number = adapters.field(key).get.numberOrZero.toInt
@@ -102,7 +102,7 @@ object Cutadapt {
else adapter_stats += (key -> number)
}
}
-
+
return ("num_reads_affected" := affected) ->:
("num_reads_discarded_too_short" := tooShort) ->:
("num_reads_discarded_too_long" := tooLong) ->:
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Fastqc.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Fastqc.scala
index 970932940cf873b3ac7c75e4a94fed4c0dcd3e97..de042f1e4fd49786f31919b092f21aa48ca34a3f 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Fastqc.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Fastqc.scala
@@ -49,8 +49,8 @@ class Fastqc(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Fastqc(r
"plot_sequence_length_distribution" -> "Images/sequence_length_distribution.png",
"fastqc_data" -> "fastqc_data.txt")
val dir = output.getAbsolutePath.stripSuffix(".zip") + "/"
- var outputMap:Map[String,Map[String,String]] = Map()
- for ((k,v) <- subfixs) outputMap += (k -> Map("path" -> (dir+v)))
+ var outputMap: Map[String, Map[String, String]] = Map()
+ for ((k, v) <- subfixs) outputMap += (k -> Map("path" -> (dir + v)))
val temp = ("" := outputMap) ->: jEmptyObject
return temp.fieldOrEmptyObject("")
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 5d65b7f01191a1911f5a3b8d750dadb746a13310..b0366e5f5bcf0036ed5e64c8ee5c7f3dcb87c8ef 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
@@ -6,7 +6,7 @@ import org.broadinstitute.gatk.utils.commandline.{ Input, Argument }
import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.extensions.{ Gzip, Pbzip2, Md5sum, Zcat, Seqstat }
-import nl.lumc.sasc.biopet.scripts.{ FastqSync , FastqcToContams}
+import nl.lumc.sasc.biopet.scripts.{ FastqSync, FastqcToContams }
class Flexiprep(val root: Configurable) extends QScript with BiopetQScript {
def this() = this(null)
@@ -74,10 +74,10 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript {
runInitialJobs()
val out = if (paired) runTrimClip(outputFiles("fastq_input_R1"), outputFiles("fastq_input_R2"), outputDir)
- else runTrimClip(outputFiles("fastq_input_R1"), outputDir)
-
- val R1_files = for ((k,v) <- outputFiles if k.endsWith("output_R1")) yield v
- val R2_files = for ((k,v) <- outputFiles if k.endsWith("output_R2")) yield v
+ else runTrimClip(outputFiles("fastq_input_R1"), outputDir)
+
+ val R1_files = for ((k, v) <- outputFiles if k.endsWith("output_R1")) yield v
+ val R2_files = for ((k, v) <- outputFiles if k.endsWith("output_R2")) yield v
runFinalize(R1_files.toList, R2_files.toList)
}
@@ -133,19 +133,19 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript {
var R1: File = new File(R1_in)
var R2: File = new File(R2_in)
var deps: List[File] = if (paired) List(R1, R2) else List(R1)
-
+
val seqtkSeq_R1 = SeqtkSeq.apply(this, R1, swapExt(outDir, R1, R1_ext, ".sanger" + R1_ext), fastqc_R1)
add(seqtkSeq_R1, isIntermediate = true)
R1 = seqtkSeq_R1.output
deps ::= R1
-
+
if (paired) {
val seqtkSeq_R2 = SeqtkSeq.apply(this, R2, swapExt(outDir, R2, R2_ext, ".sanger" + R2_ext), fastqc_R2)
add(seqtkSeq_R2, isIntermediate = true)
R2 = seqtkSeq_R2.output
deps ::= R2
}
-
+
val seqstat_R1 = Seqstat(this, R1, outDir)
add(seqstat_R1, isIntermediate = true)
summary.addSeqstat(seqstat_R1, R2 = false, after = false, chunk)
@@ -155,7 +155,7 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript {
add(seqstat_R2, isIntermediate = true)
summary.addSeqstat(seqstat_R2, R2 = true, after = false, chunk)
}
-
+
if (!skipClip) { // Adapter clipping
val cutadapt_R1 = Cutadapt(this, R1, swapExt(outDir, R1, R1_ext, ".clip" + R1_ext))
@@ -174,9 +174,9 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript {
summary.addCutadapt(cutadapt_R2, R2 = true, chunk)
R2 = cutadapt_R2.fastq_output
deps ::= R2
-
- val fastqSync = FastqSync(this, cutadapt_R1.fastq_input, cutadapt_R1.fastq_output, cutadapt_R2.fastq_output,
- swapExt(outDir, R1, R1_ext, ".sync" + R1_ext), swapExt(outDir, R2, R2_ext, ".sync" + R2_ext), swapExt(outDir, R1, R1_ext, ".sync.stats"))
+
+ val fastqSync = FastqSync(this, cutadapt_R1.fastq_input, cutadapt_R1.fastq_output, cutadapt_R2.fastq_output,
+ swapExt(outDir, R1, R1_ext, ".sync" + R1_ext), swapExt(outDir, R2, R2_ext, ".sync" + R2_ext), swapExt(outDir, R1, R1_ext, ".sync.stats"))
fastqSync.deps :::= deps
add(fastqSync, isIntermediate = true)
summary.addFastqcSync(fastqSync, chunk)
@@ -225,7 +225,7 @@ class Flexiprep(val root: Configurable) extends QScript with BiopetQScript {
if (fastq_R1.length != fastq_R2.length && paired) throw new IllegalStateException("R1 and R2 file number is not the same")
val R1 = new File(outputDir + R1_name + ".qc" + R1_ext + ".gz")
val R2 = new File(outputDir + R2_name + ".qc" + R2_ext + ".gz")
-
+
add(Gzip(this, fastq_R1, R1))
if (paired) add(Gzip(this, fastq_R2, R2))
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/FlexiprepSummary.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/FlexiprepSummary.scala
index 7a93d9022776f2d5083e9987329f2f711ec584d7..188bcb6bd96d29b8022a6ba6e54e789a6ee0ca07 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/FlexiprepSummary.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/FlexiprepSummary.scala
@@ -48,8 +48,8 @@ class FlexiprepSummary(val root: Configurable) extends InProcessFunction with Co
var flexiprep: Flexiprep = if (root.isInstanceOf[Flexiprep]) root.asInstanceOf[Flexiprep] else {
throw new IllegalStateException("Root is no instance of Flexiprep")
}
-
- var resources:Map[String, Json] = Map()
+
+ var resources: Map[String, Json] = Map()
def addFastqc(fastqc: Fastqc, R2: Boolean = false, after: Boolean = false): Fastqc = {
if (!R2 && !after) this.fastqcR1 = fastqc
@@ -135,7 +135,7 @@ class FlexiprepSummary(val root: Configurable) extends InProcessFunction with Co
def seqstatSummary(): Option[Json] = {
val R1_chunks = for ((key, value) <- chunks) yield value.seqstatR1.getSummary
val R1: Json = Seqstat.mergeSummaries(R1_chunks.toList)
-
+
val R2: Option[Json] = if (!flexiprep.paired) None
else if (chunks.size == 1) Option(chunks.head._2.seqstatR2.getSummary)
else {
@@ -166,7 +166,7 @@ class FlexiprepSummary(val root: Configurable) extends InProcessFunction with Co
val R2_raw = md5Summary(md5R2)
val R1_proc = md5Summary(md5R1after)
val R2_proc = md5Summary(md5R2after)
-
+
if (!R1_raw.isEmpty) resources += ("fastq_R1_raw" -> R1_raw.get)
if (!R2_raw.isEmpty) resources += ("fastq_R2_raw" -> R2_raw.get)
if (!R1_proc.isEmpty) resources += ("fastq_R1_proc" -> R1_proc.get)
@@ -178,12 +178,12 @@ class FlexiprepSummary(val root: Configurable) extends InProcessFunction with Co
else return Option(md5sum.getSummary)
}
- def getResources(fastqc:Fastqc, md5sum:Md5sum): Option[Json] = {
+ def getResources(fastqc: Fastqc, md5sum: Md5sum): Option[Json] = {
if (fastqc == null || md5sum == null) return None
val fastqcSum = fastqcSummary(fastqc).get
return Option(("fastq" := md5Summary(md5sum)) ->: fastqcSum)
}
-
+
def fastqcSummary(fastqc: Fastqc): Option[Json] = {
if (fastqc == null) return None
else return Option(fastqc.getSummary)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/SeqtkSeq.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/SeqtkSeq.scala
index 70c4a5dc5c53c7fad7d95111935cf837aab54409..cb4a05e60615f5d180074578469b92b49b18f28e 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/SeqtkSeq.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/SeqtkSeq.scala
@@ -12,20 +12,20 @@ class SeqtkSeq(root: Configurable) extends nl.lumc.sasc.biopet.extensions.seqtk.
if (fastqc != null && Q == None) {
val encoding = fastqc.getEncoding
Q = encoding match {
- case null => None
+ case null => None
case s if (s.contains("Sanger / Illumina 1.9")) => None
- case s if (s.contains("Illumina <1.3")) => Option(64)
- case s if (s.contains("Illumina 1.3")) => Option(64)
- case s if (s.contains("Illumina 1.5")) => Option(64)
+ case s if (s.contains("Illumina <1.3")) => Option(64)
+ case s if (s.contains("Illumina 1.3")) => Option(64)
+ case s if (s.contains("Illumina 1.5")) => Option(64)
}
if (Q != None) V = true
}
}
-
+
override def afterGraph {
if (fastqc != null) deps ::= fastqc.output
}
-
+
override def cmdLine = {
if (Q != None) {
analysisName = getClass.getSimpleName
@@ -38,7 +38,7 @@ class SeqtkSeq(root: Configurable) extends nl.lumc.sasc.biopet.extensions.seqtk.
}
object SeqtkSeq {
- def apply(root: Configurable, input:File, output:File, fastqc:Fastqc = null): SeqtkSeq = {
+ def apply(root: Configurable, input: File, output: File, fastqc: Fastqc = null): SeqtkSeq = {
val seqtkSeq = new SeqtkSeq(root)
seqtkSeq.input = input
seqtkSeq.output = output
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Sickle.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Sickle.scala
index 74cdaacab38008a91bf4e064356403731874e316..f255bad4078ef67fbe7bfd999a7d30e186a3ce67 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Sickle.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/flexiprep/Sickle.scala
@@ -14,25 +14,25 @@ class Sickle(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Sickle(r
val singleKept = """FastQ single records kept: (\d*) \(from PE1: (\d*), from PE2: (\d*)\)""".r
val pairDiscarded = """FastQ paired records discarded: (\d*) \((\d*) pairs\)""".r
val singleDiscarded = """FastQ single records discarded: (\d*) \(from PE1: (\d*), from PE2: (\d*)\)""".r
-
- var stats:Map[String, Int] = Map()
-
+
+ var stats: Map[String, Int] = Map()
+
if (output_stats.exists) for (line <- Source.fromFile(output_stats).getLines) {
line match {
case pairKept(reads, pairs) => stats += ("num_paired_reads_kept" -> reads.toInt)
case singleKept(total, r1, r2) => {
- stats += ("num_reads_kept_R1" -> r1.toInt)
- stats += ("num_reads_kept_R2" -> r2.toInt)
+ stats += ("num_reads_kept_R1" -> r1.toInt)
+ stats += ("num_reads_kept_R2" -> r2.toInt)
}
case pairDiscarded(reads, pairs) => stats += ("num_paired_reads_discarded" -> reads.toInt)
case singleDiscarded(total, r1, r2) => {
- stats += ("num_reads_discarded_R1" -> r1.toInt)
- stats += ("num_reads_discarded_R2" -> r2.toInt)
+ stats += ("num_reads_discarded_R1" -> r1.toInt)
+ stats += ("num_reads_discarded_R2" -> r2.toInt)
}
- case _ =>
+ case _ =>
}
}
-
+
val temp = ("" := stats.toMap) ->: jEmptyObject
return temp.fieldOrEmptyObject("")
}
@@ -41,7 +41,7 @@ class Sickle(root: Configurable) extends nl.lumc.sasc.biopet.extensions.Sickle(r
object Sickle {
def mergeSummaries(jsons: List[Json]): Json = {
var total: Map[String, Int] = Map()
-
+
for (json <- jsons) {
for (key <- json.objectFieldsOrEmpty) {
if (json.field(key).get.isNumber) {
@@ -51,7 +51,7 @@ object Sickle {
}
}
}
-
+
val temp = ("" := total.toMap) ->: jEmptyObject
return temp.fieldOrEmptyObject("")
}
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 9cd93a32dc2f0663bcedf50ebb40e53945458765..623dc8c9a783bf33360d9a4654c16f056e9f0ab7 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
@@ -16,7 +16,7 @@ import org.broadinstitute.gatk.utils.commandline.{ Argument }
class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScript {
def this() = this(null)
-
+
@Argument(doc = "Only Sample", shortName = "sample", required = false)
val onlySample: String = ""
@@ -28,10 +28,10 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
@Argument(doc = "Joint variantcalling", shortName = "jointVariantCalling", required = false)
var jointVariantcalling = false
-
+
@Argument(doc = "Joint genotyping", shortName = "jointGenotyping", required = false)
var jointGenotyping = false
-
+
var singleSampleCalling = true
var reference: File = _
var dbsnp: File = _
@@ -43,11 +43,11 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
var mappedBamFile: File = _
var variantcalling: GatkVariantcalling.ScriptOutput = _
}
-
+
class SampleOutput extends AbstractSampleOutput {
var variantcalling: GatkVariantcalling.ScriptOutput = _
}
-
+
def init() {
useAllelesOption = config("use_alleles_option", default = false)
reference = config("reference", required = true)
@@ -68,7 +68,7 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
def biopetScript() {
if (onlySample.isEmpty) {
runSamplesJobs
-
+
//SampleWide jobs
if (mergeGvcfs && gvcfFiles.size > 0) {
val newFile = outputDir + "merged.gvcf.vcf.gz"
@@ -87,18 +87,20 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
var vcfFile = gatkGenotyping.outputFile
}
} else logger.warn("No gVCFs to genotype")
-
+
if (jointVariantcalling) {
- val allBamfiles = for ((sampleID,sampleOutput) <- samplesOutput;
- file <- sampleOutput.variantcalling.bamFiles) yield file
- val allRawVcfFiles = for ((sampleID,sampleOutput) <- samplesOutput) yield sampleOutput.variantcalling.rawFilterVcfFile
-
+ val allBamfiles = for (
+ (sampleID, sampleOutput) <- samplesOutput;
+ file <- sampleOutput.variantcalling.bamFiles
+ ) yield file
+ val allRawVcfFiles = for ((sampleID, sampleOutput) <- samplesOutput) yield sampleOutput.variantcalling.rawFilterVcfFile
+
val cvRaw = CombineVariants(this, allRawVcfFiles.toList, outputDir + "variantcalling/multisample.raw.vcf.gz")
add(cvRaw)
-
+
val gatkVariantcalling = new GatkVariantcalling(this) {
override protected lazy val configName = "gatkvariantcalling"
- override def configPath: List[String] = "multisample" :: super.configPath
+ override def configPath: List[String] = "multisample" :: super.configPath
}
gatkVariantcalling.preProcesBams = Some(false)
gatkVariantcalling.doublePreProces = Some(false)
@@ -109,7 +111,7 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
gatkVariantcalling.init
gatkVariantcalling.biopetScript
addAll(gatkVariantcalling.functions)
-
+
if (config("inputtype", default = "dna").getString != "rna" && config("recalibration", default = false).getBoolean) {
val recalibration = new GatkVariantRecalibration(this)
recalibration.inputVcf = gatkVariantcalling.scriptOutput.finalVcfFile
@@ -169,10 +171,10 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
} else if (runConfig.contains("bam")) {
var bamFile = new File(runConfig("bam").toString)
if (!bamFile.exists) throw new IllegalStateException("Bam in config does not exist, file: " + bamFile)
-
+
if (config("bam_to_fastq", default = false).getBoolean) {
- val samToFastq = SamToFastq(this, bamFile, runDir + sampleID + "-" + runID + ".R1.fastq",
- runDir + sampleID + "-" + runID + ".R2.fastq")
+ val samToFastq = SamToFastq(this, bamFile, runDir + sampleID + "-" + runID + ".R1.fastq",
+ runDir + sampleID + "-" + runID + ".R2.fastq")
add(samToFastq, isIntermediate = true)
val mapping = Mapping.loadFromLibraryConfig(this, runConfig, sampleConfig, runDir, startJobs = false)
mapping.input_R1 = samToFastq.fastqR1
@@ -206,15 +208,15 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
if (runConfig.contains("CN")) aorrg.RGCN = runConfig("CN").toString
add(aorrg, isIntermediate = true)
bamFile = aorrg.output
- } else throw new IllegalStateException("Readgroup sample and/or library of input bamfile is not correct, file: " + bamFile +
- "\nPossible to set 'correct_readgroups' to true on config to automatic fix this")
+ } else throw new IllegalStateException("Readgroup sample and/or library of input bamfile is not correct, file: " + bamFile +
+ "\nPossible to set 'correct_readgroups' to true on config to automatic fix this")
}
addAll(BamMetrics(this, bamFile, runDir + "metrics/").functions)
libraryOutput.mappedBamFile = bamFile
}
} else logger.error("Sample: " + sampleID + ": No R1 found for run: " + runConfig)
-
+
val gatkVariantcalling = new GatkVariantcalling(this)
gatkVariantcalling.inputBams = List(libraryOutput.mappedBamFile)
gatkVariantcalling.outputDir = runDir
@@ -225,7 +227,7 @@ class GatkPipeline(val root: Configurable) extends QScript with MultiSampleQScri
gatkVariantcalling.biopetScript
addAll(gatkVariantcalling.functions)
libraryOutput.variantcalling = gatkVariantcalling.scriptOutput
-
+
return libraryOutput
}
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala
index 8e6a07887c89e262c749bb7cc53faa7bb47e7b16..d5dcdb9f2289b19e1835c828be988ed57d6cfe04 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/GatkVariantRecalibration.scala
@@ -10,36 +10,36 @@ import org.broadinstitute.gatk.queue.QScript
