diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala
index 0cd432c6e7021d73b10f7906af2af7110f2b9432..b033fb45ed88fc8cea258d7ca19db3a2553e4e5c 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/scripts/SquishBed.scala
@@ -40,6 +40,6 @@ object SquishBed {
val squishBed = new SquishBed(root)
squishBed.input = input
squishBed.output = new File(outputDir, input.getName.stripSuffix(".bed") + ".squish.bed")
- return squishBed
+ squishBed
}
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/AnnotateVcfWithBed.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/AnnotateVcfWithBed.scala
index 0f749e2832d69d8221c1ebbe68f3c301c7dc3ea4..2646ea9611df2a8d9f65c91b1a5131015ae4fd6a 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/AnnotateVcfWithBed.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/AnnotateVcfWithBed.scala
@@ -26,13 +26,15 @@ import scala.collection.JavaConversions._
import scala.collection.mutable
import scala.io.Source
-/**
- * Created by pjvan_thof on 1/10/15.
- */
class AnnotateVcfWithBed {
// TODO: Queue wrapper
}
+/**
+ * This a tools to annotate a vcf file with values from a bed file
+ *
+ * Created by pjvan_thof on 1/10/15.
+ */
object AnnotateVcfWithBed extends ToolCommand {
/**
@@ -52,30 +54,29 @@ object AnnotateVcfWithBed extends ToolCommand {
fieldType: String = "String") extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required () unbounded () valueName ("<vcf file>") action { (x, c) =>
+ opt[File]('I', "inputFile") required () unbounded () valueName "<vcf file>" action { (x, c) =>
c.copy(inputFile = x)
- } text ("Input is a required file property")
- opt[File]('B', "bedFile") required () unbounded () valueName ("<bed file>") action { (x, c) =>
+ } text "Input is a required file property"
+ opt[File]('B', "bedFile") required () unbounded () valueName "<bed file>" action { (x, c) =>
c.copy(bedFile = x)
- } text ("Bedfile is a required file property")
- opt[File]('o', "output") required () unbounded () valueName ("<vcf file>") action { (x, c) =>
+ } text "Bedfile is a required file property"
+ opt[File]('o', "output") required () unbounded () valueName "<vcf file>" action { (x, c) =>
c.copy(outputFile = x)
- } text ("out is a required file property")
- opt[String]('f', "fieldName") required () unbounded () valueName ("<name of field in vcf file>") action { (x, c) =>
+ } text "out is a required file property"
+ opt[String]('f', "fieldName") required () unbounded () valueName "<name of field in vcf file>" action { (x, c) =>
c.copy(fieldName = x)
- } text ("Name of info field in new vcf file")
- opt[String]('d', "fieldDescription") unbounded () valueName ("<name of field in vcf file>") action { (x, c) =>
+ } text "Name of info field in new vcf file"
+ opt[String]('d', "fieldDescription") unbounded () valueName "<name of field in vcf file>" action { (x, c) =>
c.copy(fieldDescription = x)
- } text ("Description of field in new vcf file")
- opt[String]('t', "fieldType") unbounded () valueName ("<name of field in vcf file>") action { (x, c) =>
+ } text "Description of field in new vcf file"
+ opt[String]('t', "fieldType") unbounded () valueName "<name of field in vcf file>" action { (x, c) =>
c.copy(fieldType = x)
- } text ("Description of field in new vcf file")
+ } text "Description of field in new vcf file"
}
/**
- * Program will Annotate a vcf file with the overlapping regions of a bed file, 4e column of the bed file we in a info tag in the vcf file
- *
- * @param args
+ * Program will Annotate a vcf file with the overlapping regions of a bed file,
+ * 4e column of the bed file we in a info tag in the vcf file
*/
def main(args: Array[String]): Unit = {
@@ -108,7 +109,7 @@ object AnnotateVcfWithBed extends ToolCommand {
val values = line.split("\t")
if (values.size >= 4)
bedRecords(values(0)) = (values(1).toInt, values(2).toInt, values(3)) :: bedRecords.getOrElse(values(0), Nil)
- else (values.size >= 3 && fieldType == VCFHeaderLineType.Flag)
+ else values.size >= 3 && fieldType == VCFHeaderLineType.Flag
bedRecords(values(0)) = (values(1).toInt, values(2).toInt, "") :: bedRecords.getOrElse(values(0), Nil)
}
@@ -148,8 +149,8 @@ object AnnotateVcfWithBed extends ToolCommand {
writer.add(builder.make)
}
}
- reader.close
- writer.close
+ reader.close()
+ writer.close()
logger.info("Done")
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BastyGenerateFasta.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BastyGenerateFasta.scala
index 53872b2caa8f8a68f7753f3bd605025f04883619..62cf74f8e6a0669666aa5b00adbed576b60ca827 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BastyGenerateFasta.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BastyGenerateFasta.scala
@@ -58,8 +58,8 @@ class BastyGenerateFasta(val root: Configurable) extends ToolCommandFuntion with
override val defaultCoreMemory = 4.0
- override def beforeGraph: Unit = {
- super.beforeGraph
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
reference = referenceFasta()
}
@@ -91,43 +91,43 @@ object BastyGenerateFasta extends ToolCommand {
reference: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('V', "inputVcf") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('V', "inputVcf") unbounded () valueName "<file>" action { (x, c) =>
c.copy(inputVcf = x)
- } text ("vcf file, needed for outputVariants and outputConsensusVariants") validate { x =>
+ } text "vcf file, needed for outputVariants and outputConsensusVariants" validate { x =>