class GatkVariantRecalibration(val root: Configurable) extends QScript with BiopetQScript {
def this() = this(null)
-
+
@Input(doc = "input vcf file", shortName = "I")
var inputVcf: File = _
-
+
@Input(doc = "input vcf file", shortName = "BAM", required = false)
var bamFiles: List[File] = Nil
-
+
@Output(doc = "output vcf file", shortName = "out")
var outputVcf: File = _
-
+
def init() {
if (inputVcf == null) throw new IllegalStateException("Missing Output directory on gatk module")
if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
else if (!outputDir.endsWith("/")) outputDir += "/"
}
-
+
def biopetScript() {
var vcfFile: File = if (!bamFiles.isEmpty) addVariantAnnotator(inputVcf, bamFiles, outputDir) else inputVcf
vcfFile = addSnpVariantRecalibrator(vcfFile, outputDir)
vcfFile = addIndelVariantRecalibrator(vcfFile, outputDir)
}
-
+
def addSnpVariantRecalibrator(inputVcf: File, dir: String): File = {
- val snpRecal = VariantRecalibrator(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal"),
- swapExt(dir, inputVcf, ".vcf", ".indel.tranches"), indel = false)
+ val snpRecal = VariantRecalibrator(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal"),
+ swapExt(dir, inputVcf, ".vcf", ".indel.tranches"), indel = false)
if (!snpRecal.resource.isEmpty) {
add(snpRecal)
- val snpApply = ApplyRecalibration(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal.vcf"),
- snpRecal.recal_file, snpRecal.tranches_file, indel = false)
+ val snpApply = ApplyRecalibration(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal.vcf"),
+ snpRecal.recal_file, snpRecal.tranches_file, indel = false)
add(snpApply)
return snpApply.out
@@ -50,13 +50,13 @@ class GatkVariantRecalibration(val root: Configurable) extends QScript with Biop
}
def addIndelVariantRecalibrator(inputVcf: File, dir: String): File = {
- val indelRecal = VariantRecalibrator(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal"),
- swapExt(dir, inputVcf, ".vcf", ".indel.tranches"), indel = true)
+ val indelRecal = VariantRecalibrator(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal"),
+ swapExt(dir, inputVcf, ".vcf", ".indel.tranches"), indel = true)
if (!indelRecal.resource.isEmpty) {
add(indelRecal)
-
- val indelApply = ApplyRecalibration(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal.vcf"),
- indelRecal.recal_file, indelRecal.tranches_file, indel = true)
+
+ val indelApply = ApplyRecalibration(this, inputVcf, swapExt(dir, inputVcf, ".vcf", ".indel.recal.vcf"),
+ indelRecal.recal_file, indelRecal.tranches_file, indel = true)
add(indelApply)
return indelApply.out
@@ -67,7 +67,7 @@ class GatkVariantRecalibration(val root: Configurable) extends QScript with Biop
}
def addVariantAnnotator(inputvcf: File, bamfiles: List[File], dir: String): File = {
- val variantAnnotator = VariantAnnotator(this, inputvcf, bamfiles, swapExt(dir, inputvcf, ".vcf", ".anotated.vcf"))
+ val variantAnnotator = VariantAnnotator(this, inputvcf, bamfiles, swapExt(dir, inputvcf, ".vcf", ".anotated.vcf"))
add(variantAnnotator)
return variantAnnotator.out
}
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 bf63aaaf4341ded9f33efe100ad0da1c04dfc0fd..c39a2fc85531cac296f4f77cb39ecb0495d57f55 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
@@ -1,10 +1,10 @@
package nl.lumc.sasc.biopet.pipelines.gatk
-import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand}
+import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
import java.io.File
import nl.lumc.sasc.biopet.tools.{ MpileupToVcf, VcfFilter }
import nl.lumc.sasc.biopet.core.config.Configurable
-import nl.lumc.sasc.biopet.extensions.gatk.{AnalyzeCovariates,BaseRecalibrator,GenotypeGVCFs,HaplotypeCaller,IndelRealigner,PrintReads,RealignerTargetCreator, SelectVariants, CombineVariants, UnifiedGenotyper}
+import nl.lumc.sasc.biopet.extensions.gatk.{ AnalyzeCovariates, BaseRecalibrator, GenotypeGVCFs, HaplotypeCaller, IndelRealigner, PrintReads, RealignerTargetCreator, SelectVariants, CombineVariants, UnifiedGenotyper }
import nl.lumc.sasc.biopet.extensions.picard.MarkDuplicates
import org.broadinstitute.gatk.queue.QScript
import org.broadinstitute.gatk.queue.extensions.gatk.TaggedFile
@@ -15,10 +15,10 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
def this() = this(null)
val scriptOutput = new GatkVariantcalling.ScriptOutput
-
+
@Input(doc = "Bam files (should be deduped bams)", shortName = "BAM")
var inputBams: List[File] = Nil
-
+
@Input(doc = "Raw vcf file", shortName = "raw")
var rawVcfInput: File = _
@@ -33,7 +33,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
@Argument(doc = "Sample name", required = false)
var sampleID: String = _
-
+
var preProcesBams: Option[Boolean] = None
var variantcalling: Boolean = true
var doublePreProces: Option[Boolean] = None
@@ -55,20 +55,20 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
else if (!outputDir.endsWith("/")) outputDir += "/"
}
- private def doublePreProces(files:List[File]): List[File] = {
- if (files.size == 1) return files
- if (files.isEmpty) throw new IllegalStateException("Files can't be empty")
- if (!doublePreProces.get) return files
- val markDub = MarkDuplicates(this, files, new File(outputDir + outputName + ".dedup.bam"))
- if (dbsnp != null) {
- add(markDub, isIntermediate = true)
- List(addIndelRealign(markDub.output, outputDir, isIntermediate = false))
- } else {
- add(markDub, isIntermediate = true)
- List(markDub.output)
- }
+ private def doublePreProces(files: List[File]): List[File] = {
+ if (files.size == 1) return files
+ if (files.isEmpty) throw new IllegalStateException("Files can't be empty")
+ if (!doublePreProces.get) return files
+ val markDub = MarkDuplicates(this, files, new File(outputDir + outputName + ".dedup.bam"))
+ if (dbsnp != null) {
+ add(markDub, isIntermediate = true)
+ List(addIndelRealign(markDub.output, outputDir, isIntermediate = false))
+ } else {
+ add(markDub, isIntermediate = true)
+ List(markDub.output)
}
-
+ }
+
def biopetScript() {
scriptOutput.bamFiles = if (preProcesBams.get) {
var bamFiles: List[File] = Nil
@@ -80,10 +80,10 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
} else if (inputBams.size > 1 && doublePreProces.get) {
doublePreProces(inputBams)
} else inputBams
-
+
if (variantcalling) {
var mergBuffer: SortedMap[String, File] = SortedMap()
-
+
if (sampleID != null && (useHaplotypecaller.get || config("joint_genotyping", default = false).getBoolean)) {
val hcGvcf = new HaplotypeCaller(this)
hcGvcf.useGvcf
@@ -92,7 +92,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
add(hcGvcf)
scriptOutput.gvcfFile = hcGvcf.out
}
-
+
if (useHaplotypecaller.get) {
if (sampleID != null) {
val genotypeGVCFs = GenotypeGVCFs(this, List(scriptOutput.gvcfFile), outputDir + outputName + ".hc.discovery.vcf.gz")
@@ -107,7 +107,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
}
mergBuffer += ("1.HC-Discovery" -> scriptOutput.hcVcfFile)
}
-
+
if (useUnifiedGenotyper.get) {
val ugVcf = new UnifiedGenotyper(this)
ugVcf.input_file = scriptOutput.bamFiles
@@ -116,7 +116,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
scriptOutput.ugVcfFile = ugVcf.out
mergBuffer += ("2.UG-Discovery" -> scriptOutput.ugVcfFile)
}
-
+
// Generate raw vcf
if (sampleID != null && scriptOutput.bamFiles.size == 1) {
val m2v = new MpileupToVcf(this)
@@ -127,10 +127,10 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
scriptOutput.rawVcfFile = m2v.output
val vcfFilter = new VcfFilter(this)
- vcfFilter.defaults ++= Map("min_sample_depth" -> 8,
- "min_alternate_depth" -> 2,
- "min_samples_pass" -> 1,
- "filter_ref_calls" -> true)
+ vcfFilter.defaults ++= Map("min_sample_depth" -> 8,
+ "min_alternate_depth" -> 2,
+ "min_samples_pass" -> 1,
+ "filter_ref_calls" -> true)
vcfFilter.inputVcf = m2v.output
vcfFilter.outputVcf = this.swapExt(outputDir, m2v.output, ".vcf", ".filter.vcf.gz")
add(vcfFilter)
@@ -138,7 +138,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
} else if (rawVcfInput != null) scriptOutput.rawFilterVcfFile = rawVcfInput
if (scriptOutput.rawFilterVcfFile == null) throw new IllegalStateException("Files can't be empty")
mergBuffer += ("9.raw" -> scriptOutput.rawFilterVcfFile)
-
+
if (useAllelesOption.get) {
val alleleOnly = new CommandLineFunction {
@Input val input: File = scriptOutput.rawFilterVcfFile
@@ -147,7 +147,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
def commandLine = "zcat " + input + " | cut -f1,2,3,4,5,6,7,8 | bgzip -c > " + output + " && tabix -pvcf " + output
}
add(alleleOnly, isIntermediate = true)
-
+
if (useHaplotypecaller.get) {
val hcAlleles = new HaplotypeCaller(this)
hcAlleles.input_file = scriptOutput.bamFiles
@@ -158,7 +158,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
scriptOutput.hcAlleleVcf = hcAlleles.out
mergBuffer += ("3.HC-alleles" -> hcAlleles.out)
}
-
+
if (useUnifiedGenotyper.get) {
val ugAlleles = new UnifiedGenotyper(this)
ugAlleles.input_file = scriptOutput.bamFiles
@@ -171,7 +171,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
}
}
- def removeNoneVariants(input:File): File = {
+ def removeNoneVariants(input: File): File = {
val output = input.getAbsolutePath.stripSuffix(".vcf.gz") + ".variants_only.vcf.gz"
val sv = SelectVariants(this, input, output)
sv.excludeFiltered = true
@@ -180,7 +180,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
sv.out
}
- def mergeList = mergBuffer map {case (key, file) => TaggedFile(removeNoneVariants(file), "name=" + key)}
+ def mergeList = mergBuffer map { case (key, file) => TaggedFile(removeNoneVariants(file), "name=" + key) }
val cvFinal = CombineVariants(this, mergeList.toList, outputDir + outputName + ".final.vcf.gz")
add(cvFinal)
scriptOutput.finalVcfFile = cvFinal.out
@@ -199,7 +199,7 @@ class GatkVariantcalling(val root: Configurable) extends QScript with BiopetQScr
def addBaseRecalibrator(inputBam: File, dir: String, isIntermediate: Boolean = false): File = {
val baseRecalibrator = BaseRecalibrator(this, inputBam, swapExt(dir, inputBam, ".bam", ".baserecal")) //with gatkArguments {
-
+
if (baseRecalibrator.knownSites.isEmpty) {
logger.warn("No Known site found, skipping base recalibration, file: " + inputBam)
return inputBam
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 137e6bd4ad531e19d0f0d5348dc2d927bfe2ebe0..2ed691bb0d52b94a07b8ccef7c84909cbf3ff372 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
@@ -6,7 +6,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.extensions.gatk.CombineVariants
import nl.lumc.sasc.biopet.extensions.gatk.SelectVariants
import org.broadinstitute.gatk.queue.QScript
-import org.broadinstitute.gatk.queue.extensions.gatk.{ CommandLineGATK, VariantEval}
+import org.broadinstitute.gatk.queue.extensions.gatk.{ CommandLineGATK, VariantEval }
import org.broadinstitute.gatk.utils.commandline.{ Input, Argument }
class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQScript {
@@ -20,24 +20,24 @@ class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQS
@Argument(doc = "Target bed", shortName = "targetBed", required = false)
var targetBed: List[File] = Nil
-
+
@Argument(doc = "Samples", shortName = "sample", required = false)
var samples: List[String] = Nil
-
+
var vcfFile: File = _
- var sampleVcfs:Map[String, File] = Map()
+ var sampleVcfs: Map[String, File] = Map()
def generalSampleDir = outputDir + "samples/"
-
+
trait gatkArguments extends CommandLineGATK {
this.reference_sequence = reference
this.memoryLimit = 2
this.jobResourceRequests :+= "h_vmem=4G"
}
-
+
def init() {
if (reference == null) reference = config("reference")
- if (config.contains("target_bed"))
- for (bed <- config("target_bed").getList)
+ if (config.contains("target_bed"))
+ for (bed <- config("target_bed").getList)
targetBed :+= bed.toString
if (outputDir == null) throw new IllegalStateException("Missing Output directory on gatk module")
else if (!outputDir.endsWith("/")) outputDir += "/"
@@ -49,7 +49,7 @@ class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQS
add(combineVariants)
combineVariants.out
} else vcfFiles.head
-
+
for (sample <- samples) {
sampleVcfs += (sample -> new File(generalSampleDir + sample + File.separator + sample + ".vcf"))
val selectVariants = SelectVariants(this, vcfFile, sampleVcfs(sample))
@@ -57,7 +57,7 @@ class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQS
selectVariants.excludeNonVariants = true
add(selectVariants)
}
-
+
val sampleCompareMetrics = new SampleCompareMetrics(this)
sampleCompareMetrics.samples = samples
sampleCompareMetrics.sampleDir = generalSampleDir
@@ -66,10 +66,10 @@ class GatkVcfSampleCompare(val root: Configurable) extends QScript with BiopetQS
sampleCompareMetrics.indelRelFile = outputDir + "compare.indel.rel.tsv"
sampleCompareMetrics.indelAbsFile = outputDir + "compare.indel.abs.tsv"
sampleCompareMetrics.totalFile = outputDir + "total.tsv"
-
- for ((sample,sampleVcf) <- sampleVcfs) {
+
+ for ((sample, sampleVcf) <- sampleVcfs) {
val sampleDir = generalSampleDir + sample + File.separator
- for ((compareSample,compareSampleVcf) <- sampleVcfs) {
+ for ((compareSample, compareSampleVcf) <- sampleVcfs) {
val variantEval = new VariantEval with gatkArguments
variantEval.eval = Seq(sampleVcf)
variantEval.comp = Seq(compareSampleVcf)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala
index 8c111d15dd962a11205e4daa83e2202ef4f698a0..b66ac47c353a84a3093d61a343d294cc2af93c58 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/SampleCompareMetrics.scala
@@ -7,7 +7,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.R.RScriptExecutor
import org.broadinstitute.gatk.utils.commandline.{ Output, Argument }
import scala.io.Source
-import org.broadinstitute.gatk.utils.R.{RScriptLibrary, RScriptExecutor}
+import org.broadinstitute.gatk.utils.R.{ RScriptLibrary, RScriptExecutor }
import org.broadinstitute.gatk.utils.io.Resource
import scala.collection.mutable.Map
import scala.math._
@@ -17,39 +17,39 @@ class SampleCompareMetrics(val root: Configurable) extends BiopetJavaCommandLine
@Argument(doc = "Sample Dir", shortName = "sampleDir", required = true)
var sampleDir: String = _
-
+
@Argument(doc = "Samples", shortName = "sample", required = true)
var samples: List[String] = Nil
-
+
@Argument(doc = "File sufix", shortName = "sufix", required = false)
var fileSufix: String = _
-
+
@Output(doc = "snpRelFile", shortName = "snpRelFile", required = true)
var snpRelFile: File = _
-
+
@Output(doc = "snpAbsFile", shortName = "snpAbsFile", required = true)
var snpAbsFile: File = _
-
+
@Output(doc = "indelRelFile", shortName = "indelRelFile", required = true)
var indelRelFile: File = _
-
+
@Output(doc = "indelAbsFile", shortName = "indelAbsFile", required = true)
var indelAbsFile: File = _
-
+
@Output(doc = "totalFile", shortName = "totalFile", required = true)
var totalFile: File = _
-
+
override val defaultVmem = "8G"
memoryLimit = Option(4.0)
-
- override def commandLine = super.commandLine +
- required("-sampleDir", sampleDir) +
- repeat("-sample", samples) +
- optional("-fileSufix", fileSufix) +
- required("-snpRelFile", snpRelFile) +
- required("-snpAbsFile", snpAbsFile) +
- required("-indelRelFile", indelRelFile) +
- required("-indelAbsFile", indelAbsFile) +
+
+ override def commandLine = super.commandLine +
+ required("-sampleDir", sampleDir) +
+ repeat("-sample", samples) +
+ optional("-fileSufix", fileSufix) +
+ required("-snpRelFile", snpRelFile) +
+ required("-snpAbsFile", snpAbsFile) +
+ required("-indelRelFile", indelRelFile) +
+ required("-indelAbsFile", indelAbsFile) +
required("-totalFile", totalFile)
}
@@ -66,41 +66,41 @@ object SampleCompareMetrics {
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
-
+
for (t <- 0 until args.size) {
args(t) match {
- case "-sample" => samples +:= args(t+1)
- case "-sampleDir" => sampleDir = args(t+1)
- case "-fileSufix" => fileSufix = args(t+1)
- case "-snpRelFile" => snpRelFile = new File(args(t+1))
- case "-snpAbsFile" => snpAbsFile = new File(args(t+1))
- case "-indelRelFile" => indelRelFile = new File(args(t+1))
- case "-indelAbsFile" => indelAbsFile = new File(args(t+1))