if (x.exists) success else failure("File does not exist: " + x)
}
- opt[File]("bamFile") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("bamFile") unbounded () valueName "<file>" action { (x, c) =>
c.copy(bamFile = x)
- } text ("bam file, needed for outputConsensus and outputConsensusVariants") validate { x =>
+ } text "bam file, needed for outputConsensus and outputConsensusVariants" validate { x =>
if (x.exists) success else failure("File does not exist: " + x)
}
- opt[File]("outputVariants") maxOccurs (1) unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("outputVariants") maxOccurs 1 unbounded () valueName "<file>" action { (x, c) =>
c.copy(outputVariants = x)
- } text ("fasta with only variants from vcf file")
- opt[File]("outputConsensus") maxOccurs (1) unbounded () valueName ("<file>") action { (x, c) =>
+ } text "fasta with only variants from vcf file"
+ opt[File]("outputConsensus") maxOccurs 1 unbounded () valueName "<file>" action { (x, c) =>
c.copy(outputConsensus = x)
- } text ("Consensus fasta from bam, always reference bases else 'N'")
- opt[File]("outputConsensusVariants") maxOccurs (1) unbounded () valueName ("<file>") action { (x, c) =>
+ } text "Consensus fasta from bam, always reference bases else 'N'"
+ opt[File]("outputConsensusVariants") maxOccurs 1 unbounded () valueName "<file>" action { (x, c) =>
c.copy(outputConsensusVariants = x)
- } text ("Consensus fasta from bam with variants from vcf file, always reference bases else 'N'")
+ } text "Consensus fasta from bam with variants from vcf file, always reference bases else 'N'"
opt[Unit]("snpsOnly") unbounded () action { (x, c) =>
c.copy(snpsOnly = true)
- } text ("Only use snps from vcf file")
+ } text "Only use snps from vcf file"
opt[String]("sampleName") unbounded () action { (x, c) =>
c.copy(sampleName = x)
- } text ("Sample name in vcf file")
+ } text "Sample name in vcf file"
opt[String]("outputName") required () unbounded () action { (x, c) =>
c.copy(outputName = x)
- } text ("Output name in fasta file header")
+ } text "Output name in fasta file header"
opt[Int]("minAD") unbounded () action { (x, c) =>
c.copy(minAD = x)
- } text ("min AD value in vcf file for sample. Defaults to: 8")
+ } text "min AD value in vcf file for sample. Defaults to: 8"
opt[Int]("minDepth") unbounded () action { (x, c) =>
c.copy(minDepth = x)
- } text ("min depth in bam file. Defaults to: 8")
+ } text "min depth in bam file. Defaults to: 8"
opt[File]("reference") unbounded () action { (x, c) =>
c.copy(reference = x)
- } text ("Indexed reference fasta file") validate { x =>
+ } text "Indexed reference fasta file" validate { x =>
if (x.exists) success else failure("File does not exist: " + x)
}
@@ -188,7 +188,7 @@ object BastyGenerateFasta extends ToolCommand {
val variants: Map[(Int, Int), VariantContext] = if (cmdArgs.inputVcf != null) {
val reader = new VCFFileReader(cmdArgs.inputVcf, true)
- (for (variant <- reader.query(chrName, begin, end) if (!cmdArgs.snpsOnly || variant.isSNP)) yield {
+ (for (variant <- reader.query(chrName, begin, end) if !cmdArgs.snpsOnly || variant.isSNP) yield {
(variant.getStart, variant.getEnd) -> variant
}).toMap
} else Map()
@@ -202,10 +202,10 @@ object BastyGenerateFasta extends ToolCommand {
for (t <- s to e) coverage(t - begin) += 1
}
} else {
- for (t <- 0 until coverage.length) coverage(t) = cmdArgs.minDepth
+ for (t <- coverage.indices) coverage(t) = cmdArgs.minDepth
}
- val consensus = for (t <- 0 until coverage.length) yield {
+ val consensus = for (t <- coverage.indices) yield {
if (coverage(t) >= cmdArgs.minDepth) referenceSequence.getBases()(t).toChar
else 'N'
}
@@ -222,7 +222,7 @@ object BastyGenerateFasta extends ToolCommand {
val stripSufix = if (variant.get._1._2 > end) variant.get._1._2 - end else 0
val allele = getMaxAllele(variant.get._2)
consensusPos += variant.get._2.getReference.getBases.length
- buffer.append(allele.substring(stripPrefix, allele.size - stripSufix))
+ buffer.append(allele.substring(stripPrefix, allele.length - stripSufix))
} else {
buffer.append(consensus(consensusPos))
consensusPos += 1
@@ -230,7 +230,7 @@ object BastyGenerateFasta extends ToolCommand {
}
}
- (chunk -> (consensus.mkString.toUpperCase, buffer.toString.toUpperCase))
+ chunk -> (consensus.mkString.toUpperCase, buffer.toString().toUpperCase)
}).toMap
if (cmdArgs.outputConsensus != null) {
val writer = new PrintWriter(cmdArgs.outputConsensus)
@@ -239,7 +239,7 @@ object BastyGenerateFasta extends ToolCommand {
writer.print(chunks(c)._1)
}
writer.println()
- writer.close
+ writer.close()
}
if (cmdArgs.outputConsensusVariants != null) {
val writer = new PrintWriter(cmdArgs.outputConsensusVariants)
@@ -248,7 +248,7 @@ object BastyGenerateFasta extends ToolCommand {
writer.print(chunks(c)._2)
}
writer.println()
- writer.close
+ writer.close()
}
}
}
@@ -257,12 +257,12 @@ object BastyGenerateFasta extends ToolCommand {
val writer = new PrintWriter(cmdArgs.outputVariants)
writer.println(">" + cmdArgs.outputName)
val vcfReader = new VCFFileReader(cmdArgs.inputVcf, false)
- for (vcfRecord <- vcfReader if (!cmdArgs.snpsOnly || vcfRecord.isSNP)) yield {
+ for (vcfRecord <- vcfReader if !cmdArgs.snpsOnly || vcfRecord.isSNP) yield {
writer.print(getMaxAllele(vcfRecord))
}
writer.println()
- writer.close
- vcfReader.close
+ writer.close()
+ vcfReader.close()
}
protected def getMaxAllele(vcfRecord: VariantContext): String = {