- case "-totalFile" => totalFile = new File(args(t+1))
- case _ =>
+ case "-sample" => samples +:= args(t + 1)
+ case "-sampleDir" => sampleDir = args(t + 1)
+ case "-fileSufix" => fileSufix = args(t + 1)
+ case "-snpRelFile" => snpRelFile = new File(args(t + 1))
+ case "-snpAbsFile" => snpAbsFile = new File(args(t + 1))
+ case "-indelRelFile" => indelRelFile = new File(args(t + 1))
+ case "-indelAbsFile" => indelAbsFile = new File(args(t + 1))
+ case "-totalFile" => totalFile = new File(args(t + 1))
+ case _ =>
}
}
if (sampleDir == null) throw new IllegalStateException("No sampleDir, use -sampleDir")
else if (!sampleDir.endsWith("/")) sampleDir += "/"
-
+
val regex = """\W+""".r
- val snpsOverlap: Map[(String,String), Int] = Map()
- val indelsOverlap: Map[(String,String), Int] = Map()
+ val snpsOverlap: Map[(String, String), Int] = Map()
+ val indelsOverlap: Map[(String, String), Int] = Map()
val snpsTotal: Map[String, Int] = Map()
val indelsTotal: Map[String, Int] = Map()
for (sample1 <- samples; sample2 <- samples) {
val reader = Source.fromFile(new File(sampleDir + sample1 + "/" + sample1 + "-" + sample2 + fileSufix))
for (line <- reader.getLines) {
regex.split(line) match {
- case Array(_,_,_,varType, all, novel, overlap, rate, _*) => {
+ case Array(_, _, _, varType, all, novel, overlap, rate, _*) => {
varType match {
case "SNP" => {
- snpsOverlap += (sample1, sample2) -> overlap.toInt
- snpsTotal += sample1 -> all.toInt
+ snpsOverlap += (sample1, sample2) -> overlap.toInt
+ snpsTotal += sample1 -> all.toInt
}
case "INDEL" => {
- indelsOverlap += (sample1, sample2) -> overlap.toInt
- indelsTotal += sample1 -> all.toInt
+ indelsOverlap += (sample1, sample2) -> overlap.toInt
+ indelsTotal += sample1 -> all.toInt
}
case _ =>
}
@@ -110,12 +110,12 @@ object SampleCompareMetrics {
}
reader.close()
}
-
+
val snpRelWritter = new PrintWriter(snpRelFile)
val snpAbsWritter = new PrintWriter(snpAbsFile)
val indelRelWritter = new PrintWriter(indelRelFile)
val indelAbsWritter = new PrintWriter(indelAbsFile)
-
+
val allWritters = List(snpRelWritter, snpAbsWritter, indelRelWritter, indelAbsWritter)
for (writter <- allWritters) writter.println(samples.mkString("\t", "\t", ""))
for (sample1 <- samples) {
@@ -129,14 +129,14 @@ object SampleCompareMetrics {
for (writter <- allWritters) writter.println()
}
for (writter <- allWritters) writter.close()
-
+
val totalWritter = new PrintWriter(totalFile)
totalWritter.println("Sample\tSNPs\tIndels")
- for (sample <- samples)
+ for (sample <- samples)
totalWritter.println(sample + "\t" + snpsTotal(sample) + "\t" + indelsTotal(sample))
totalWritter.close()
-
- def plot(file:File) {
+
+ def plot(file: File) {
val executor = new RScriptExecutor
executor.addScript(new Resource("plotHeatmap.R", getClass))
executor.addArgs(file, file.getAbsolutePath.stripSuffix(".tsv") + ".png", file.getAbsolutePath.stripSuffix(".tsv") + ".clustering.png")
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 d3085d3447cafaaf8579ed684fdead1c5c3c1e36..ad1406f566dab1c061e7cb52f7feae8e9c260df9 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
@@ -5,8 +5,8 @@ import java.io.File
import java.util.Date
import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
import nl.lumc.sasc.biopet.tools.FastqSplitter
-import nl.lumc.sasc.biopet.extensions.aligners.{ Bwa, Star , Bowtie, Stampy}
-import nl.lumc.sasc.biopet.extensions.picard.{MarkDuplicates, SortSam, MergeSamFiles, AddOrReplaceReadGroups}
+import nl.lumc.sasc.biopet.extensions.aligners.{ Bwa, Star, Bowtie, Stampy }
+import nl.lumc.sasc.biopet.extensions.picard.{ MarkDuplicates, SortSam, MergeSamFiles, AddOrReplaceReadGroups }
import nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics
import nl.lumc.sasc.biopet.pipelines.flexiprep.Flexiprep
import org.broadinstitute.gatk.queue.QScript
@@ -34,7 +34,7 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
@Argument(doc = "Skip metrics", shortName = "skipmetrics", required = false)
var skipMetrics: Boolean = false
-
+
@Argument(doc = "Aligner", shortName = "ALN", required = false)
var aligner: String = _
@@ -43,7 +43,7 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
@Argument(doc = "Chunking", shortName = "chunking", required = false)
var chunking: Boolean = false
-
+
@ClassType(classOf[Int])
@Argument(doc = "Number of chunks, when not defined pipeline will automatic calculate number of chunks", shortName = "numberChunks", required = false)
var numberChunks: Option[Int] = None
@@ -79,7 +79,7 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
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)
@@ -112,7 +112,7 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
else {
val chunkSize: Int = config("chunksize", (1 << 30))
val filesize = if (input_R1.getName.endsWith(".gz") || input_R1.getName.endsWith(".gzip")) input_R1.length * 3
- else input_R1.length
+ else input_R1.length
numberChunks = Option(ceil(filesize.toDouble / chunkSize).toInt)
}
}
@@ -146,8 +146,9 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
val chunkDir = outputDir + "chunks/" + t + "/"
chunks += (chunkDir -> (removeGz(chunkDir + fastq_R1.getName),
if (paired) removeGz(chunkDir + fastq_R2.getName) else ""))
- } else chunks += (outputDir -> (flexiprep.extractIfNeeded(fastq_R1, flexiprep.outputDir),
- flexiprep.extractIfNeeded(fastq_R2, flexiprep.outputDir)))
+ }
+ else chunks += (outputDir -> (flexiprep.extractIfNeeded(fastq_R1, flexiprep.outputDir),
+ flexiprep.extractIfNeeded(fastq_R2, flexiprep.outputDir)))
if (chunking) {
val fastSplitter_R1 = new FastqSplitter(this)
@@ -176,16 +177,16 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
fastq_R1_output :+= R1
fastq_R2_output :+= R2
}
-
+
val outputBam = new File(chunkDir + outputName + ".bam")
bamFiles :+= outputBam
aligner match {
- case "bwa" => addBwa(R1, R2, outputBam, deps)
- case "bowtie" => addBowtie(R1, R2, outputBam, deps)
- case "stampy" => addStampy(R1, R2, outputBam, deps)
- case "star" => addStar(R1, R2, outputBam, deps)
+ case "bwa" => addBwa(R1, R2, outputBam, deps)
+ case "bowtie" => addBowtie(R1, R2, outputBam, deps)
+ case "stampy" => addStampy(R1, R2, outputBam, deps)
+ case "star" => addStar(R1, R2, outputBam, deps)
case "star-2pass" => addStar2pass(R1, R2, outputBam, deps)
- case _ => throw new IllegalStateException("Option Aligner: '" + aligner + "' is not valid")
+ case _ => throw new IllegalStateException("Option Aligner: '" + aligner + "' is not valid")
}
if (config("chunk_metrics", default = false))
addAll(BamMetrics(this, outputBam, chunkDir + "metrics/").functions)
@@ -204,13 +205,13 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
add(mergeSamFile)
bamFile = mergeSamFile.output
}
-
+
if (!skipMetrics) addAll(BamMetrics(this, bamFile, outputDir + "metrics/").functions)
-
+
outputFiles += ("finalBamFile" -> bamFile)
}
- def addBwa(R1:File, R2:File, output:File, deps:List[File]): File = {
+ def addBwa(R1: File, R2: File, output: File, deps: List[File]): File = {
val bwaCommand = new Bwa(this)
bwaCommand.R1 = R1
if (paired) bwaCommand.R2 = R2
@@ -223,9 +224,9 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
add(sortSam)
return sortSam.output
}
-
- def addStampy(R1:File, R2:File, output:File, deps:List[File]): File = {
-
+
+ def addStampy(R1: File, R2: File, output: File, deps: List[File]): File = {
+
var RG: String = "ID:" + RGID + ","
RG += "SM:" + RGSM + ","
RG += "LB:" + RGLB + ","
@@ -249,8 +250,8 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
add(sortSam)
return sortSam.output
}
-
- def addBowtie(R1:File, R2:File, output:File, deps:List[File]): File = {
+
+ def addBowtie(R1: File, R2: File, output: File, deps: List[File]): File = {
val bowtie = new Bowtie(this)
bowtie.R1 = R1
if (paired) bowtie.R2 = R2
@@ -259,19 +260,19 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
add(bowtie, isIntermediate = true)
return addAddOrReplaceReadGroups(bowtie.output, output)
}
-
- def addStar(R1:File, R2:File, output:File, deps:List[File]): File = {
+
+ def addStar(R1: File, R2: File, output: File, deps: List[File]): File = {
val starCommand = Star(this, R1, if (paired) R2 else null, outputDir, isIntermediate = true, deps = deps)
add(starCommand)
return addAddOrReplaceReadGroups(starCommand.outputSam, output)
}
-
- def addStar2pass(R1:File, R2:File, output:File, deps:List[File]): File = {
+
+ def addStar2pass(R1: File, R2: File, output: File, deps: List[File]): File = {
val starCommand = Star._2pass(this, R1, if (paired) R2 else null, outputDir, isIntermediate = true, deps = deps)
addAll(starCommand._2)
return addAddOrReplaceReadGroups(starCommand._1, output)
}
-
+
def addAddOrReplaceReadGroups(input: File, output: File): File = {
val addOrReplaceReadGroups = AddOrReplaceReadGroups(this, input, output)
addOrReplaceReadGroups.createIndex = true
@@ -305,7 +306,7 @@ class Mapping(val root: Configurable) extends QScript with BiopetQScript {
}
object Mapping extends PipelineCommand {
- def loadFromLibraryConfig(root: Configurable, runConfig: Map[String, Any], sampleConfig: Map[String, Any],
+ def loadFromLibraryConfig(root: Configurable, runConfig: Map[String, Any], sampleConfig: Map[String, Any],
runDir: String, startJobs: Boolean = true): Mapping = {
val mapping = new Mapping(root)
@@ -323,7 +324,7 @@ object Mapping extends PipelineCommand {
if (runConfig.contains("PU")) mapping.RGPU = runConfig("PU").toString
if (runConfig.contains("CN")) mapping.RGCN = runConfig("CN").toString
mapping.outputDir = runDir
-
+
if (startJobs) {
mapping.init
mapping.biopetScript
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 36da78d18051e41b59085f98340a0575ef9ea89c..937b84261a20935025aeb79c4f555a7fdfb6827b 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
@@ -18,45 +18,45 @@ import org.broadinstitute.gatk.queue.function._
class Sage(val root: Configurable) extends QScript with MultiSampleQScript {
def this() = this(null)
-
+
@Input(doc = "countBed", required = false)
- var countBed : File = _
-
+ var countBed: File = _
+
@Input(doc = "squishedCountBed, by suppling this file the auto squish job will be skipped", required = false)
- var squishedCountBed : File = _
-
+ var squishedCountBed: File = _
+
@Input(doc = "Transcriptome, used for generation of tag library", required = false)
- var transcriptome : File = _
-
- var tagsLibrary : File = _
-
+ var transcriptome: File = _
+
+ var tagsLibrary: File = _
+
defaults ++= Map("bowtie" -> Map(
- "m" -> 1,
- "k" -> 1,
- "best" -> true,
- "strata" -> true,
- "seedmms" -> 1
- )
- )
-
+ "m" -> 1,
+ "k" -> 1,
+ "best" -> true,
+ "strata" -> true,
+ "seedmms" -> 1
+ )
+ )
+
class LibraryOutput extends AbstractLibraryOutput {
var mappedBamFile: File = _
var prefixFastq: File = _
}
-
+
class SampleOutput extends AbstractSampleOutput {
-
+
}
-
+
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)
+ if (transcriptome == null && tagsLibrary == null)
throw new IllegalStateException("No transcriptome or taglib found")
- if (countBed == null && squishedCountBed == null)
+ if (countBed == null && squishedCountBed == null)
throw new IllegalStateException("No bedfile supplied, please add a countBed or squishedCountBed")
}
@@ -66,7 +66,7 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript {
add(squishBed)
squishedCountBed = squishBed.output
}
-
+
if (tagsLibrary == null) {
val cdl = new SageCreateLibrary(this)
cdl.input = transcriptome
@@ -77,38 +77,38 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript {
add(cdl)
tagsLibrary = cdl.output
}
-
+
runSamplesJobs
}
-
+
// Called for each sample
def runSingleSampleJobs(sampleConfig: Map[String, Any]): SampleOutput = {
val sampleOutput = new SampleOutput
var libraryBamfiles: List[File] = List()
var libraryFastqFiles: List[File] = List()
val sampleID: String = sampleConfig("ID").toString
- val sampleDir: String = globalSampleDir + sampleID + "/"
+ val sampleDir: String = globalSampleDir + sampleID + "/"
for ((library, libraryFiles) <- runLibraryJobs(sampleConfig)) {
libraryFastqFiles +:= libraryFiles.prefixFastq
libraryBamfiles +:= libraryFiles.mappedBamFile
}
-
+
val bamFile: File = if (libraryBamfiles.size == 1) libraryBamfiles.head
- else if (libraryBamfiles.size > 1) {
- val mergeSamFiles = MergeSamFiles(this, libraryBamfiles, sampleDir)
- add(mergeSamFiles)
- mergeSamFiles.output
- } else null
+ else if (libraryBamfiles.size > 1) {
+ val mergeSamFiles = MergeSamFiles(this, libraryBamfiles, sampleDir)
+ add(mergeSamFiles)
+ mergeSamFiles.output
+ } else null
val fastqFile: File = if (libraryFastqFiles.size == 1) libraryFastqFiles.head
- else if (libraryFastqFiles.size > 1) {
- val cat = Cat.apply(this, libraryFastqFiles, sampleDir + sampleID + ".fastq")
- add(cat)
- cat.output
- } else null
-
+ else if (libraryFastqFiles.size > 1) {
+ val cat = Cat.apply(this, libraryFastqFiles, sampleDir + sampleID + ".fastq")
+ add(cat)
+ cat.output
+ } else null
+
addBedtoolsCounts(bamFile, sampleID, sampleDir)
addTablibCounts(fastqFile, sampleID, sampleDir)
-
+
return sampleOutput
}
@@ -129,14 +129,14 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript {
flexiprep.init
flexiprep.biopetScript
addAll(flexiprep.functions)
-
- val flexiprepOutput = for ((key,file) <- flexiprep.outputFiles if key.endsWith("output_R1")) yield file
+
+ val flexiprepOutput = for ((key, file) <- flexiprep.outputFiles if key.endsWith("output_R1")) yield file
val prefixFastq = PrefixFastq.apply(this, flexiprepOutput.head, runDir)
prefixFastq.prefix = config("sage_tag", default = "CATG")
prefixFastq.deps +:= flexiprep.outputFiles("fastq_input_R1")
add(prefixFastq)
libraryOutput.prefixFastq = prefixFastq.output
-
+
val mapping = new Mapping(this)
mapping.skipFlexiprep = true
mapping.skipMarkduplicates = true
@@ -151,45 +151,45 @@ class Sage(val root: Configurable) extends QScript with MultiSampleQScript {
mapping.init
mapping.biopetScript
addAll(mapping.functions)
-
+
if (config("library_counts", default = false).getBoolean) {
addBedtoolsCounts(mapping.outputFiles("finalBamFile"), sampleID + "-" + runID, runDir)
addTablibCounts(prefixFastq.output, sampleID + "-" + runID, runDir)
}
-
+
libraryOutput.mappedBamFile = mapping.outputFiles("finalBamFile")
} else this.logger.error("Sample: " + sampleID + ": No R1 found for run: " + runConfig)
return libraryOutput
}
-
- def addBedtoolsCounts(bamFile:File, outputPrefix: String, outputDir: String) {
- val bedtoolsSense = BedtoolsCoverage(this, bamFile, squishedCountBed, outputDir + outputPrefix + ".genome.sense.coverage",
- depth = false, sameStrand = true, diffStrand = false)
+
+ def addBedtoolsCounts(bamFile: File, outputPrefix: String, outputDir: String) {
+ val bedtoolsSense = BedtoolsCoverage(this, bamFile, squishedCountBed, outputDir + outputPrefix + ".genome.sense.coverage",
+ depth = false, sameStrand = true, diffStrand = false)
val countSense = new BedtoolsCoverageToCounts(this)
countSense.input = bedtoolsSense.output
countSense.output = outputDir + outputPrefix + ".genome.sense.counts"
-
- val bedtoolsAntisense = BedtoolsCoverage(this, bamFile, squishedCountBed, outputDir + outputPrefix + ".genome.antisense.coverage",
- depth = false, sameStrand = false, diffStrand = true)
+
+ val bedtoolsAntisense = BedtoolsCoverage(this, bamFile, squishedCountBed, outputDir + outputPrefix + ".genome.antisense.coverage",
+ depth = false, sameStrand = false, diffStrand = true)
val countAntisense = new BedtoolsCoverageToCounts(this)
countAntisense.input = bedtoolsAntisense.output
countAntisense.output = outputDir + outputPrefix + ".genome.antisense.counts"
-
- val bedtools = BedtoolsCoverage(this, bamFile, squishedCountBed, outputDir + outputPrefix + ".genome.coverage",
- depth = false, sameStrand = false, diffStrand = false)
+
+ val bedtools = BedtoolsCoverage(this, bamFile, squishedCountBed, outputDir + outputPrefix + ".genome.coverage",
+ depth = false, sameStrand = false, diffStrand = false)
val count = new BedtoolsCoverageToCounts(this)
count.input = bedtools.output
count.output = outputDir + outputPrefix + ".genome.counts"
-
+
add(bedtoolsSense, countSense, bedtoolsAntisense, countAntisense, bedtools, count)