@@ -276,6 +276,6 @@ object BastyGenerateFasta extends ToolCommand {
if (AD == null) return fillAllele("", maxSize)
val maxADid = AD.zipWithIndex.maxBy(_._1)._2
if (AD(maxADid) < cmdArgs.minAD) return fillAllele("", maxSize)
- return fillAllele(vcfRecord.getAlleles()(maxADid).getBaseString, maxSize)
+ fillAllele(vcfRecord.getAlleles()(maxADid).getBaseString, maxSize)
}
}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala
index 76dae2616415147039d8c4ba8c31a64e3468df0e..f396cb3d3ca6417ce1533555f8f2223a0c6060d7 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedToInterval.scala
@@ -53,19 +53,19 @@ object BedToInterval extends ToolCommand {
bedToInterval.input = inputBed
bedToInterval.bamFile = inputBam
bedToInterval.output = output
- return bedToInterval
+ bedToInterval
}
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) =>
+ opt[File]('I', "inputFile") required () valueName "<file>" action { (x, c) =>
c.copy(inputFile = x)
}
- opt[File]('o', "output") required () valueName ("<file>") action { (x, c) =>
+ opt[File]('o', "output") required () valueName "<file>" action { (x, c) =>
c.copy(outputFile = x)
}
- opt[File]('b', "bam") required () valueName ("<file>") action { (x, c) =>
+ opt[File]('b', "bam") required () valueName "<file>" action { (x, c) =>
c.copy(bamFile = x)
}
}
@@ -85,12 +85,12 @@ object BedToInterval extends ToolCommand {
writer.write("@SQ\tSN:" + record.getSequenceName + "\tLN:" + record.getSequenceLength + "\n")
record.getSequenceName -> record.getSequenceLength
}
- inputSam.close
+ inputSam.close()
val refsMap = Map(refs: _*)
val bedFile = Source.fromFile(commandArgs.inputFile)
for (
- line <- bedFile.getLines;
+ line <- bedFile.getLines();
split = line.split("\t") if split.size >= 3;
chr = split(0);
start = split(1);
@@ -102,7 +102,7 @@ object BedToInterval extends ToolCommand {
else {
var strand = "+"
for (t <- 3 until split.length) {
- if ((split(t) == "+" || split(t) == "-")) strand = split(t)
+ if (split(t) == "+" || split(t) == "-") strand = split(t)
}
writer.write(strand)
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala
index 56cea947ce022426370169a4166cc322c7319d06..cea645c4607b9e2a5e8fd7a4b7980da320266ab0 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BedtoolsCoverageToCounts.scala
@@ -21,8 +21,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.core.{ ToolCommand, ToolCommandFuntion }
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-import scala.collection.SortedMap
-import scala.collection.mutable.Map
+import scala.collection.{ mutable, SortedMap }
import scala.io.Source
class BedtoolsCoverageToCounts(val root: Configurable) extends ToolCommandFuntion {
@@ -45,10 +44,10 @@ object BedtoolsCoverageToCounts extends ToolCommand {
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) =>
+ 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) =>
+ opt[File]('o', "output") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(output = x)
}
}
@@ -62,8 +61,8 @@ object BedtoolsCoverageToCounts extends ToolCommand {
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
- val counts: Map[String, Long] = Map()
- for (line <- Source.fromFile(commandArgs.input).getLines) {
+ val counts: mutable.Map[String, Long] = mutable.Map()
+ for (line <- Source.fromFile(commandArgs.input).getLines()) {
val values = line.split("\t")
val gene = values(3)
val count = values(6).toLong
@@ -77,6 +76,6 @@ object BedtoolsCoverageToCounts extends ToolCommand {
for ((seq, count) <- sortedCounts) {
if (count > 0) writer.println(seq + "\t" + count)
}
- writer.close
+ writer.close()
}
}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala
index 568e2321a4195ca4bc77bab59481cf7434528838..7340a5830a875c6d2ee5a4126d9af62a44203da8 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/BiopetFlagstat.scala
@@ -25,6 +25,7 @@ import nl.lumc.sasc.biopet.utils.ConfigUtils
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import scala.collection.JavaConversions._
+import scala.collection.mutable
class BiopetFlagstat(val root: Configurable) extends ToolCommandFuntion with Summarizable {
javaMainClass = getClass.getName
@@ -63,13 +64,13 @@ object BiopetFlagstat extends ToolCommand {
case class Args(inputFile: File = null, summaryFile: Option[File] = None, region: Option[String] = None) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required () valueName ("<file>") action { (x, c) =>
+ opt[File]('I', "inputFile") required () valueName "<file>" action { (x, c) =>
c.copy(inputFile = x)
- } text ("input bam file")
- opt[File]('s', "summaryFile") valueName ("<file>") action { (x, c) =>
+ } text "input bam file"
+ opt[File]('s', "summaryFile") valueName "<file>" action { (x, c) =>
c.copy(summaryFile = Some(x))
- } text ("summary output file")
- opt[String]('r', "region") valueName ("<chr:start-stop>") action { (x, c) =>
+ } text "summary output file"
+ opt[String]('r', "region") valueName "<chr:start-stop>" action { (x, c) =>
c.copy(region = Some(x))
}
}
@@ -82,7 +83,7 @@ object BiopetFlagstat extends ToolCommand {
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
val inputSam = SamReaderFactory.makeDefault.open(commandArgs.inputFile)
- val iterSam = if (commandArgs.region == None) inputSam.iterator else {
+ val iterSam = if (commandArgs.region.isEmpty) inputSam.iterator else {
val regionRegex = """(.*):(.*)-(.*)""".r
commandArgs.region.get match {
case regionRegex(chr, start, stop) => inputSam.query(chr, start.toInt, stop.toInt, false)