}
-
- def addTablibCounts(fastq:File, outputPrefix: String, outputDir: String) {
+
+ def addTablibCounts(fastq: File, outputPrefix: String, outputDir: String) {
val countFastq = new SageCountFastq(this)
countFastq.input = fastq
countFastq.output = outputDir + outputPrefix + ".raw.counts"
add(countFastq)
-
+
val createTagCounts = new SageCreateTagCounts(this)
createTagCounts.input = countFastq.output
createTagCounts.tagLib = tagsLibrary
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 16460f0fd66978f98ba79268cbf93e2a10425e00..10aef464b610c43571398d6285d3ddd7bc9c5b3c 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
@@ -12,7 +12,6 @@ import nl.lumc.sasc.biopet.extensions.sambamba.{ SambambaIndex, SambambaMerge }
import nl.lumc.sasc.biopet.extensions.svcallers.pindel.Pindel
import nl.lumc.sasc.biopet.extensions.svcallers.{ Breakdancer, Clever }
-
import nl.lumc.sasc.biopet.pipelines.mapping.Mapping
import org.broadinstitute.gatk.queue.QScript
@@ -67,7 +66,6 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript {
val sampleDir: String = outputDir + sampleID + "/"
val alignmentDir: String = sampleDir + "alignment/"
-
val svcallingDir: String = sampleDir + "svcalls/"
sampleOutput.libraries = runLibraryJobs(sampleConfig)
@@ -76,7 +74,7 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript {
libraryBamfiles ++= List(libraryOutput.mappedBamFile)
}
- val bamFile: File =
+ val bamFile: File =
if (libraryBamfiles.size == 1) libraryBamfiles.head
else if (libraryBamfiles.size > 1) {
val mergeSamFiles = new SambambaMerge(root)
@@ -85,10 +83,10 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript {
add(mergeSamFiles)
mergeSamFiles.output
} else null
-
+
val bamIndex = SambambaIndex(root, bamFile)
add(bamIndex)
-
+
/// bamfile will be used as input for the SV callers. First run Clever
// val cleverVCF : File = sampleDir + "/" + sampleID + ".clever.vcf"
@@ -104,12 +102,12 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript {
addAll(breakdancer.functions)
// for pindel we should use per library config collected into one config file
-// val pindelDir = svcallingDir + sampleID + ".pindel/"
-// val pindel = Pindel(this, bamFile, this.reference, pindelDir)
-// sampleOutput.vcf += ("pindel" -> List(pindel.outputvcf))
-// addAll(pindel.functions)
-//
-//
+ // val pindelDir = svcallingDir + sampleID + ".pindel/"
+ // val pindel = Pindel(this, bamFile, this.reference, pindelDir)
+ // sampleOutput.vcf += ("pindel" -> List(pindel.outputvcf))
+ // addAll(pindel.functions)
+ //
+ //
return sampleOutput
}
@@ -117,12 +115,12 @@ class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript {
def runSingleLibraryJobs(runConfig: Map[String, Any], sampleConfig: Map[String, Any]): LibraryOutput = {
val libraryOutput = new LibraryOutput
-
+
val runID: String = runConfig("ID").toString
val sampleID: String = sampleConfig("ID").toString
val alignmentDir: String = outputDir + sampleID + "/alignment/"
val runDir: String = alignmentDir + "run_" + runID + "/"
-
+
if (runConfig.contains("R1")) {
val mapping = new Mapping(this)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/CoverageStats.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/CoverageStats.scala
index fc1ffb12a499e33dc0687d2c917bbfb92a8ef158..11ac6281796563659929670e9a2158371dc5d926 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/CoverageStats.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/CoverageStats.scala
@@ -16,7 +16,7 @@ class CoverageStats(val root: Configurable) extends PythonCommandLineFunction {
@Output(doc = "plot File (png)")
var plot: File = _
-
+
override val defaultVmem = "12G"
def cmdLine = getPythonCommand +
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/FastqSync.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/FastqSync.scala
index f98f9299a636abbe9fac47bff98c543afdd9ebc7..01d65e4eea8e2a947b0cd412b66de872798178fe 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/FastqSync.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/FastqSync.scala
@@ -35,33 +35,33 @@ class FastqSync(val root: Configurable) extends PythonCommandLineFunction {
def cmdLine = {
getPythonCommand +
- required(input_start_fastq) +
- required(input_R1) +
- required(input_R2) +
- required(output_R1) +
- required(output_R2) +
- " > " +
- required(output_stats)
+ required(input_start_fastq) +
+ required(input_R1) +
+ required(input_R2) +
+ required(output_R1) +
+ required(output_R2) +
+ " > " +
+ required(output_stats)
}
def getSummary: Json = {
val R1_filteredR = """Filtered (\d*) reads from first read file.""".r
val R2_filteredR = """Filtered (\d*) reads from second read file.""".r
val readsLeftR = """Synced read files contain (\d*) reads.""".r
-
+
var R1_filtered = 0
var R2_filtered = 0
var readsLeft = 0
-
+
if (output_stats.exists) for (line <- Source.fromFile(output_stats).getLines) {
line match {
case R1_filteredR(m) => R1_filtered = m.toInt
case R2_filteredR(m) => R2_filtered = m.toInt
- case readsLeftR(m) => readsLeft = m.toInt
- case _ =>
+ case readsLeftR(m) => readsLeft = m.toInt
+ case _ =>
}
}
-
+
return ("num_reads_discarded_R1" := R1_filtered) ->:
("num_reads_discarded_R2" := R2_filtered) ->:
("num_reads_kept" := readsLeft) ->:
@@ -70,8 +70,8 @@ class FastqSync(val root: Configurable) extends PythonCommandLineFunction {
}
object FastqSync {
- def apply(root: Configurable, input_start_fastq:File, input_R1:File, input_R2:File,
- output_R1:File, output_R2:File, output_stats:File): FastqSync = {
+ def apply(root: Configurable, input_start_fastq: File, input_R1: File, input_R2: File,
+ output_R1: File, output_R2: File, output_stats: File): FastqSync = {
val fastqSync = new FastqSync(root)
fastqSync.input_start_fastq = input_start_fastq
fastqSync.input_R1 = input_R1
@@ -81,18 +81,18 @@ object FastqSync {
fastqSync.output_stats = output_stats
return fastqSync
}
-
+
def mergeSummaries(jsons: List[Json]): Json = {
var R1_filtered = 0
var R2_filtered = 0
var readsLeft = 0
-
+
for (json <- jsons) {
R1_filtered += json.field("num_reads_discarded_R1").get.numberOrZero.toInt
R2_filtered += json.field("num_reads_discarded_R2").get.numberOrZero.toInt
readsLeft += json.field("num_reads_kept").get.numberOrZero.toInt
}
-
+
return ("num_reads_discarded_R1" := R1_filtered) ->:
("num_reads_discarded_R2" := R2_filtered) ->:
("num_reads_kept" := readsLeft) ->:
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala
index f41fd754771b055fdb33a4de1b88dcad2f0a0490..85c40191fa42fada02aa378dca9c2e9dd4b37277 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala
@@ -13,9 +13,9 @@ class SquishBed(val root: Configurable) extends PythonCommandLineFunction {
@Output(doc = "output File")
var output: File = _
-
+
def cmdLine = getPythonCommand +
- required(input) +
+ required(input) +
required(output)
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/prefixFastq.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/prefixFastq.scala
index 07070727a2af455e956fd02bb8ebe754ad53a795..0411eb46ad1087d36b7c1c7b52d87a6fc42540c9 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/prefixFastq.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/prefixFastq.scala
@@ -16,17 +16,17 @@ class PrefixFastq(val root: Configurable) extends PythonCommandLineFunction {
@Argument(doc = "Prefix sequence")
var prefix: String = "CATG"
-
+
@Argument(doc = "Input file is gziped", required = false)
var gzip: Boolean = _
-
+
override def beforeCmd {
if (input.getName.endsWith(".gzip") || input.getName.endsWith("gz")) gzip = true
}
-
+
def cmdLine = getPythonCommand +
- required("-o", output) +
- required("--prefix", prefix) +
+ required("-o", output) +
+ required("--prefix", prefix) +
required(input)
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala
index 550853dff22d871690bb71631b80d6c55dc19698..436a4ff083eea141b3a45dda18d024022a0960e0 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala
@@ -45,24 +45,27 @@ object BedToInterval extends ToolCommand {
return bedToInterval
}
- case class Args (inputFile:File = null, outputFile:File = null, bamFile:File = null) extends AbstractArgs
+ case class Args(inputFile: File = null, outputFile: File = null, bamFile: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required() valueName("<file>") action { (x, c) =>
- c.copy(inputFile = x) }
- opt[File]('o', "output") required() valueName("<file>") action { (x, c) =>
- c.copy(outputFile = x) }
- opt[File]('b', "bam") required() valueName("<file>") action { (x, c) =>
- c.copy(bamFile = x) }
+ opt[File]('I', "inputFile") required () valueName ("<file>") action { (x, c) =>
+ c.copy(inputFile = x)
+ }
+ opt[File]('o', "output") required () valueName ("<file>") action { (x, c) =>
+ c.copy(outputFile = x)
+ }
+ opt[File]('b', "bam") required () valueName ("<file>") action { (x, c) =>
+ c.copy(bamFile = x)
+ }
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
val writer = new PrintWriter(commandArgs.outputFile)
val inputSam = new SAMFileReader(commandArgs.bamFile)
@@ -72,19 +75,16 @@ object BedToInterval extends ToolCommand {
record.getSequenceName -> record.getSequenceLength
}
inputSam.close
- val refsMap = Map(refs:_*)
-
+ val refsMap = Map(refs: _*)
+
val bedFile = Source.fromFile(commandArgs.inputFile)
for (
- line <- bedFile.getLines;
- val split = line.split("\t")
- if split.size >= 3;
- val chr = split(0);
- val start = split(1);
- val stop = split(2)
- if start forall Character.isDigit
- if stop forall Character.isDigit
- ) {
+ line <- bedFile.getLines;
+ val split = line.split("\t") if split.size >= 3;
+ val chr = split(0);
+ val start = split(1);
+ val stop = split(2) if start forall Character.isDigit if stop forall Character.isDigit
+ ) {
if (!refsMap.contains(chr)) throw new IllegalStateException("Chr '" + chr + "' in bed file not found in bam file")
writer.write(chr + "\t" + start + "\t" + stop + "\t")
if (split.length >= 6 && (split(5) == "+" || split(5) == "-")) writer.write(split(5))
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala
index 004d322caabfb8fe0dd24ad793b14b141371d30b..ff818d111d9e44a334d035ec3e492e97d51e89e7 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala
@@ -16,38 +16,40 @@ class BedtoolsCoverageToCounts(val root: Configurable) extends BiopetJavaCommand
@Input(doc = "Input fasta", shortName = "input", required = true)
var input: File = _
-
+
@Output(doc = "Output tag library", shortName = "output", required = true)
var output: File = _
-
+
override val defaultVmem = "8G"
memoryLimit = Option(4.0)
-
- override def commandLine = super.commandLine +
- required("-I", input) +
+
+ override def commandLine = super.commandLine +
+ required("-I", input) +
required("-o", output)
}
object BedtoolsCoverageToCounts extends ToolCommand {
- case class Args (input:File = null, output:File = null) extends AbstractArgs
+ case class Args(input: File = null, output: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") required() valueName("<file>") action { (x, c) =>
- c.copy(input = x) }
- opt[File]('o', "output") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(output = x) }
+ opt[File]('I', "input") required () valueName ("<file>") action { (x, c) =>
+ c.copy(input = x)
+ }
+ opt[File]('o', "output") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(output = x)
+ }
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
-
- val counts:Map[String, Long] = Map()
+
+ val counts: Map[String, Long] = Map()
for (line <- Source.fromFile(commandArgs.input).getLines) {
val values = line.split("\t")
val gene = values(3)
@@ -55,11 +57,11 @@ object BedtoolsCoverageToCounts extends ToolCommand {
if (counts.contains(gene)) counts(gene) += count
else counts += gene -> count
}
-
- val sortedCounts:SortedMap[String, Long] = SortedMap(counts.toArray:_*)
-
+
+ val sortedCounts: SortedMap[String, Long] = SortedMap(counts.toArray: _*)
+
val writer = new PrintWriter(commandArgs.output)
- for ((seq,count) <- sortedCounts) {
+ for ((seq, count) <- sortedCounts) {
if (count > 0) writer.println(seq + "\t" + count)
}
writer.close
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala
index 361c6e6c8b6cbb80a5696ea7ff027d8dd82a522e..8465f45637bd2f8aec6976ec814d49d00636d338 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala
@@ -38,41 +38,43 @@ object BiopetFlagstat extends ToolCommand {
flagstat.output = new File(outputDir, input.getName.stripSuffix(".bam") + ".biopetflagstat")
return flagstat
}
-
- case class Args (inputFile:File = null, region:Option[String] = None) extends AbstractArgs
+
+ case class Args(inputFile: File = null, region: Option[String] = None) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required() valueName("<file>") action { (x, c) =>
- c.copy(inputFile = x) } text("out is a required file property")
- opt[String]('r', "region") valueName("<chr:start-stop>") action { (x, c) =>
- c.copy(region = Some(x)) } text("out is a required file property")
+ opt[File]('I', "inputFile") required () valueName ("<file>") action { (x, c) =>
+ c.copy(inputFile = x)
+ } text ("out is a required file property")
+ opt[String]('r', "region") valueName ("<chr:start-stop>") action { (x, c) =>
+ c.copy(region = Some(x))
+ } text ("out is a required file property")
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
- val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+ val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
+
val inputSam = new SAMFileReader(commandArgs.inputFile)
val iterSam = if (commandArgs.region == None) inputSam.iterator else {
val regionRegex = """(.*):(.*)-(.*)""".r
commandArgs.region.get match {
case regionRegex(chr, start, stop) => inputSam.query(chr, start.toInt, stop.toInt, false)
- case _ => sys.error("Region wrong format")
+ case _ => sys.error("Region wrong format")
}
}
-
+
val flagstatCollector = new FlagstatCollector
flagstatCollector.loadDefaultFunctions
val m = 10
val max = 60
for (t <- 0 to (max / m))
flagstatCollector.addFunction("MAPQ>" + (t * m), record => record.getMappingQuality > (t * m))
- flagstatCollector.addFunction("First normal, second read inverted (paired end orientation)", record => {
- if (record.getReadPairedFlag &&
- record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag != record.getMateNegativeStrandFlag &&
+ flagstatCollector.addFunction("First normal, second read inverted (paired end orientation)", record => {
+ if (record.getReadPairedFlag &&
+ record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag != record.getMateNegativeStrandFlag &&
((record.getFirstOfPairFlag && !record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
(record.getFirstOfPairFlag && record.getReadNegativeStrandFlag && record.getAlignmentStart > record.getMateAlignmentStart) ||
(record.getSecondOfPairFlag && !record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
@@ -80,8 +82,8 @@ object BiopetFlagstat extends ToolCommand {
else false
})
flagstatCollector.addFunction("First normal, second read normal", record => {
- if (record.getReadPairedFlag &&
- record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag == record.getMateNegativeStrandFlag &&
+ if (record.getReadPairedFlag &&
+ record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag == record.getMateNegativeStrandFlag &&
((record.getFirstOfPairFlag && !record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
(record.getFirstOfPairFlag && record.getReadNegativeStrandFlag && record.getAlignmentStart > record.getMateAlignmentStart) ||
(record.getSecondOfPairFlag && record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
@@ -89,8 +91,8 @@ object BiopetFlagstat extends ToolCommand {
else false
})
flagstatCollector.addFunction("First inverted, second read inverted", record => {
- if (record.getReadPairedFlag &&
- record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag == record.getMateNegativeStrandFlag &&
+ if (record.getReadPairedFlag &&
+ record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag == record.getMateNegativeStrandFlag &&
((record.getFirstOfPairFlag && record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
(record.getFirstOfPairFlag && !record.getReadNegativeStrandFlag && record.getAlignmentStart > record.getMateAlignmentStart) ||
(record.getSecondOfPairFlag && !record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
@@ -98,8 +100,8 @@ object BiopetFlagstat extends ToolCommand {
else false
})
flagstatCollector.addFunction("First inverted, second read normal", record => {
- if (record.getReadPairedFlag &&
- record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag != record.getMateNegativeStrandFlag &&
+ if (record.getReadPairedFlag &&
+ record.getReferenceIndex == record.getMateReferenceIndex && record.getReadNegativeStrandFlag != record.getMateNegativeStrandFlag &&
((record.getFirstOfPairFlag && record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
(record.getFirstOfPairFlag && !record.getReadNegativeStrandFlag && record.getAlignmentStart > record.getMateAlignmentStart) ||
(record.getSecondOfPairFlag && record.getReadNegativeStrandFlag && record.getAlignmentStart < record.getMateAlignmentStart) ||
@@ -109,7 +111,7 @@ object BiopetFlagstat extends ToolCommand {
flagstatCollector.addFunction("Mate in same strand", record => record.getReadPairedFlag && record.getReadNegativeStrandFlag && record.getMateNegativeStrandFlag &&
record.getReferenceIndex == record.getMateReferenceIndex)
flagstatCollector.addFunction("Mate on other chr", record => record.getReadPairedFlag && record.getReferenceIndex != record.getMateReferenceIndex)
-
+
logger.info("Start reading file: " + commandArgs.inputFile)
for (record <- iterSam) {
if (flagstatCollector.readsCount % 1e6 == 0 && flagstatCollector.readsCount > 0)
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala
index 315a8db8c8b2743c81cdb618685a6eabf381891f..867eb36ad2b17e19cbb3b8d93bc894ef50c05dae 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala
@@ -36,60 +36,64 @@ import scala.math._
//}
object CheckAllelesVcfInBam extends ToolCommand {
- case class Args (inputFile:File = null, outputFile:File = null, samples:List[String] = Nil,
- bamFiles:List[File] = Nil, minMapQual:Int = 1) extends AbstractArgs
+ case class Args(inputFile: File = null, outputFile: File = null, samples: List[String] = Nil,
+ bamFiles: List[File] = Nil, minMapQual: Int = 1) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(inputFile = x) }
- opt[File]('o', "outputFile") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(outputFile = x) }
- opt[String]('s', "sample") unbounded() minOccurs(1) action { (x, c) =>
- c.copy(samples = x :: c.samples) }
- opt[File]('b', "bam") unbounded() minOccurs(1) action { (x, c) =>
- c.copy(bamFiles = x :: c.bamFiles) }
- opt[Int]('m', "min_mapping_quality") maxOccurs(1) action { (x, c) =>
- c.copy(minMapQual = c.minMapQual) }
+ opt[File]('I', "inputFile") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(inputFile = x)
+ }
+ opt[File]('o', "outputFile") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(outputFile = x)
+ }
+ opt[String]('s', "sample") unbounded () minOccurs (1) action { (x, c) =>
+ c.copy(samples = x :: c.samples)
+ }
+ opt[File]('b', "bam") unbounded () minOccurs (1) action { (x, c) =>
+ c.copy(bamFiles = x :: c.bamFiles)
+ }
+ opt[Int]('m', "min_mapping_quality") maxOccurs (1) action { (x, c) =>
+ c.copy(minMapQual = c.minMapQual)
+ }
}
-
- private class CountReport (
+
+ private class CountReport(
var notFound: Int = 0,
var aCounts: mutable.Map[String, Int] = mutable.Map(),
var duplicateReads: Int = 0,
- var lowMapQualReads: Int = 0
- )
-
+ var lowMapQualReads: Int = 0)
+
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
if (commandArgs.bamFiles.size != commandArgs.samples.size)
logger.warn("Number of samples is diffrent then number of bam files, left over will be removed")
- val bamReaders:Map[String,SAMFileReader] = Map(commandArgs.samples zip commandArgs.bamFiles.map(x => new SAMFileReader(x)):_*)
+ val bamReaders: Map[String, SAMFileReader] = Map(commandArgs.samples zip commandArgs.bamFiles.map(x => new SAMFileReader(x)): _*)
val bamHeaders = bamReaders.map(x => (x._1, x._2.getFileHeader))
-
+
val reader = new VCFFileReader(commandArgs.inputFile, false)
val writer = new AsyncVariantContextWriter(new VariantContextWriterBuilder().setOutputFile(commandArgs.outputFile).build)
-
+
val header = reader.getFileHeader
- for ((sample,_) <- bamReaders) {
- header.addMetaDataLine(new VCFInfoHeaderLine("BAM-AD-" + sample,
- VCFHeaderLineCount.UNBOUNDED, VCFHeaderLineType.Integer, "Allele depth, ref and alt on order of vcf file"))
- header.addMetaDataLine(new VCFInfoHeaderLine("BAM-DP-" + sample,
- 1, VCFHeaderLineType.Integer, "Total reads on this location"))
+ for ((sample, _) <- bamReaders) {
+ header.addMetaDataLine(new VCFInfoHeaderLine("BAM-AD-" + sample,
+ VCFHeaderLineCount.UNBOUNDED, VCFHeaderLineType.Integer, "Allele depth, ref and alt on order of vcf file"))
+ header.addMetaDataLine(new VCFInfoHeaderLine("BAM-DP-" + sample,
+ 1, VCFHeaderLineType.Integer, "Total reads on this location"))
}
-
+
writer.writeHeader(header)
-
+
for (vcfRecord <- reader) {
- val countReports: Map[String,CountReport] = bamReaders.map(x => (x._1, new CountReport))
+ val countReports: Map[String, CountReport] = bamReaders.map(x => (x._1, new CountReport))
val refAllele = vcfRecord.getReference.getBaseString
for ((sample, bamReader) <- bamReaders) {
- val queryInterval = new QueryInterval(bamHeaders(sample).getSequenceIndex(vcfRecord.getChr),
- vcfRecord.getStart, vcfRecord.getStart + refAllele.size - 1)
+ val queryInterval = new QueryInterval(bamHeaders(sample).getSequenceIndex(vcfRecord.getChr),
+ vcfRecord.getStart, vcfRecord.getStart + refAllele.size - 1)
val bamIter = bamReader.query(Array(queryInterval), false)
-
- def filterRead(samRecord:SAMRecord): Boolean = {
+
+ def filterRead(samRecord: SAMRecord): Boolean = {
if (samRecord.getDuplicateReadFlag) {
countReports(sample).duplicateReads += 1
return true
@@ -102,26 +106,26 @@ object CheckAllelesVcfInBam extends ToolCommand {
}
return false
}
-
+
val counts = for (samRecord <- bamIter if !filterRead(samRecord)) {
checkAlles(samRecord, vcfRecord) match {
- case Some(a) => if (countReports(sample).aCounts.contains(a)) countReports(sample).aCounts(a) += 1
- else countReports(sample).aCounts += (a -> 1)
+ case Some(a) => if (countReports(sample).aCounts.contains(a)) countReports(sample).aCounts(a) += 1
+ else countReports(sample).aCounts += (a -> 1)
case _ => countReports(sample).notFound += 1
}
- }
+ }
bamIter.close
}
-
+
val builder = new VariantContextBuilder(vcfRecord)
- for ((k,v) <- countReports) {
+ for ((k, v) <- countReports) {
val s = for (allele <- vcfRecord.getAlleles) yield {
val s = allele.getBaseString
if (v.aCounts.contains(s)) v.aCounts(s)
else 0
}
builder.attribute("BAM-AD-" + k, s.mkString(","))
- builder.attribute("BAM-DP-" + k, (0 /: s) (_ + _) + v.notFound)
+ builder.attribute("BAM-DP-" + k, (0 /: s)(_ + _) + v.notFound)
}
writer.add(builder.make)
}
@@ -129,32 +133,32 @@ object CheckAllelesVcfInBam extends ToolCommand {
reader.close
writer.close
}
-
- def checkAlles(samRecord:SAMRecord, vcfRecord:VariantContext): Option[String] = {
+
+ def checkAlles(samRecord: SAMRecord, vcfRecord: VariantContext): Option[String] = {
val readStartPos = List.range(0, samRecord.getReadBases.length)
- .find(x => samRecord.getReferencePositionAtReadPosition(x+1) == vcfRecord.getStart) getOrElse { return None }
+ .find(x => samRecord.getReferencePositionAtReadPosition(x + 1) == vcfRecord.getStart) getOrElse { return None }
val readBases = samRecord.getReadBases()
val alleles = vcfRecord.getAlleles.map(x => x.getBaseString)
val refAllele = alleles.head
var maxSize = 1
for (allele <- alleles if allele.size > maxSize) maxSize = allele.size
- val readC = for (t <- readStartPos until readStartPos+maxSize if t < readBases.length) yield readBases(t).toChar
- val allelesInRead = mutable.Set(alleles.filter(readC.mkString.startsWith(_)):_*)
-
+ val readC = for (t <- readStartPos until readStartPos + maxSize if t < readBases.length) yield readBases(t).toChar
+ val allelesInRead = mutable.Set(alleles.filter(readC.mkString.startsWith(_)): _*)
+
// Removal of insertions that are not really in the cigarstring
for (allele <- allelesInRead if allele.size > refAllele.size) {
val refPos = for (t <- refAllele.size until allele.size) yield samRecord.getReferencePositionAtReadPosition(readStartPos + t + 1)
if (refPos.exists(_ > 0)) allelesInRead -= allele
}
-
+
// Removal of alleles that are not really in the cigarstring
for (allele <- allelesInRead) {
val readPosAfterAllele = samRecord.getReferencePositionAtReadPosition(readStartPos + allele.size + 1)
val vcfPosAfterAllele = vcfRecord.getStart + refAllele.size
- if (readPosAfterAllele != vcfPosAfterAllele &&
- (refAllele.size != allele.size || (refAllele.size == allele.size && readPosAfterAllele < 0))) allelesInRead -= allele
+ if (readPosAfterAllele != vcfPosAfterAllele &&
+ (refAllele.size != allele.size || (refAllele.size == allele.size && readPosAfterAllele < 0))) allelesInRead -= allele
}
-
+
for (allele <- allelesInRead if allele.size >= refAllele.size) {
if (allelesInRead.exists(_.size > allele.size)) allelesInRead -= allele
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala
index 83a607de4a035013cbf82072223f533380ff942c..d0f09baaa820b1a57ed181f66c25996faf9330a6 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala
@@ -83,9 +83,9 @@ object ExtractAlignedFastq extends ToolCommand {
require(inAlnReader.hasIndex)
def getSequenceIndex(name: String): Int = inAlnReader.getFileHeader.getSequenceIndex(name) match {
- case x if x >= 0 =>
+ case x if x >= 0 =>
x
- case otherwise =>
+ case otherwise =>
throw new IllegalArgumentException("Chromosome " + name + " is not found in the alignment file")
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala
index c59d8a2464797f03eca4e0f7b2d6c3e0965ab624..9a95d2435c6ad44020a0438cac8ed3e7ce55df8c 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala
@@ -24,22 +24,24 @@ class FastqSplitter(val root: Configurable) extends BiopetJavaCommandLineFunctio
}
object FastqSplitter extends ToolCommand {
- case class Args (inputFile:File = null, outputFile:List[File] = Nil) extends AbstractArgs
+ case class Args(inputFile: File = null, outputFile: List[File] = Nil) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required() valueName("<file>") action { (x, c) =>
- c.copy(inputFile = x) } text("out is a required file property")
- opt[File]('o', "output") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(outputFile = x :: c.outputFile) } text("out is a required file property")
+ opt[File]('I', "inputFile") required () valueName ("<file>") action { (x, c) =>
+ c.copy(inputFile = x)
+ } text ("out is a required file property")
+ opt[File]('o', "output") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(outputFile = x :: c.outputFile)
+ } text ("out is a required file property")
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
- val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+ val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
+
val groupsize = 100
val output = for (file <- commandArgs.outputFile) yield new PrintWriter(file)
val inputStream = {
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala
index add0849bc4e60e4df8662c5432dad0c197b26631..b6c9690bc90b45c2f9376f69b574e73157f39f06 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala
@@ -26,40 +26,44 @@ import scala.io.Source
import scala.collection.JavaConversions._
object FindRepeatsPacBio extends ToolCommand {
- case class Args (inputBam:File = null, inputBed:File = null) extends AbstractArgs
+ case class Args(inputBam: File = null, inputBed: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputBam") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(inputBam = x) }
- opt[File]('b', "inputBed") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(inputBed = x) } text("output file, default to stdout")
+ opt[File]('I', "inputBam") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(inputBam = x)
+ }
+ opt[File]('b', "inputBed") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(inputBed = x)
+ } text ("output file, default to stdout")
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
-
+
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
val bamReader = new SAMFileReader(commandArgs.inputBam)
bamReader.setValidationStringency(ValidationStringency.SILENT)
val bamHeader = bamReader.getFileHeader
-
- val header = List("chr", "startPos", "stopPos","Repeat_seq", "repeatLength",
- "original_Repeat_readLength", "Calculated_repeat_readLength",
- "minLength", "maxLength", "inserts", "deletions", "notSpan")
+
+ val header = List("chr", "startPos", "stopPos", "Repeat_seq", "repeatLength",
+ "original_Repeat_readLength", "Calculated_repeat_readLength",
+ "minLength", "maxLength", "inserts", "deletions", "notSpan")
println(header.mkString("\t"))
-
- for (bedLine <- Source.fromFile(commandArgs.inputBed).getLines;
- val values = bedLine.split("\t"); if values.size >= 3) {
+
+ for (
+ bedLine <- Source.fromFile(commandArgs.inputBed).getLines;
+ val values = bedLine.split("\t"); if values.size >= 3
+ ) {
val interval = new QueryInterval(bamHeader.getSequenceIndex(values(0)), values(1).toInt, values(2).toInt)
val bamIter = bamReader.query(Array(interval), false)
- val results = for (samRecord <-bamIter) yield procesSamrecord(samRecord, interval)
+ val results = for (samRecord <- bamIter) yield procesSamrecord(samRecord, interval)
val chr = values(0)
val startPos = values(1)
val stopPos = values(2)
- val typeRepeat: String = if (values.size >= 15) values(14) else ""
+ val typeRepeat: String = if (values.size >= 15) values(14) else ""
val repeatLength = typeRepeat.length
val oriRepeatLength = values(2).toInt - values(1).toInt + 1
var calcRepeatLength: List[Int] = Nil
@@ -68,48 +72,48 @@ object FindRepeatsPacBio extends ToolCommand {
var inserts: List[String] = Nil
var deletions: List[String] = Nil
var notSpan = 0
-
+
for (result <- results) {
if (result.isEmpty) notSpan += 1
else {
inserts ::= result.get.ins.map(_.insert).mkString(",")
deletions ::= result.get.dels.map(_.length).mkString(",")
- val length = oriRepeatLength - result.get.beginDel - result.get.endDel -
- ((0 /: result.get.dels.map(_.length)) (_ + _)) + ((0 /: result.get.ins.map(_.insert.size)) (_ + _))
+ val length = oriRepeatLength - result.get.beginDel - result.get.endDel -
+ ((0 /: result.get.dels.map(_.length))(_ + _)) + ((0 /: result.get.ins.map(_.insert.size))(_ + _))
calcRepeatLength ::= length
if (length > maxLength) maxLength = length
if (length < minLength || minLength == -1) minLength = length
}
}
- println(List(chr, startPos, stopPos, typeRepeat, repeatLength, oriRepeatLength, calcRepeatLength.mkString(","), minLength,
- maxLength, inserts.mkString("/"), deletions.mkString("/"), notSpan).mkString("\t"))
+ println(List(chr, startPos, stopPos, typeRepeat, repeatLength, oriRepeatLength, calcRepeatLength.mkString(","), minLength,
+ maxLength, inserts.mkString("/"), deletions.mkString("/"), notSpan).mkString("\t"))
bamIter.close
}
}
-
- case class Del(pos:Int, length:Int)
- case class Ins(pos:Int, insert:String)
-
+
+ case class Del(pos: Int, length: Int)
+ case class Ins(pos: Int, insert: String)
+
class Result() {
var beginDel = 0
var endDel = 0
var dels: List[Del] = Nil
var ins: List[Ins] = Nil
var samRecord: SAMRecord = _
-
+
override def toString = {
- "id: " + samRecord.getReadName + " beginDel: " + beginDel + " endDel: " + endDel + " dels: " + dels + " ins: " + ins
+ "id: " + samRecord.getReadName + " beginDel: " + beginDel + " endDel: " + endDel + " dels: " + dels + " ins: " + ins
}
}
-
- def procesSamrecord(samRecord:SAMRecord, interval:QueryInterval): Option[Result] = {
+
+ def procesSamrecord(samRecord: SAMRecord, interval: QueryInterval): Option[Result] = {
val readStartPos = List.range(0, samRecord.getReadBases.length)
- .find(x => samRecord.getReferencePositionAtReadPosition(x) >= interval.start)
+ .find(x => samRecord.getReferencePositionAtReadPosition(x) >= interval.start)
var readPos = if (readStartPos.isEmpty) return None else readStartPos.get