@@ -91,7 +92,7 @@ object BiopetFlagstat extends ToolCommand {
}
val flagstatCollector = new FlagstatCollector
- flagstatCollector.loadDefaultFunctions
+ flagstatCollector.loadDefaultFunctions()
val m = 10
val max = 60
for (t <- 0 to (max / m))
@@ -144,11 +145,10 @@ object BiopetFlagstat extends ToolCommand {
}
commandArgs.summaryFile.foreach {
- case file => {
+ case file =>
val writer = new PrintWriter(file)
writer.println(flagstatCollector.summary)
writer.close()
- }
}
println(flagstatCollector.report)
@@ -157,12 +157,12 @@ object BiopetFlagstat extends ToolCommand {
class FlagstatCollector {
private var functionCount = 0
var readsCount = 0
- private val names: Map[Int, String] = Map()
+ private val names: mutable.Map[Int, String] = mutable.Map()
private var functions: Array[SAMRecord => Boolean] = Array()
private var totalCounts: Array[Long] = Array()
private var crossCounts = Array.ofDim[Long](1, 1)
- def loadDefaultFunctions {
+ def loadDefaultFunctions() {
addFunction("All", record => true)
addFunction("Mapped", record => !record.getReadUnmappedFlag)
addFunction("Duplicates", record => record.getDuplicateReadFlag)
@@ -207,7 +207,7 @@ object BiopetFlagstat extends ToolCommand {
crossCounts = Array.ofDim[Long](functionCount, functionCount)
totalCounts = new Array[Long](functionCount)
val temp = new Array[SAMRecord => Boolean](functionCount)
- for (t <- 0 until (temp.size - 1)) temp(t) = functions(t)
+ for (t <- 0 until (temp.length - 1)) temp(t) = functions(t)
functions = temp
val index = functionCount - 1
@@ -228,7 +228,7 @@ object BiopetFlagstat extends ToolCommand {
buffer.append(crossReport() + "\n")
buffer.append(crossReport(fraction = true) + "\n")
- return buffer.toString
+ buffer.toString()
}
def summary: String = {
@@ -236,7 +236,7 @@ object BiopetFlagstat extends ToolCommand {
names(t) -> totalCounts(t)
}).toMap
- return ConfigUtils.mapToJson(map).spaces4
+ ConfigUtils.mapToJson(map).spaces4
}
def crossReport(fraction: Boolean = false): String = {
@@ -258,7 +258,7 @@ object BiopetFlagstat extends ToolCommand {
else buffer.append("\t")
}
}
- return buffer.toString
+ buffer.toString()
}
} // End of class
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala
index 720bb36914b31381c40d16423a3bcd5ab3e48b0d..1059f7c4bcc3595bb5382fed8c5279b623695856 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/CheckAllelesVcfInBam.scala
@@ -46,19 +46,19 @@ object CheckAllelesVcfInBam extends ToolCommand {
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) =>
+ 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) =>
+ 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) =>
+ 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) =>
+ 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) =>
+ opt[Int]('m', "min_mapping_quality") maxOccurs 1 action { (x, c) =>
c.copy(minMapQual = c.minMapQual)
}
}
@@ -98,7 +98,7 @@ object CheckAllelesVcfInBam extends ToolCommand {
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)
+ vcfRecord.getStart, vcfRecord.getStart + refAllele.length - 1)
val bamIter = bamReader.query(Array(queryInterval), false)
def filterRead(samRecord: SAMRecord): Boolean = {
@@ -112,7 +112,7 @@ object CheckAllelesVcfInBam extends ToolCommand {
countReports(sample).lowMapQualReads += 1
return true
}
- return false
+ false
}
val counts = for (samRecord <- bamIter if !filterRead(samRecord)) {
@@ -122,7 +122,7 @@ object CheckAllelesVcfInBam extends ToolCommand {
case _ => countReports(sample).notFound += 1
}
}
- bamIter.close
+ bamIter.close()
}
val builder = new VariantContextBuilder(vcfRecord)
@@ -137,49 +137,49 @@ object CheckAllelesVcfInBam extends ToolCommand {
}
writer.add(builder.make)
}
- for ((_, r) <- bamReaders) r.close
- reader.close
- writer.close
+ for ((_, r) <- bamReaders) r.close()
+ reader.close()
+ writer.close()
}
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 }
- val readBases = samRecord.getReadBases()
+ 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
+ for (allele <- alleles if allele.length > maxSize) maxSize = allele.length
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 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)
+ for (allele <- allelesInRead if allele.length > refAllele.length) {
+ val refPos = for (t <- refAllele.length until allele.length) 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
+ val readPosAfterAllele = samRecord.getReferencePositionAtReadPosition(readStartPos + allele.length + 1)
+ val vcfPosAfterAllele = vcfRecord.getStart + refAllele.length
if (readPosAfterAllele != vcfPosAfterAllele &&
- (refAllele.size != allele.size || (refAllele.size == allele.size && readPosAfterAllele < 0))) allelesInRead -= allele
+ (refAllele.length != allele.length || (refAllele.length == allele.length && readPosAfterAllele < 0))) allelesInRead -= allele
}
- for (allele <- allelesInRead if allele.size >= refAllele.size) {
- if (allelesInRead.exists(_.size > allele.size)) allelesInRead -= allele
+ for (allele <- allelesInRead if allele.length >= refAllele.length) {
+ if (allelesInRead.exists((_.length) > allele.length)) allelesInRead -= allele
}
- if (allelesInRead.contains(refAllele) && allelesInRead.exists(_.size < refAllele.size)) allelesInRead -= refAllele
- if (allelesInRead.isEmpty) return None
- else if (allelesInRead.size == 1) return Some(allelesInRead.head)
+ if (allelesInRead.contains(refAllele) && allelesInRead.exists((_.length) < refAllele.length)) allelesInRead -= refAllele