if (samRecord.getAlignmentEnd < interval.end) return None
if (samRecord.getAlignmentStart > interval.start) return None
var refPos = samRecord.getReferencePositionAtReadPosition(readPos)
-
+
val result = new Result
result.samRecord = samRecord
result.beginDel = interval.start - refPos
@@ -119,19 +123,19 @@ object FindRepeatsPacBio extends ToolCommand {
do {
readPos += 1
refPos = samRecord.getReferencePositionAtReadPosition(readPos)
- } while(refPos < oldReadPos)
+ } while (refPos < oldReadPos)
val readDiff = readPos - oldReadPos
val refDiff = refPos - oldRefPos
if (refPos > interval.end) {
result.endDel = interval.end - oldRefPos
} else if (readDiff > refDiff) { //Insertion
- val insert = for (t <- oldReadPos+1 until readPos) yield samRecord.getReadBases()(t-1).toChar
+ val insert = for (t <- oldReadPos + 1 until readPos) yield samRecord.getReadBases()(t - 1).toChar
result.ins ::= Ins(oldRefPos, insert.mkString)
} else if (readDiff < refDiff) { // Deletion
result.dels ::= Del(oldRefPos, refDiff - readDiff)
}
}
-
+
return Some(result)
}
}
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 a407a64de28c47de0a2c53033793a4b3c4f15a5e..52b5df3f5c5f0d9f6c007e00a48722aece6785ee 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
@@ -15,82 +15,89 @@ import scala.collection.JavaConversions._
class MpileupToVcf(val root: Configurable) extends BiopetJavaCommandLineFunction {
javaMainClass = getClass.getName
-
+
@Input(doc = "Input mpileup file", shortName = "mpileup", required = false)
var inputMpileup: File = _
-
+
@Input(doc = "Input bam file", shortName = "bam", required = false)
var inputBam: File = _
-
+
@Output(doc = "Output tag library", shortName = "output", required = true)
var output: File = _
-
- var minDP:Option[Int] = config("min_dp")
- var minAP:Option[Int] = config("min_ap")
- var homoFraction:Option[Double] = config("homoFraction")
- var ploidy:Option[Int] = config("ploidy")
+
+ var minDP: Option[Int] = config("min_dp")
+ var minAP: Option[Int] = config("min_ap")
+ var homoFraction: Option[Double] = config("homoFraction")
+ var ploidy: Option[Int] = config("ploidy")
var sample: String = _
var reference: String = config("reference")
-
+
override val defaultVmem = "6G"
memoryLimit = Option(2.0)
-
+
if (config.contains("target_bed")) defaults ++= Map("samtoolsmpileup" -> Map("interval_bed" -> config("target_bed").getStringList.head,
- "disable_baq" -> true, "min_map_quality" -> 1))
-
+ "disable_baq" -> true, "min_map_quality" -> 1))
+
override def afterGraph {
super.afterGraph
val samtoolsMpileup = new SamtoolsMpileup(this)
}
-
+
override def commandLine = {
(if (inputMpileup == null) {
val samtoolsMpileup = new SamtoolsMpileup(this)
samtoolsMpileup.input = inputBam
samtoolsMpileup.cmdPipe + " | "
- } else "") +
- super.commandLine +
- required("-o", output) +
- optional("--minDP", minDP) +
+ } else "") +
+ super.commandLine +
+ required("-o", output) +
+ optional("--minDP", minDP) +
optional("--minAP", minAP) +
optional("--homoFraction", homoFraction) +
optional("--ploidy", ploidy) +
- required("--sample", sample) +
+ required("--sample", sample) +
(if (inputBam == null) required("-I", inputMpileup) else "")
}
}
object MpileupToVcf extends ToolCommand {
- case class Args (input:File = null, output:File = null, sample:String = null, minDP:Int = 8, minAP:Int = 2,
- homoFraction:Double = 0.8, ploidy:Int = 2) extends AbstractArgs
+ case class Args(input: File = null, output: File = null, sample: String = null, minDP: Int = 8, minAP: Int = 2,
+ homoFraction: Double = 0.8, ploidy: Int = 2) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") valueName("<file>") action { (x, c) =>
- c.copy(input = x) } text("input, default is stdin")
- opt[File]('o', "output") required() valueName("<file>") action { (x, c) =>
- c.copy(output = x) } text("out is a required file property")
- opt[String]('s', "sample") required() action { (x, c) =>
- c.copy(sample = x) }
- opt[Int]("minDP") required() action { (x, c) =>
- c.copy(minDP = x) }
- opt[Int]("minAP") required() action { (x, c) =>
- c.copy(minAP = x) }
- opt[Double]("homoFraction") required() action { (x, c) =>
- c.copy(homoFraction = x) }
- opt[Int]("ploidy") required() action { (x, c) =>
- c.copy(ploidy = x) }
+ opt[File]('I', "input") valueName ("<file>") action { (x, c) =>
+ c.copy(input = x)
+ } text ("input, default is stdin")
+ opt[File]('o', "output") required () valueName ("<file>") action { (x, c) =>
+ c.copy(output = x)
+ } text ("out is a required file property")
+ opt[String]('s', "sample") required () action { (x, c) =>
+ c.copy(sample = x)
+ }
+ opt[Int]("minDP") required () action { (x, c) =>
+ c.copy(minDP = x)
+ }
+ opt[Int]("minAP") required () action { (x, c) =>
+ c.copy(minAP = x)
+ }
+ opt[Double]("homoFraction") required () action { (x, c) =>
+ c.copy(homoFraction = x)
+ }
+ opt[Int]("ploidy") required () action { (x, c) =>
+ c.copy(ploidy = x)
+ }
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
import scala.collection.mutable.Map
if (commandArgs.input != null && !commandArgs.input.exists) throw new IllegalStateException("Input file does not exist")
-
+
val writer = new PrintWriter(commandArgs.output)
writer.println("##fileformat=VCFv4.1")
writer.println("##INFO=<ID=DP,Number=1,Type=Integer,Description=\"Total Depth\">")
@@ -105,83 +112,85 @@ object MpileupToVcf extends ToolCommand {
writer.println("##FORMAT=<ID=GT,Number=1,Type=String,Description=\"Genotype\">")
writer.println("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t" + commandArgs.sample)
val inputStream = if (commandArgs.input != null) Source.fromFile(commandArgs.input).getLines else Source.stdin.getLines
- class Counts(var forward:Int, var reverse:Int)
- for (line <- inputStream;
- val values = line.split("\t");
- if values.size > 5) {
+ class Counts(var forward: Int, var reverse: Int)
+ for (
+ line <- inputStream;
+ val values = line.split("\t");
+ if values.size > 5
+ ) {
val chr = values(0)
val pos = values(1)
val ref = values(2)
val reads = values(3).toInt
val mpileup = values(4)
val qual = values(5)
-
- val counts: Map[String, Counts] = Map(ref.toUpperCase -> new Counts(0,0))
-
- def addCount(s:String) {
+
+ val counts: Map[String, Counts] = Map(ref.toUpperCase -> new Counts(0, 0))
+
+ def addCount(s: String) {
val upper = s.toUpperCase
- if (!counts.contains(upper)) counts += upper -> new Counts(0,0)
+ if (!counts.contains(upper)) counts += upper -> new Counts(0, 0)
if (s(0).isLower) counts(upper).reverse += 1
else counts(upper).forward += 1
}
-
+
var t = 0
var dels = 0
- while(t < mpileup.size) {
+ while (t < mpileup.size) {
mpileup(t) match {
case ',' => {
- addCount(ref.toLowerCase)
- t += 1
+ addCount(ref.toLowerCase)
+ t += 1
}
case '.' => {
- addCount(ref.toUpperCase)
- t += 1
+ addCount(ref.toUpperCase)
+ t += 1
}
case '^' => t += 2
case '$' => t += 1
case '*' => {
- dels += 1
- t += 1
+ dels += 1
+ t += 1
}
case '+' | '-' => {
+ t += 1
+ var size = ""
+ var insert = ""
+ while (mpileup(t).isDigit) {
+ size += mpileup(t)
t += 1
- var size = ""
- var insert = ""
- while (mpileup(t).isDigit) {
- size += mpileup(t)
- t += 1
- }
- for (c <- t until t + size.toInt) insert = insert + mpileup(c)
- t += size.toInt
+ }
+ for (c <- t until t + size.toInt) insert = insert + mpileup(c)
+ t += size.toInt
}
- case 'a' | 'c' | 't' | 'g' | 'A' | 'C' | 'T' | 'G' => {
- addCount(mpileup(t).toString)
- t += 1
+ case 'a' | 'c' | 't' | 'g' | 'A' | 'C' | 'T' | 'G' => {
+ addCount(mpileup(t).toString)
+ t += 1
}
case _ => t += 1
}
}
-
+
val info: ArrayBuffer[String] = ArrayBuffer("DP=" + reads)
val format: Map[String, String] = Map("DP" -> reads.toString)
val alt: ArrayBuffer[String] = new ArrayBuffer
format += ("RFC" -> counts(ref.toUpperCase).forward.toString)
format += ("RRC" -> counts(ref.toUpperCase).reverse.toString)
format += ("AD" -> (counts(ref.toUpperCase).forward + counts(ref.toUpperCase).reverse).toString)
- if (reads >= commandArgs.minDP) for ((key, value) <- counts if key != ref.toUpperCase if value.forward+value.reverse >= commandArgs.minAP) {
+ if (reads >= commandArgs.minDP) for ((key, value) <- counts if key != ref.toUpperCase if value.forward + value.reverse >= commandArgs.minAP) {
alt += key
format += ("AD" -> (format("AD") + "," + (value.forward + value.reverse).toString))
- format += ("AFC" -> ( (if (format.contains("AFC")) format("AFC") + "," else "") + value.forward))
- format += ("ARC" -> ( (if (format.contains("ARC")) format("ARC") + "," else "") + value.reverse))
- format += ("FREQ" -> ( (if (format.contains("FREQ")) format("FREQ") + "," else "") +
- round((value.forward+value.reverse).toDouble/reads*1E4).toDouble/1E2))
+ format += ("AFC" -> ((if (format.contains("AFC")) format("AFC") + "," else "") + value.forward))
+ format += ("ARC" -> ((if (format.contains("ARC")) format("ARC") + "," else "") + value.reverse))
+ format += ("FREQ" -> ((if (format.contains("FREQ")) format("FREQ") + "," else "") +
+ round((value.forward + value.reverse).toDouble / reads * 1E4).toDouble / 1E2))
}
-
+
if (alt.size > 0) {
val ad = for (ad <- format("AD").split(",")) yield ad.toInt
var left = reads - dels
val gt = ArrayBuffer[Int]()
-
+
for (p <- 0 to alt.size if gt.size < commandArgs.ploidy) {
var max = -1
for (a <- 0 until ad.length if ad(a) > (if (max >= 0) ad(max) else -1) && !gt.exists(_ == a)) max = a
@@ -192,9 +201,9 @@ object MpileupToVcf extends ToolCommand {
}
left -= ad(max)
}
- writer.println(Array(chr, pos, ".", ref.toUpperCase, alt.mkString(","), ".", ".", info.mkString(";"),
- "GT:" + format.keys.mkString(":"), gt.sortWith(_ < _).mkString("/") + ":" + format.values.mkString(":")
- ).mkString("\t"))
+ writer.println(Array(chr, pos, ".", ref.toUpperCase, alt.mkString(","), ".", ".", info.mkString(";"),
+ "GT:" + format.keys.mkString(":"), gt.sortWith(_ < _).mkString("/") + ":" + format.values.mkString(":")
+ ).mkString("\t"))
}
}
writer.close
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
index a07cc4b8bb8eb73aeb00d1dbc2b2880b761b6acc..b2b10550328709ed41745005d5ce8a410fd8d4ac 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
@@ -6,7 +6,7 @@ import nl.lumc.sasc.biopet.core.BiopetJavaCommandLineFunction
import nl.lumc.sasc.biopet.core.ToolCommand
import nl.lumc.sasc.biopet.core.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-import org.biojava3.sequencing.io.fastq.{SangerFastqReader, StreamListener, Fastq}
+import org.biojava3.sequencing.io.fastq.{ SangerFastqReader, StreamListener, Fastq }
import scala.collection.JavaConversions._
import scala.collection.SortedMap
import scala.collection.mutable.Map
@@ -17,44 +17,46 @@ class SageCountFastq(val root: Configurable) extends BiopetJavaCommandLineFuncti
@Input(doc = "Input fasta", shortName = "input", required = true)
var input: File = _
-
+
@Output(doc = "Output tag library", shortName = "output", required = true)
var output: File = _
-
+
override val defaultVmem = "8G"
memoryLimit = Option(4.0)
-
- override def commandLine = super.commandLine +
- required("-I", input) +
+
+ override def commandLine = super.commandLine +
+ required("-I", input) +
required("-o", output)
}
object SageCountFastq extends ToolCommand {
- case class Args (input:File = null, output:File = null) extends AbstractArgs
+ case class Args(input: File = null, output: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") required() valueName("<file>") action { (x, c) =>
- c.copy(input = x) }
- opt[File]('o', "output") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(output = x) }
+ opt[File]('I', "input") required () valueName ("<file>") action { (x, c) =>
+ c.copy(input = x)
+ }
+ opt[File]('o', "output") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(output = x)
+ }
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
-
- val counts:Map[String, Long] = Map()
+
+ val counts: Map[String, Long] = Map()
val reader = new SangerFastqReader
var count = 0
logger.info("Reading fastq file: " + commandArgs.input)
val fileReader = new FileReader(commandArgs.input)
reader.stream(fileReader, new StreamListener {
- def fastq(fastq:Fastq) {
+ def fastq(fastq: Fastq) {
val seq = fastq.getSequence
if (counts.contains(seq)) counts(seq) += 1
else counts += (seq -> 1)
@@ -63,13 +65,13 @@ object SageCountFastq extends ToolCommand {
}
})
logger.info(count + " sequences done")
-
+
logger.info("Sorting")
- val sortedCounts:SortedMap[String, Long] = SortedMap(counts.toArray:_*)
-
+ val sortedCounts: SortedMap[String, Long] = SortedMap(counts.toArray: _*)
+
logger.info("Writting outputfile: " + commandArgs.output)
val writer = new PrintWriter(commandArgs.output)
- for ((seq,count) <- sortedCounts) {
+ for ((seq, count) <- sortedCounts) {
writer.println(seq + "\t" + count)
}
writer.close
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala
index b339ab2471e756e654fbbe621e15a1ac7f5a36cb..61336896ed4c8f2a3140ba6143060ab6f5bd1ef4 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala
@@ -9,7 +9,7 @@ import org.biojava3.core.sequence.DNASequence
import org.biojava3.core.sequence.io.FastaReaderHelper
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import scala.collection.SortedMap
-import scala.collection.mutable.{Map, Set}
+import scala.collection.mutable.{ Map, Set }
import scala.collection.JavaConversions._
import scala.util.matching.Regex
@@ -18,28 +18,28 @@ class SageCreateLibrary(val root: Configurable) extends BiopetJavaCommandLineFun
@Input(doc = "Input fasta", shortName = "input", required = true)
var input: File = _
-
+
@Output(doc = "Output tag library", shortName = "output", required = true)
var output: File = _
-
+
@Output(doc = "Output no tags", shortName = "noTagsOutput", required = false)
var noTagsOutput: File = _
-
+
@Output(doc = "Output no anti tags library", shortName = "noAntiTagsOutput", required = false)
var noAntiTagsOutput: File = _
-
+
@Output(doc = "Output file all genes", shortName = "allGenes", required = false)
var allGenesOutput: File = _
-
+
var tag: String = config("tag", default = "CATG")
var length: Option[Int] = config("length", default = 17)
-
+
override val defaultVmem = "8G"
memoryLimit = Option(4.0)
-
- override def commandLine = super.commandLine +
- required("-I", input) +
- optional("--tag", tag) +
+
+ override def commandLine = super.commandLine +
+ required("-I", input) +
+ optional("--tag", tag) +
optional("--length", length) +
optional("--notag", noTagsOutput) +
optional("--noantitag", noAntiTagsOutput) +
@@ -47,54 +47,61 @@ class SageCreateLibrary(val root: Configurable) extends BiopetJavaCommandLineFun
}
object SageCreateLibrary extends ToolCommand {
- case class Args (input:File = null, tag:String = "CATG", length:Int = 17,output:File = null, noTagsOutput:File = null,
- noAntiTagsOutput:File = null, allGenesOutput:File = null) extends AbstractArgs
+ case class Args(input: File = null, tag: String = "CATG", length: Int = 17, output: File = null, noTagsOutput: File = null,
+ noAntiTagsOutput: File = null, allGenesOutput: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(input = x) }
- opt[File]('o', "output") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(output = x) }
- opt[String]("tag") required() unbounded() action { (x, c) =>
- c.copy(tag = x) }
- opt[Int]("length") required() unbounded() action { (x, c) =>
- c.copy(length = x) }
- opt[File]("noTagsOutput") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(noTagsOutput = x) }
- opt[File]("noAntiTagsOutput") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(noAntiTagsOutput = x) }
- opt[File]("allGenesOutput") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(allGenesOutput = x) }
+ opt[File]('I', "input") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(input = x)
+ }
+ opt[File]('o', "output") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(output = x)
+ }
+ opt[String]("tag") required () unbounded () action { (x, c) =>
+ c.copy(tag = x)
+ }
+ opt[Int]("length") required () unbounded () action { (x, c) =>
+ c.copy(length = x)
+ }
+ opt[File]("noTagsOutput") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(noTagsOutput = x)