+ if (allelesInRead.isEmpty) None
+ else if (allelesInRead.size == 1) Some(allelesInRead.head)
else {
logger.warn("vcfRecord: " + vcfRecord)
logger.warn("samRecord: " + samRecord.getSAMString)
logger.warn("Found multiple options: " + allelesInRead.toString)
logger.warn("ReadStartPos: " + readStartPos + " Read Length: " + samRecord.getReadLength)
logger.warn("Read skipped, please report this")
- return None
+ None
}
}
}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala
index 219d4f7104355fc309d0821d53a683f3df2ff838..e8042553b5c32affee466c6372eeac29d1e5f7c6 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/ExtractAlignedFastq.scala
@@ -229,9 +229,9 @@ object ExtractAlignedFastq extends ToolCommand {
""".stripMargin)
checkConfig { c =>
- if (c.inputFastq2 != None && c.outputFastq2 == None)
+ if (c.inputFastq2.isDefined && c.outputFastq2.isEmpty)
failure("Missing output FASTQ file 2")
- else if (c.inputFastq2 == None && c.outputFastq2 != None)
+ else if (c.inputFastq2.isEmpty && c.outputFastq2.isDefined)
failure("Missing input FASTQ file 2")
else
success
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala
index cffc5023c750b15f7fb390b945401d0d19da7b1a..beed86c64f2aa792af84bac2bd3439ff616dedca 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FastqSplitter.scala
@@ -53,12 +53,12 @@ object FastqSplitter extends ToolCommand {
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) =>
+ 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) =>
+ } 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")
+ } text "out is a required file property"
}
/**
@@ -87,7 +87,7 @@ object FastqSplitter extends ToolCommand {
}
}
}
- for (writer <- output) writer.close
+ for (writer <- output) writer.close()
logger.info("Done, " + counter + " reads processed")
}
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala
index 9c7baf364ee741be7b7eb8ea9b2af22a4ac63bb5..dafa21f20d18ce0c0e364e17778b3547f0d2ed67 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/FindRepeatsPacBio.scala
@@ -27,12 +27,12 @@ object FindRepeatsPacBio extends ToolCommand {
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) =>
+ 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) =>
+ opt[File]('b', "inputBed") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(inputBed = x)
- } text ("output file, default to stdout")
+ } text "output file, default to stdout"
}
/**
@@ -53,7 +53,7 @@ object FindRepeatsPacBio extends ToolCommand {
println(header.mkString("\t"))
for (
- bedLine <- Source.fromFile(commandArgs.inputBed).getLines;
+ bedLine <- Source.fromFile(commandArgs.inputBed).getLines();
values = bedLine.split("\t"); if values.size >= 3
) {
val interval = new QueryInterval(bamHeader.getSequenceIndex(values(0)), values(1).toInt, values(2).toInt)
@@ -78,7 +78,7 @@ object FindRepeatsPacBio extends ToolCommand {
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))(_ + _))
+ (0 /: result.get.dels.map(_.length))(_ + _) + (0 /: result.get.ins.map(_.insert.length))(_ + _)
calcRepeatLength ::= length
if (length > maxLength) maxLength = length
if (length < minLength || minLength == -1) minLength = length
@@ -86,7 +86,7 @@ object FindRepeatsPacBio extends ToolCommand {
}
println(List(chr, startPos, stopPos, typeRepeat, repeatLength, oriRepeatLength, calcRepeatLength.mkString(","), minLength,
maxLength, inserts.mkString("/"), deletions.mkString("/"), notSpan).mkString("\t"))
- bamIter.close
+ bamIter.close()
}
}
@@ -135,6 +135,6 @@ object FindRepeatsPacBio extends ToolCommand {
}
}
- return Some(result)
+ Some(result)
}
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeAlleles.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeAlleles.scala
index 4f972de13b29adb649bf3c1bfc3bc59b5b0b25b7..1ff699f1ad4de288f7019e0903cd748e9755bc47 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeAlleles.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeAlleles.scala
@@ -26,7 +26,7 @@ import nl.lumc.sasc.biopet.core.{ ToolCommand, ToolCommandFuntion }
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import scala.collection.JavaConversions._
-import scala.collection.SortedMap
+import scala.collection.{ mutable, SortedMap }
import scala.collection.mutable.{ Map, Set }
class MergeAlleles(val root: Configurable) extends ToolCommandFuntion {
@@ -45,8 +45,8 @@ class MergeAlleles(val root: Configurable) extends ToolCommandFuntion {
override val defaultCoreMemory = 1.0
- override def beforeGraph {
- super.beforeGraph
+ override def beforeGraph() {
+ super.beforeGraph()
if (output.getName.endsWith(".gz")) outputIndex = new File(output.getAbsolutePath + ".tbi")
if (output.getName.endsWith(".vcf")) outputIndex = new File(output.getAbsolutePath + ".idx")
}
@@ -62,19 +62,19 @@ object MergeAlleles extends ToolCommand {
val mergeAlleles = new MergeAlleles(root)
mergeAlleles.input = input
mergeAlleles.output = output
- return mergeAlleles
+ mergeAlleles
}
case class Args(inputFiles: List[File] = Nil, outputFile: File = null, reference: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputVcf") minOccurs (2) required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('I', "inputVcf") minOccurs 2 required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(inputFiles = x :: c.inputFiles)
}
- opt[File]('o', "outputVcf") required () unbounded () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ opt[File]('o', "outputVcf") required () unbounded () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(outputFile = x)