+ }
+ opt[File]("noAntiTagsOutput") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(noAntiTagsOutput = x)
+ }
+ opt[File]("allGenesOutput") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(allGenesOutput = x)
+ }
}
-
+
var tagRegex: Regex = null
var geneRegex = """ENSG[0-9]{11}""".r
-
+
val tagGenesMap: Map[String, TagGenes] = Map()
-
+
val allGenes: Set[String] = Set()
val tagGenes: Set[String] = Set()
val antiTagGenes: Set[String] = Set()
-
+
class TagGenes {
val firstTag: Set[String] = Set()
- val allTags:Set[String] = Set()
+ val allTags: Set[String] = Set()
val firstAntiTag: Set[String] = Set()
- val allAntiTags:Set[String] = Set()
+ val allAntiTags: Set[String] = Set()
}
- class TagResult( val firstTag: String, val allTags:List[String], val firstAntiTag: String, val allAntiTags:List[String] )
-
+ class TagResult(val firstTag: String, val allTags: List[String], val firstAntiTag: String, val allAntiTags: List[String])
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
-
+
tagRegex = (commandArgs.tag + "[CATG]{" + commandArgs.length + "}").r
-
+
var count = 0
System.err.println("Reading fasta file")
val reader = FastaReaderHelper.readFastaDNASequence(commandArgs.input)
@@ -105,22 +112,22 @@ object SageCreateLibrary extends ToolCommand {
if (count % 10000 == 0) System.err.println(count + " transcripts done")
}
System.err.println(count + " transcripts done")
-
+
System.err.println("Start sorting tags")
- val tagGenesMapSorted:SortedMap[String, TagGenes] = SortedMap(tagGenesMap.toArray:_*)
-
+ val tagGenesMapSorted: SortedMap[String, TagGenes] = SortedMap(tagGenesMap.toArray: _*)
+
System.err.println("Writting output files")
val writer = new PrintWriter(commandArgs.output)
writer.println("#tag\tfirstTag\tAllTags\tFirstAntiTag\tAllAntiTags")
for ((tag, genes) <- tagGenesMapSorted) {
val line = tag + "\t" + genes.firstTag.mkString(",") +
- "\t" + genes.allTags.mkString(",") +
- "\t" + genes.firstAntiTag.mkString(",") +
- "\t" + genes.allAntiTags.mkString(",")
+ "\t" + genes.allTags.mkString(",") +
+ "\t" + genes.firstAntiTag.mkString(",") +
+ "\t" + genes.allAntiTags.mkString(",")
writer.println(line)
}
writer.close()
-
+
if (commandArgs.noTagsOutput != null) {
val writer = new PrintWriter(commandArgs.noTagsOutput)
for (gene <- allGenes if !tagGenes.contains(gene)) {
@@ -128,7 +135,7 @@ object SageCreateLibrary extends ToolCommand {
}
writer.close
}
-
+
if (commandArgs.noAntiTagsOutput != null) {
val writer = new PrintWriter(commandArgs.noAntiTagsOutput)
for (gene <- allGenes if !antiTagGenes.contains(gene)) {
@@ -136,7 +143,7 @@ object SageCreateLibrary extends ToolCommand {
}
writer.close
}
-
+
if (commandArgs.allGenesOutput != null) {
val writer = new PrintWriter(commandArgs.allGenesOutput)
for (gene <- allGenes) {
@@ -145,44 +152,44 @@ object SageCreateLibrary extends ToolCommand {
writer.close
}
}
-
- def addTagresultToTaglib(name:String, tagResult:TagResult) {
+
+ def addTagresultToTaglib(name: String, tagResult: TagResult) {
val id = name.split(" ").head //.stripPrefix("hg19_ensGene_")
val geneID = geneRegex.findFirstIn(name).getOrElse("unknown_gene")
allGenes.add(geneID)
-
+
if (tagResult.firstTag != null) {
if (!tagGenesMap.contains(tagResult.firstTag)) tagGenesMap += (tagResult.firstTag -> new TagGenes)
tagGenesMap(tagResult.firstTag).firstTag.add(geneID)
tagGenes.add(geneID)
}
-
+
for (tag <- tagResult.allTags) {
if (!tagGenesMap.contains(tag)) tagGenesMap += (tag -> new TagGenes)
tagGenesMap(tag).allTags.add(geneID)
}
-
+
if (tagResult.firstAntiTag != null) {
if (!tagGenesMap.contains(tagResult.firstAntiTag)) tagGenesMap += (tagResult.firstAntiTag -> new TagGenes)
tagGenesMap(tagResult.firstAntiTag).firstAntiTag.add(geneID)
antiTagGenes.add(geneID)
}
-
+
for (tag <- tagResult.allAntiTags) {
if (!tagGenesMap.contains(tag)) tagGenesMap += (tag -> new TagGenes)
tagGenesMap(tag).allAntiTags.add(geneID)
}
}
-
- def getTags(name:String, seq: DNASequence): TagResult = {
+
+ def getTags(name: String, seq: DNASequence): TagResult = {
val allTags: List[String] = for (tag <- tagRegex.findAllMatchIn(seq.getSequenceAsString).toList) yield tag.toString
val firstTag = if (allTags.isEmpty) null else allTags.last
val allAntiTags: List[String] = for (tag <- tagRegex.findAllMatchIn(seq.getReverseComplement.getSequenceAsString).toList) yield tag.toString
- val firstAntiTag = if (allAntiTags.isEmpty) null else allAntiTags.head
+ val firstAntiTag = if (allAntiTags.isEmpty) null else allAntiTags.head
val result = new TagResult(firstTag, allTags, firstAntiTag, allAntiTags)
-
+
addTagresultToTaglib(name, result)
-
+
return result
}
}
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala
index 1bfc6e0f8606c3ed14576791f9ac50a8cfa99b04..eba1ff87f3984f5996071059dd9f05dd2163ab71 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala
@@ -15,62 +15,68 @@ class SageCreateTagCounts(val root: Configurable) extends BiopetJavaCommandLineF
@Input(doc = "Raw count file", shortName = "input", required = true)
var input: File = _
-
+
@Input(doc = "tag library", shortName = "taglib", required = true)
var tagLib: File = _
-
+
@Output(doc = "Sense count file", shortName = "sense", required = true)
var countSense: File = _
-
+
@Output(doc = "Sense all coun filet", shortName = "allsense", required = true)
var countAllSense: File = _
-
+
@Output(doc = "AntiSense count file", shortName = "antisense", required = true)
var countAntiSense: File = _
-
+
@Output(doc = "AntiSense all count file", shortName = "allantisense", required = true)
var countAllAntiSense: File = _
-
+
override val defaultVmem = "8G"
memoryLimit = Option(4.0)
-
- override def commandLine = super.commandLine +
- required("-I", input) +
- required("--taglib", tagLib) +
- optional("--sense", countSense) +
- optional("--allsense", countAllSense) +
- optional("--antisense", countAntiSense) +
+
+ override def commandLine = super.commandLine +
+ required("-I", input) +
+ required("--taglib", tagLib) +
+ optional("--sense", countSense) +
+ optional("--allsense", countAllSense) +
+ optional("--antisense", countAntiSense) +
optional("--allantisense", countAllAntiSense)
}
object SageCreateTagCounts extends ToolCommand {
- case class Args (input:File = null, tagLib:File = null, countSense:File = null, countAllSense:File = null,
- countAntiSense:File = null, countAllAntiSense:File = null) extends AbstractArgs
+ case class Args(input: File = null, tagLib: File = null, countSense: File = null, countAllSense: File = null,
+ countAntiSense: File = null, countAllAntiSense: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(input = x) }
- opt[File]('t', "tagLib") required() unbounded() valueName("<file>") action { (x, c) =>
- c.copy(tagLib = x) }
- opt[File]("countSense") unbounded() valueName("<file>") action { (x, c) =>
- c.copy(countSense = x) }
- opt[File]("countAllSense") unbounded() valueName("<file>") action { (x, c) =>
- c.copy(countAllSense = x) }
- opt[File]("countAntiSense") unbounded() valueName("<file>") action { (x, c) =>
- c.copy(countAntiSense = x) }
- opt[File]("countAllAntiSense") unbounded() valueName("<file>") action { (x, c) =>
- c.copy(countAllAntiSense = x) }
+ opt[File]('I', "input") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(input = x)
+ }
+ opt[File]('t', "tagLib") required () unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(tagLib = x)
+ }
+ opt[File]("countSense") unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(countSense = x)
+ }
+ opt[File]("countAllSense") unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(countAllSense = x)
+ }
+ opt[File]("countAntiSense") unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(countAntiSense = x)
+ }
+ opt[File]("countAllAntiSense") unbounded () valueName ("<file>") action { (x, c) =>
+ c.copy(countAllAntiSense = x)
+ }
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
-
+
val rawCounts: Map[String, Long] = Map()
for (line <- Source.fromFile(commandArgs.input).getLines) {
val values = line.split("\t")
@@ -79,50 +85,50 @@ object SageCreateTagCounts extends ToolCommand {
if (rawCounts.contains(gene)) rawCounts(gene) += count
else rawCounts += gene -> count
}
-
+
val senseCounts: Map[String, Long] = Map()
val allSenseCounts: Map[String, Long] = Map()
val antiSenseCounts: Map[String, Long] = Map()
val allAntiSenseCounts: Map[String, Long] = Map()
-
+
for (line <- Source.fromFile(commandArgs.tagLib).getLines if !line.startsWith("#")) {
val values = line.split("\t")
- val tag = values(0)
+ val tag = values(0)
val sense = values(1)
val allSense = values(2)
val antiSense = if (values.size > 3) values(3) else ""
val allAntiSense = if (values.size > 4) values(4) else ""
-
+
if (!sense.isEmpty && !sense.contains(",")) {
val count = if (rawCounts.contains(tag)) rawCounts(tag) else 0
if (senseCounts.contains(sense)) senseCounts(sense) += count
else senseCounts += sense -> count
}
-
+
if (!allSense.isEmpty && !allSense.contains(",")) {
val count = if (rawCounts.contains(tag)) rawCounts(tag) else 0
if (allSenseCounts.contains(allSense)) allSenseCounts(allSense) += count
else allSenseCounts += allSense -> count
}
-
+
if (!antiSense.isEmpty && !antiSense.contains(",")) {
val count = if (rawCounts.contains(tag)) rawCounts(tag) else 0
if (antiSenseCounts.contains(antiSense)) antiSenseCounts(antiSense) += count
else antiSenseCounts += antiSense -> count
}
-
+
if (!allAntiSense.isEmpty && !allAntiSense.contains(",")) {
val count = if (rawCounts.contains(tag)) rawCounts(tag) else 0
if (allAntiSenseCounts.contains(allAntiSense)) allAntiSenseCounts(allAntiSense) += count
else allAntiSenseCounts += allAntiSense -> count
}
}
-
- def writeFile(file:File, counts:Map[String, Long]) {
- val sorted: SortedMap[String,Long] = SortedMap(counts.toArray:_*)
+
+ def writeFile(file: File, counts: Map[String, Long]) {
+ val sorted: SortedMap[String, Long] = SortedMap(counts.toArray: _*)
if (file != null) {
val writer = new PrintWriter(file)
- for ((gene,count) <- sorted) {
+ for ((gene, count) <- sorted) {
if (count > 0) writer.println(gene + "\t" + count)
}
writer.close
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
index dfd93ff511ac2c64792722893fbb507f8cc6f61e..d9f9c8c49aad126d42d3538e3276274b66e83d2c 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
@@ -16,19 +16,19 @@ class VcfFilter(val root: Configurable) extends BiopetJavaCommandLineFunction {
@Input(doc = "Input vcf", shortName = "I", required = true)
var inputVcf: File = _
-
+
@Output(doc = "Output vcf", shortName = "o", required = false)
var outputVcf: File = _
-
+
var minSampleDepth: Option[Int] = _
var minTotalDepth: Option[Int] = _
var minAlternateDepth: Option[Int] = _
var minSamplesPass: Option[Int] = _
var filterRefCalls: Boolean = _
-
+
override val defaultVmem = "8G"
memoryLimit = Option(4.0)
-
+
override def afterGraph {
minSampleDepth = config("min_sample_depth")
minTotalDepth = config("min_total_depth")
@@ -36,82 +36,90 @@ class VcfFilter(val root: Configurable) extends BiopetJavaCommandLineFunction {
minSamplesPass = config("min_samples_pass")
filterRefCalls = config("filter_ref_calls")
}
-
- override def commandLine = super.commandLine +
- required("-I", inputVcf) +
+
+ override def commandLine = super.commandLine +
+ required("-I", inputVcf) +
required("-o", outputVcf) +
optional("--minSampleDepth", minSampleDepth) +
optional("--minTotalDepth", minTotalDepth) +
- optional("--minAlternateDepth", minAlternateDepth) +
+ optional("--minAlternateDepth", minAlternateDepth) +
optional("--minSamplesPass", minSamplesPass) +
conditional(filterRefCalls, "--filterRefCalls")
}
object VcfFilter extends ToolCommand {
- case class Args (inputVcf:File = null, outputVcf:File = null, minSampleDepth: Int = -1, minTotalDepth: Int = -1,
- minAlternateDepth: Int = -1, minSamplesPass: Int = 0, minBamAlternateDepth: Int = 0, filterRefCalls: Boolean = false) extends AbstractArgs
+ case class Args(inputVcf: File = null, outputVcf: File = null, minSampleDepth: Int = -1, minTotalDepth: Int = -1,
+ minAlternateDepth: Int = -1, minSamplesPass: Int = 0, minBamAlternateDepth: Int = 0, filterRefCalls: Boolean = false) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputVcf") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(inputVcf = x) }
- opt[File]('o', "outputVcf") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(outputVcf = x) } text("output file, default to stdout")
- opt[Int]("minSampleDepth") unbounded() action { (x, c) =>
- c.copy(minSampleDepth = x ) }
- opt[Int]("minTotalDepth") unbounded() action { (x, c) =>
- c.copy(minTotalDepth = x ) }
- opt[Int]("minAlternateDepth") unbounded() action { (x, c) =>
- c.copy(minAlternateDepth = x) }
- opt[Int]("minSamplesPass") unbounded() action { (x, c) =>
- c.copy(minSamplesPass = x) }
- opt[Int]("minBamAlternateDepth") unbounded() action { (x, c) =>
- c.copy(minBamAlternateDepth = x) }
- opt[Unit]("filterRefCalls") unbounded() action { (x, c) =>
- c.copy(filterRefCalls = true) }
+ opt[File]('I', "inputVcf") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(inputVcf = x)
+ }
+ opt[File]('o', "outputVcf") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(outputVcf = x)
+ } text ("output file, default to stdout")
+ opt[Int]("minSampleDepth") unbounded () action { (x, c) =>
+ c.copy(minSampleDepth = x)
+ }
+ opt[Int]("minTotalDepth") unbounded () action { (x, c) =>
+ c.copy(minTotalDepth = x)
+ }
+ opt[Int]("minAlternateDepth") unbounded () action { (x, c) =>
+ c.copy(minAlternateDepth = x)
+ }
+ opt[Int]("minSamplesPass") unbounded () action { (x, c) =>
+ c.copy(minSamplesPass = x)
+ }
+ opt[Int]("minBamAlternateDepth") unbounded () action { (x, c) =>
+ c.copy(minBamAlternateDepth = x)
+ }
+ opt[Unit]("filterRefCalls") unbounded () action { (x, c) =>
+ c.copy(filterRefCalls = true)
+ }
}
-
+
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
val reader = new VCFFileReader(commandArgs.inputVcf, false)
val header = reader.getFileHeader
val writer = new AsyncVariantContextWriter(new VariantContextWriterBuilder().setOutputFile(commandArgs.outputVcf).build)
writer.writeHeader(header)
-
+
val bamADFields = (for (line <- header.getInfoHeaderLines if line.getID.startsWith("BAM-AD-")) yield line.getID).toList
val bamDPFields = (for (line <- header.getInfoHeaderLines if line.getID.startsWith("BAM-DP-")) yield line.getID).toList
-
+
for (record <- reader) {
val genotypes = for (genotype <- record.getGenotypes) yield {
val DP = if (genotype.hasDP) genotype.getDP else -1
- val AD = if (genotype.hasAD) List(genotype.getAD:_*) else Nil
- DP >= commandArgs.minSampleDepth &&
- (if (!AD.isEmpty) AD.tail.count(_ >= commandArgs.minAlternateDepth) > 0 else true) &&
- !(commandArgs.filterRefCalls && genotype.isHomRef)
+ val AD = if (genotype.hasAD) List(genotype.getAD: _*) else Nil
+ DP >= commandArgs.minSampleDepth &&
+ (if (!AD.isEmpty) AD.tail.count(_ >= commandArgs.minAlternateDepth) > 0 else true) &&
+ !(commandArgs.filterRefCalls && genotype.isHomRef)
}
-
+
val bamADvalues = (for (field <- bamADFields) yield {
record.getAttribute(field, new ArrayList) match {
- case t:ArrayList[_] if t.length > 1 => {
- for (i <- 1 until t.size) yield {
- t(i) match {
- case a:Int => a > commandArgs.minBamAlternateDepth
- case a:String => a.toInt > commandArgs.minBamAlternateDepth
- case _ => false
- }
+ case t: ArrayList[_] if t.length > 1 => {
+ for (i <- 1 until t.size) yield {
+ t(i) match {
+ case a: Int => a > commandArgs.minBamAlternateDepth
+ case a: String => a.toInt > commandArgs.minBamAlternateDepth
+ case _ => false
}
+ }
}
case _ => List(false)
}
}).flatten
-
- if (record.getAttributeAsInt("DP", -1) >= commandArgs.minTotalDepth &&
- genotypes.count(_ == true) >= commandArgs.minSamplesPass &&
- (commandArgs.minBamAlternateDepth <= 0 || bamADvalues.count(_ == true) >= commandArgs.minSamplesPass))
+
+ if (record.getAttributeAsInt("DP", -1) >= commandArgs.minTotalDepth &&
+ genotypes.count(_ == true) >= commandArgs.minSamplesPass &&
+ (commandArgs.minBamAlternateDepth <= 0 || bamADvalues.count(_ == true) >= commandArgs.minSamplesPass))
writer.add(record)
}
reader.close
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala
index 3629ad74a4e8577aaf30f3d50f4183149a8d756d..1a5c374fca1990f33f321aaef8a8c3b2a9be3d83 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala
@@ -21,78 +21,85 @@ import java.io.File
import java.io.PrintStream
import nl.lumc.sasc.biopet.core.ToolCommand
import scala.collection.JavaConversions._
-import scala.collection.mutable.{Map, ListBuffer}
+import scala.collection.mutable.{ Map, ListBuffer }
class VcfToTsv {
// TODO: Queue wrapper
}
object VcfToTsv extends ToolCommand {
- case class Args (inputFile:File = null, outputFile:File = null, fields: List[String] = Nil, infoFields: List[String] = Nil,
- sampleFileds: List[String] = Nil, disableDefaults: Boolean = false,
- allInfo:Boolean = false, allFormat:Boolean = false) extends AbstractArgs
+ case class Args(inputFile: File = null, outputFile: File = null, fields: List[String] = Nil, infoFields: List[String] = Nil,
+ sampleFileds: List[String] = Nil, disableDefaults: Boolean = false,
+ allInfo: Boolean = false, allFormat: Boolean = false) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required() maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(inputFile = x) }
- opt[File]('o', "outputFile") maxOccurs(1) valueName("<file>") action { (x, c) =>
- c.copy(outputFile = x) } text("output file, default to stdout")
- opt[String]('f', "field") unbounded() action { (x, c) =>
- c.copy(fields = x :: c.fields) }
- opt[String]('i', "info_field") unbounded() action { (x, c) =>
- c.copy(infoFields = x :: c.infoFields) }
- opt[Unit]("all_info") unbounded() action { (x, c) =>
- c.copy(allInfo = true) }
- opt[Unit]("all_format") unbounded() action { (x, c) =>
- c.copy(allFormat = true) }
- opt[String]('s', "sample_field") unbounded() action { (x, c) =>
- c.copy(sampleFileds = x :: c.sampleFileds) }
- opt[Unit]('d', "disable_defaults") unbounded() action { (x, c) =>
- c.copy(disableDefaults = true) }
+ opt[File]('I', "inputFile") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(inputFile = x)
+ }
+ opt[File]('o', "outputFile") maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ c.copy(outputFile = x)
+ } text ("output file, default to stdout")
+ opt[String]('f', "field") unbounded () action { (x, c) =>
+ c.copy(fields = x :: c.fields)
+ }
+ opt[String]('i', "info_field") unbounded () action { (x, c) =>
+ c.copy(infoFields = x :: c.infoFields)
+ }
+ opt[Unit]("all_info") unbounded () action { (x, c) =>
+ c.copy(allInfo = true)
+ }
+ opt[Unit]("all_format") unbounded () action { (x, c) =>
+ c.copy(allFormat = true)
+ }
+ opt[String]('s', "sample_field") unbounded () action { (x, c) =>
+ c.copy(sampleFileds = x :: c.sampleFileds)
+ }
+ opt[Unit]('d', "disable_defaults") unbounded () action { (x, c) =>
+ c.copy(disableDefaults = true)
+ }
}
-
+
val defaultFields = List("chr", "pos", "id", "ref", "alt", "qual")
-
+
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
-
+
val reader = new VCFFileReader(commandArgs.inputFile, false)
val header = reader.getFileHeader
val samples = header.getSampleNamesInOrder
-
+
val allInfoFields = header.getInfoHeaderLines.map(_.getID).toList
val allFormatFields = header.getFormatHeaderLines.map(_.getID).toList
-
- val fields: Set[String] = (if (commandArgs.disableDefaults) Nil else defaultFields).toSet[String] ++
- commandArgs.fields.toSet[String] ++
- (if (commandArgs.allInfo) allInfoFields else commandArgs.infoFields).map("INFO-"+_) ++ {
- val buffer: ListBuffer[String] = ListBuffer()
- for (f <- (if (commandArgs.allFormat) allFormatFields else commandArgs.sampleFileds); sample <- samples) {
- buffer += sample+"-"+f
+
+ val fields: Set[String] = (if (commandArgs.disableDefaults) Nil else defaultFields).toSet[String] ++
+ commandArgs.fields.toSet[String] ++
+ (if (commandArgs.allInfo) allInfoFields else commandArgs.infoFields).map("INFO-" + _) ++ {
+ val buffer: ListBuffer[String] = ListBuffer()
+ for (f <- (if (commandArgs.allFormat) allFormatFields else commandArgs.sampleFileds); sample <- samples) {
+ buffer += sample + "-" + f
+ }
+ buffer.toSet[String]
}
- buffer.toSet[String]
- }
-
- val sortedFields = fields.toList.sortWith((a,b) => {
- val aT = if (a.startsWith("INFO-")) 'i' else if (samples.exists(x => a.startsWith(x+"-"))) 'f' else 'g'
- val bT = if (b.startsWith("INFO-")) 'i' else if (samples.exists(x => b.startsWith(x+"-"))) 'f' else 'g'
+
+ val sortedFields = fields.toList.sortWith((a, b) => {
+ val aT = if (a.startsWith("INFO-")) 'i' else if (samples.exists(x => a.startsWith(x + "-"))) 'f' else 'g'
+ val bT = if (b.startsWith("INFO-")) 'i' else if (samples.exists(x => b.startsWith(x + "-"))) 'f' else 'g'
if (aT == 'g' && bT == 'g') {
val ai = defaultFields.indexOf(a)
val bi = defaultFields.indexOf(b)
if (bi < 0) true
else ai <= bi
- }
- else if (aT == 'g') true
+ } else if (aT == 'g') true
else if (bT == 'g') false
else if (aT == bT) (if (a.compareTo(b) > 0) false else true)
else if (aT == 'i') true
else false
})
-
+
val witter = if (commandArgs.outputFile != null) new PrintStream(commandArgs.outputFile)
else sys.process.stdout
-
+
witter.println(sortedFields.mkString("#", "\t", ""))
for (vcfRecord <- reader) {
val values: Map[String, Any] = Map()
@@ -104,36 +111,36 @@ object VcfToTsv extends ToolCommand {
val t = for (a <- vcfRecord.getAlternateAlleles) yield a.getBaseString
t.mkString(",")
}
- values += "qual" -> (if (vcfRecord.getPhredScaledQual == -10) "." else scala.math.round(vcfRecord.getPhredScaledQual*100.0)/100.0)
+ values += "qual" -> (if (vcfRecord.getPhredScaledQual == -10) "." else scala.math.round(vcfRecord.getPhredScaledQual * 100.0) / 100.0)
values += "filter" -> vcfRecord.getFilters
for ((field, content) <- vcfRecord.getAttributes) {
- values += "INFO-"+field -> {
+ values += "INFO-" + field -> {
content match {
- case a:List[_] => a.mkString(",")
- case a:Array[_] => a.mkString(",")
- case a:java.util.ArrayList[_] => a.mkString(",")
- case _ => content
+ case a: List[_] => a.mkString(",")
+ case a: Array[_] => a.mkString(",")
+ case a: java.util.ArrayList[_] => a.mkString(",")
+ case _ => content
}
}
}
-
+
for (sample <- samples) {
val genotype = vcfRecord.getGenotype(sample)
- values += sample+"-GT" -> {
+ values += sample + "-GT" -> {
val l = for (g <- genotype.getAlleles) yield vcfRecord.getAlleleIndex(g)
l.map(x => if (x < 0) "." else x).mkString("/")
}
- if (genotype.hasAD) values += sample+"-AD" -> List(genotype.getAD:_*).mkString(",")
- if (genotype.hasDP) values += sample+"-DP" -> genotype.getDP
- if (genotype.hasGQ )values += sample+"-GQ" -> genotype.getGQ
- if (genotype.hasPL) values += sample+"-PL" -> List(genotype.getPL:_*).mkString(",")
+ if (genotype.hasAD) values += sample + "-AD" -> List(genotype.getAD: _*).mkString(",")
+ if (genotype.hasDP) values += sample + "-DP" -> genotype.getDP
+ if (genotype.hasGQ) values += sample + "-GQ" -> genotype.getGQ
+ if (genotype.hasPL) values += sample + "-PL" -> List(genotype.getPL: _*).mkString(",")
for ((field, content) <- genotype.getExtendedAttributes) {
- values += sample+"-"+field -> content
+ values += sample + "-" + field -> content
}
}
val line = for (f <- sortedFields) yield {
- if (values.contains(f)) {
- values(f)
+ if (values.contains(f)) {
+ values(f)
} else ""
}
witter.println(line.mkString("\t"))
diff --git a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala
index d131692da08156dcc7b4fd085e71cb791bfca2c0..37eff846f598514b13d35003dfd8a191f0b1374f 100644
--- a/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala
+++ b/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala
@@ -8,7 +8,7 @@ import java.io.File
import scala.collection.JavaConverters._
-import com.google.common.hash.{Funnel, BloomFilter, PrimitiveSink}
+import com.google.common.hash.{ Funnel, BloomFilter, PrimitiveSink }
import htsjdk.samtools.AlignmentBlock
import htsjdk.samtools.SAMFileReader
import htsjdk.samtools.QueryInterval
@@ -106,13 +106,13 @@ object WipeReads extends ToolCommand {
/** Function to create iterator from refFlat file */
def makeFeatureFromRefFlat(inFile: File): Iterator[Feature] = ???
- // convert coordinate to 1-based fully closed
- // parse chrom, start blocks, end blocks, strands
+ // convert coordinate to 1-based fully closed
+ // parse chrom, start blocks, end blocks, strands
/** Function to create iterator from GTF file */
def makeFeatureFromGtf(inFile: File): Iterator[Feature] = ???
- // convert coordinate to 1-based fully closed
- // parse chrom, start blocks, end blocks, strands
+ // convert coordinate to 1-based fully closed
+ // parse chrom, start blocks, end blocks, strands
// detect interval file format from extension
val iterFunc: (File => Iterator[Feature]) =
@@ -252,7 +252,6 @@ object WipeReads extends ToolCommand {
else
(r: SAMRecord) => readGroupIds.contains(r.getReadGroup.getReadGroupId)
-
val readyBam = prepIndexedInputBam()
/* NOTE: the interval vector here should be bypass-able if we can make
@@ -285,11 +284,11 @@ object WipeReads extends ToolCommand {
.filter(x => rgFilter(x))
// fold starting from empty set
.foldLeft(BloomFilter.create(SAMFunnel, bloomSize.toInt, bloomFp)
- )((acc, rec) => {
- acc.put(rec)
- if (rec.getReadPairedFlag) acc.put(makeMockPair(rec))
- acc
- })
+ )((acc, rec) => {
+ acc.put(rec)
+ if (rec.getReadPairedFlag) acc.put(makeMockPair(rec))
+ acc
+ })
if (filterOutMulti)
(rec: SAMRecord) => filteredOutSet.mightContain(rec)
diff --git a/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/LnUnitTest.scala b/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/LnUnitTest.scala
index d82d70aef47603d0c7f0a0247b947671e135eca3..76c609094230185cead8dd01789b4604beb87342 100644
--- a/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/LnUnitTest.scala
+++ b/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/LnUnitTest.scala
@@ -19,7 +19,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = true
ln.in = new File("/dir/nested/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s 'target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s 'target.txt' '/dir/nested/link.txt'")
}
@Test(description = "Target is one level above link, relative set to true")
@@ -28,7 +28,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = true
ln.in = new File("/dir/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s '../target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s '../target.txt' '/dir/nested/link.txt'")
}
@Test(description = "Target is two levels above link, relative set to true")
@@ -37,7 +37,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = true
ln.in = new File("/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s '../../target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s '../../target.txt' '/dir/nested/link.txt'")
}
@Test(description = "Target is a child of a directory one level above link, relative set to true")
@@ -46,7 +46,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = true
ln.in = new File("/dir/another_nested/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s '../another_nested/target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s '../another_nested/target.txt' '/dir/nested/link.txt'")
}
@Test(description = "Target is one level below link, relative set to true")
@@ -55,7 +55,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = true
ln.in = new File("/dir/nested/deeper/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s 'deeper/target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s 'deeper/target.txt' '/dir/nested/link.txt'")
}
@Test(description = "Target is two levels below link, relative set to true")
@@ -64,7 +64,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = true
ln.in = new File("/dir/nested/even/deeper/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s 'even/deeper/target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s 'even/deeper/target.txt' '/dir/nested/link.txt'")
}
@Test(description = "Relative set to false")
@@ -73,7 +73,7 @@ class LnUnitTest extends TestNGSuite with Matchers {
ln.relative = false
ln.in = new File("/dir/nested/target.txt")
ln.out = new File("/dir/nested/link.txt")
- ln.cmd should === ("ln -s '/dir/nested/target.txt' '/dir/nested/link.txt'")
+ ln.cmd should ===("ln -s '/dir/nested/target.txt' '/dir/nested/link.txt'")
}
// TODO: test for case where abosolute is true and input paths are relative?
diff --git a/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastqUnitTest.scala b/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastqUnitTest.scala
index 0dac57875f5ae3966b009d9605a2e7c7d55b5d96..19b05904b6135df1576d334668a4338494e6bd7f 100644
--- a/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastqUnitTest.scala
+++ b/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastqUnitTest.scala
@@ -42,40 +42,40 @@ class ExtractAlignedFastqUnitTest extends TestNGSuite with MockitoSugar with Mat
@Test def testIntervalStartEnd() = {
val obs = makeIntervalFromString(List("chr5:1000-1100")).next()
val exp = new Interval("chr5", 1000, 1100)
- obs.getSequence should === (exp.getSequence)
- obs.getStart should === (exp.getStart)
- obs.getEnd should === (exp.getEnd)
+ obs.getSequence should ===(exp.getSequence)
+ obs.getStart should ===(exp.getStart)
+ obs.getEnd should ===(exp.getEnd)
}
@Test def testIntervalStartEndComma() = {
val obs = makeIntervalFromString(List("chr5:1,000-1,100")).next()
val exp = new Interval("chr5", 1000, 1100)
- obs.getSequence should === (exp.getSequence)
- obs.getStart should === (exp.getStart)
- obs.getEnd should === (exp.getEnd)
+ obs.getSequence should ===(exp.getSequence)
+ obs.getStart should ===(exp.getStart)
+ obs.getEnd should ===(exp.getEnd)
}
@Test def testIntervalStartEndDot() = {
val obs = makeIntervalFromString(List("chr5:1.000-1.100")).next()
val exp = new Interval("chr5", 1000, 1100)
- obs.getSequence should === (exp.getSequence)
- obs.getStart should === (exp.getStart)
- obs.getEnd should === (exp.getEnd)
+ obs.getSequence should ===(exp.getSequence)
+ obs.getStart should ===(exp.getStart)
+ obs.getEnd should ===(exp.getEnd)
}
@Test def testIntervalStart() = {
val obs = makeIntervalFromString(List("chr5:1000")).next()
val exp = new Interval("chr5", 1000, 1000)
- obs.getSequence should === (exp.getSequence)
- obs.getStart should === (exp.getStart)
- obs.getEnd should === (exp.getEnd)
+ obs.getSequence should ===(exp.getSequence)
+ obs.getStart should ===(exp.getStart)
+ obs.getEnd should ===(exp.getEnd)
}
@Test def testIntervalError() = {
val thrown = intercept[IllegalArgumentException] {
makeIntervalFromString(List("chr5:1000-")).next()
}
- thrown.getMessage should === ("Invalid interval string: chr5:1000-")
+ thrown.getMessage should ===("Invalid interval string: chr5:1000-")
}
@Test def testMemFuncIntervalError() = {
@@ -84,7 +84,7 @@ class ExtractAlignedFastqUnitTest extends TestNGSuite with MockitoSugar with Mat
val thrown = intercept[IllegalArgumentException] {
makeMembershipFunction(iv, inAln)
}
- thrown.getMessage should === ("Chromosome chrP is not found in the alignment file")
+ thrown.getMessage should ===("Chromosome chrP is not found in the alignment file")
}
@DataProvider(name = "singleAlnProvider1", parallel = true)
@@ -218,7 +218,7 @@ class ExtractAlignedFastqUnitTest extends TestNGSuite with MockitoSugar with Mat
val thrown = intercept[IllegalArgumentException] {
selectFastqReads(memFunc, in1, out1, in2)
}
- thrown.getMessage should === ("Missing output FASTQ 2")
+ thrown.getMessage should ===("Missing output FASTQ 2")
verify(out1, never).write(anyObject.asInstanceOf[FastqRecord])
}
@@ -230,7 +230,7 @@ class ExtractAlignedFastqUnitTest extends TestNGSuite with MockitoSugar with Mat
val thrown = intercept[IllegalArgumentException] {
selectFastqReads(memFunc, in1, out1, outputFastq2 = out2)
}
- thrown.getMessage should === ("Output FASTQ 2 supplied but there is no input FASTQ 2")
+ thrown.getMessage should ===("Output FASTQ 2 supplied but there is no input FASTQ 2")
verify(out1, never).write(anyObject.asInstanceOf[FastqRecord])
verify(out2, never).write(anyObject.asInstanceOf[FastqRecord])
}