}
- opt[File]('R', "reference") required () unbounded () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ opt[File]('R', "reference") required () unbounded () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(reference = x)
}
}
@@ -99,8 +99,8 @@ object MergeAlleles extends ToolCommand {
header.setSequenceDictionary(referenceDict)
writer.writeHeader(header)
- for (chr <- referenceDict.getSequences; chunk <- (0 to (chr.getSequenceLength / chunkSize))) {
- val output: Map[Int, List[VariantContext]] = Map()
+ for (chr <- referenceDict.getSequences; chunk <- 0 to (chr.getSequenceLength / chunkSize)) {
+ val output: mutable.Map[Int, List[VariantContext]] = mutable.Map()
val chrName = chr.getSequenceName
val begin = chunk * chunkSize + 1
@@ -119,17 +119,17 @@ object MergeAlleles extends ToolCommand {
writer.add(mergeAlleles(v))
}
}
- writer.close
+ writer.close()
readers.foreach(_.close)
}
def mergeAlleles(records: List[VariantContext]): VariantContext = {
val longestRef = {
var l: Array[Byte] = Array()
- for (a <- records.map(_.getReference.getBases) if (a.length > l.size)) l = a
+ for (a <- records.map(_.getReference.getBases) if a.length > l.length) l = a
Allele.create(l, true)
}
- val alleles: Set[Allele] = Set()
+ val alleles: mutable.Set[Allele] = mutable.Set()
val builder = new VariantContextBuilder
builder.chr(records.head.getChr)
builder.start(records.head.getStart)
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala
index 8703df78bc13ed7c06fa259950c807b11d191bc2..d9f6ce484a248666c4b8fc9a7a6f955f043a3c44 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MergeTables.scala
@@ -101,7 +101,7 @@ object MergeTables extends ToolCommand {
val split = line
.split(delimiter)
.filter(_.nonEmpty)
- val colSize = split.size
+ val colSize = split.length
require(idIdces.forall(_ < colSize), "All feature ID indices must be smaller than number of columns")
require(valIdx < colSize, "Value index must be smaller than number of columns")
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala
index 4a1b41a0653423b388c30cdff18d45a16f1ad2a8..f48bdaf7dfb6b6ca5dcca84bc45c0a7c51a77ee8 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/MpileupToVcf.scala
@@ -25,6 +25,7 @@ import nl.lumc.sasc.biopet.utils.ConfigUtils
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import scala.collection.JavaConversions._
+import scala.collection.mutable
import scala.collection.mutable.ArrayBuffer
import scala.io.Source
import scala.math.{ floor, round }
@@ -53,19 +54,19 @@ class MpileupToVcf(val root: Configurable) extends ToolCommandFuntion with Refer
override def defaults = ConfigUtils.mergeMaps(Map("samtoolsmpileup" -> Map("disable_baq" -> true, "min_map_quality" -> 1)),
super.defaults)
- override def beforeGraph {
- super.beforeGraph
+ override def beforeGraph() {
+ super.beforeGraph()
reference = referenceFasta().getAbsolutePath
val samtoolsMpileup = new SamtoolsMpileup(this)
}
- override def beforeCmd: Unit = {
+ override def beforeCmd(): Unit = {
if (sample == null && inputBam.exists()) {
val inputSam = SamReaderFactory.makeDefault.open(inputBam)
val readGroups = inputSam.getFileHeader.getReadGroups
val samples = readGroups.map(readGroup => readGroup.getSample).distinct
sample = samples.head
- inputSam.close
+ inputSam.close()
}
}
@@ -92,12 +93,12 @@ object MpileupToVcf extends ToolCommand {
homoFraction: Double = 0.8, ploidy: Int = 2) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") valueName ("<file>") action { (x, c) =>
+ 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) =>
+ } 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")
+ } text "out is a required file property"
opt[String]('s', "sample") required () action { (x, c) =>
c.copy(sample = x)
}
@@ -139,16 +140,15 @@ 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
+ Source.fromFile(commandArgs.input).getLines()
} else {
logger.info("No input file as argument, waiting on stdin")
- Source.stdin.getLines
+ Source.stdin.getLines()
}
class Counts(var forward: Int, var reverse: Int)
for (
line <- inputStream;
- values = line.split("\t");
- if values.size > 5
+ values = line.split("\t") if values.size > 5
) {
val chr = values(0)
val pos = values(1)
@@ -162,7 +162,7 @@ object MpileupToVcf extends ToolCommand {
val mpileup = values(4)
val qual = values(5)
- val counts: Map[String, Counts] = Map(ref.toUpperCase -> new Counts(0, 0))
+ val counts: mutable.Map[String, Counts] = mutable.Map(ref.toUpperCase -> new Counts(0, 0))
def addCount(s: String) {
val upper = s.toUpperCase
@@ -173,23 +173,20 @@ object MpileupToVcf extends ToolCommand {
var t = 0
var dels = 0
- while (t < mpileup.size) {
+ while (t < mpileup.length) {
mpileup(t) match {
- case ',' => {
+ case ',' =>
addCount(ref.toLowerCase)
t += 1
- }
- case '.' => {
+ case '.' =>
addCount(ref.toUpperCase)
t += 1
- }
case '^' => t += 2
case '$' => t += 1
- case '*' => {
+ case '*' =>
dels += 1
t += 1
- }
- case '+' | '-' => {
+ case '+' | '-' =>
t += 1
var size = ""
var insert = ""
@@ -199,17 +196,15 @@ object MpileupToVcf extends ToolCommand {
}
for (c <- t until t + size.toInt) insert = insert + mpileup(c)
t += size.toInt
- }
- case 'a' | 'c' | 't' | 'g' | 'A' | 'C' | 'T' | 'G' => {
+ 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 format: mutable.Map[String, String] = mutable.Map("DP" -> reads.toString)
val alt: ArrayBuffer[String] = new ArrayBuffer
format += ("RFC" -> counts(ref.toUpperCase).forward.toString)
format += ("RRC" -> counts(ref.toUpperCase).reverse.toString)
@@ -223,14 +218,14 @@ object MpileupToVcf extends ToolCommand {
round((value.forward + value.reverse).toDouble / reads * 1E4).toDouble / 1E2))
}
- if (alt.size > 0) {
+ if (alt.nonEmpty) {
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
+ for (a <- ad.indices if ad(a) > (if (max >= 0) ad(max) else -1) && !gt.contains(a)) max = a
val f = ad(max).toDouble / left
for (a <- 0 to floor(f).toInt if gt.size < commandArgs.ploidy) gt.append(max)
if (f - floor(f) >= commandArgs.homoFraction) {
@@ -243,6 +238,6 @@ object MpileupToVcf extends ToolCommand {
).mkString("\t"))
}
}
- writer.close
+ writer.close()
}
}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/PrefixFastq.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/PrefixFastq.scala
index da055614835c1e577bce53b2885f4858e1896fd9..0a325155ecd1393f72c995d0d0d17dcc564d971e 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/PrefixFastq.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/PrefixFastq.scala
@@ -64,7 +64,7 @@ object PrefixFastq extends ToolCommand {
val prefixFastq = new PrefixFastq(root)
prefixFastq.inputFastq = input
prefixFastq.outputFastq = new File(outputDir, input.getName + ".prefix.fastq")
- return prefixFastq
+ prefixFastq
}
/**
@@ -76,13 +76,13 @@ object PrefixFastq extends ToolCommand {
case class Args(input: File = null, output: File = null, seq: String = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('i', "input") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ opt[File]('i', "input") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(input = x)
}
- opt[File]('o', "output") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ opt[File]('o', "output") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(output = x)
}
- opt[String]('s', "seq") required () maxOccurs (1) valueName ("<prefix seq>") action { (x, c) =>
+ opt[String]('s', "seq") required () maxOccurs 1 valueName "<prefix seq>" action { (x, c) =>
c.copy(seq = x)
}
}
@@ -110,7 +110,7 @@ object PrefixFastq extends ToolCommand {
val readHeader = read.getReadHeader
val readSeq = cmdArgs.seq + read.getReadString
val baseQualityHeader = read.getBaseQualityHeader
- val baseQuality = Array.fill(cmdArgs.seq.size)(maxQuality).mkString + read.getBaseQualityString
+ val baseQuality = Array.fill(cmdArgs.seq.length)(maxQuality).mkString + read.getBaseQualityString
writer.write(new FastqRecord(readHeader, readSeq, baseQualityHeader, baseQuality))
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
index 18cb7ab4dc5c1dcf6d695da15dc9600abb88c87b..79388e782bf18259271b478e4fefd7e917ade100 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCountFastq.scala
@@ -22,7 +22,7 @@ import nl.lumc.sasc.biopet.core.{ ToolCommand, ToolCommandFuntion }
import org.biojava3.sequencing.io.fastq.{ Fastq, SangerFastqReader, StreamListener }
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-import scala.collection.SortedMap
+import scala.collection.{ mutable, SortedMap }
import scala.collection.mutable.Map
class SageCountFastq(val root: Configurable) extends ToolCommandFuntion {
@@ -45,10 +45,10 @@ object SageCountFastq extends ToolCommand {
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) =>
+ 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) =>
+ opt[File]('o', "output") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(output = x)
}
}
@@ -62,7 +62,7 @@ object SageCountFastq extends ToolCommand {
if (!commandArgs.input.exists) throw new IllegalStateException("Input file not found, file: " + commandArgs.input)
- val counts: Map[String, Long] = Map()
+ val counts: mutable.Map[String, Long] = mutable.Map()
val reader = new SangerFastqReader
var count = 0
logger.info("Reading fastq file: " + commandArgs.input)
@@ -86,6 +86,6 @@ object SageCountFastq extends ToolCommand {
for ((seq, count) <- sortedCounts) {
writer.println(seq + "\t" + count)
}
- writer.close
+ writer.close()
}
}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala
index 4d8bc55d32d7e28f34f8e4e4a4058493c2c2af6b..efc9ccf439db1986d59b6e57c3c9b4649da41c26 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateLibrary.scala
@@ -24,7 +24,7 @@ import org.biojava3.core.sequence.io.FastaReaderHelper
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
import scala.collection.JavaConversions._
-import scala.collection.SortedMap
+import scala.collection.{ mutable, SortedMap }
import scala.collection.mutable.{ Map, Set }
import scala.util.matching.Regex
@@ -65,10 +65,10 @@ object SageCreateLibrary extends ToolCommand {
noAntiTagsOutput: File = null, allGenesOutput: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") required () unbounded () valueName ("<file>") action { (x, c) =>
+ 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) =>
+ opt[File]('o', "output") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(output = x)
}
opt[String]("tag") required () unbounded () action { (x, c) =>
@@ -77,13 +77,13 @@ object SageCreateLibrary extends ToolCommand {
opt[Int]("length") required () unbounded () action { (x, c) =>
c.copy(length = x)
}
- opt[File]("noTagsOutput") required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("noTagsOutput") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(noTagsOutput = x)
}
- opt[File]("noAntiTagsOutput") required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("noAntiTagsOutput") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(noAntiTagsOutput = x)
}
- opt[File]("allGenesOutput") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("allGenesOutput") unbounded () valueName "<file>" action { (x, c) =>
c.copy(allGenesOutput = x)
}
}
@@ -91,17 +91,17 @@ object SageCreateLibrary extends ToolCommand {
var tagRegex: Regex = null
var geneRegex = """ENSG[0-9]{11}""".r
- val tagGenesMap: Map[String, TagGenes] = Map()
+ val tagGenesMap: mutable.Map[String, TagGenes] = mutable.Map()
- val allGenes: Set[String] = Set()
- val tagGenes: Set[String] = Set()
- val antiTagGenes: Set[String] = Set()
+ val allGenes: mutable.Set[String] = mutable.Set()
+ val tagGenes: mutable.Set[String] = mutable.Set()
+ val antiTagGenes: mutable.Set[String] = mutable.Set()
class TagGenes {
- val firstTag: Set[String] = Set()
- val allTags: Set[String] = Set()
- val firstAntiTag: Set[String] = Set()
- val allAntiTags: Set[String] = Set()
+ val firstTag: mutable.Set[String] = mutable.Set()
+ val allTags: mutable.Set[String] = mutable.Set()
+ val firstAntiTag: mutable.Set[String] = mutable.Set()
+ val allAntiTags: mutable.Set[String] = mutable.Set()
}
class TagResult(val firstTag: String, val allTags: List[String], val firstAntiTag: String, val allAntiTags: List[String])
@@ -147,7 +147,7 @@ object SageCreateLibrary extends ToolCommand {
for (gene <- allGenes if !tagGenes.contains(gene)) {
writer.println(gene)
}
- writer.close
+ writer.close()
}
if (commandArgs.noAntiTagsOutput != null) {
@@ -155,7 +155,7 @@ object SageCreateLibrary extends ToolCommand {
for (gene <- allGenes if !antiTagGenes.contains(gene)) {
writer.println(gene)
}
- writer.close
+ writer.close()
}
if (commandArgs.allGenesOutput != null) {
@@ -163,7 +163,7 @@ object SageCreateLibrary extends ToolCommand {
for (gene <- allGenes) {
writer.println(gene)
}
- writer.close
+ writer.close()
}
}
@@ -196,14 +196,14 @@ object SageCreateLibrary extends ToolCommand {
}
def getTags(name: String, seq: DNASequence): TagResult = {
- val allTags: List[String] = for (tag <- tagRegex.findAllMatchIn(seq.getSequenceAsString).toList) yield tag.toString
+ 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 allAntiTags: List[String] = for (tag <- tagRegex.findAllMatchIn(seq.getReverseComplement.getSequenceAsString).toList) yield tag.toString()
val firstAntiTag = if (allAntiTags.isEmpty) null else allAntiTags.head
val result = new TagResult(firstTag, allTags, firstAntiTag, allAntiTags)
addTagresultToTaglib(name, result)
- return result
+ result
}
}
\ No newline at end of file
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala
index 925d8f2f6512e7a71c83a589e21187acc5bf91f5..d185fbc350e4bf8c8b4cbf920667163ac517855a 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SageCreateTagCounts.scala
@@ -21,7 +21,7 @@ import nl.lumc.sasc.biopet.core.config.Configurable
import nl.lumc.sasc.biopet.core.{ ToolCommand, ToolCommandFuntion }
import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
-import scala.collection.SortedMap
+import scala.collection.{ mutable, SortedMap }
import scala.collection.mutable.Map
import scala.io.Source
@@ -62,22 +62,22 @@ object SageCreateTagCounts extends ToolCommand {
countAntiSense: File = null, countAllAntiSense: File = null) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "input") required () unbounded () valueName ("<file>") action { (x, c) =>
+ 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) =>
+ opt[File]('t', "tagLib") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(tagLib = x)
}
- opt[File]("countSense") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("countSense") unbounded () valueName "<file>" action { (x, c) =>
c.copy(countSense = x)
}
- opt[File]("countAllSense") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("countAllSense") unbounded () valueName "<file>" action { (x, c) =>
c.copy(countAllSense = x)
}
- opt[File]("countAntiSense") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("countAntiSense") unbounded () valueName "<file>" action { (x, c) =>
c.copy(countAntiSense = x)
}
- opt[File]("countAllAntiSense") unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]("countAllAntiSense") unbounded () valueName "<file>" action { (x, c) =>
c.copy(countAllAntiSense = x)
}
}
@@ -91,8 +91,8 @@ object SageCreateTagCounts extends ToolCommand {
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 rawCounts: mutable.Map[String, Long] = mutable.Map()
+ for (line <- Source.fromFile(commandArgs.input).getLines()) {
val values = line.split("\t")
val gene = values(0)
val count = values(1).toLong
@@ -100,12 +100,12 @@ object SageCreateTagCounts extends ToolCommand {
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()
+ val senseCounts: mutable.Map[String, Long] = mutable.Map()
+ val allSenseCounts: mutable.Map[String, Long] = mutable.Map()
+ val antiSenseCounts: mutable.Map[String, Long] = mutable.Map()
+ val allAntiSenseCounts: mutable.Map[String, Long] = mutable.Map()
- for (line <- Source.fromFile(commandArgs.tagLib).getLines if !line.startsWith("#")) {
+ for (line <- Source.fromFile(commandArgs.tagLib).getLines() if !line.startsWith("#")) {
val values = line.split("\t")
val tag = values(0)
val sense = values(1)
@@ -138,14 +138,14 @@ object SageCreateTagCounts extends ToolCommand {
}
}
- def writeFile(file: File, counts: Map[String, Long]) {
+ def writeFile(file: File, counts: mutable.Map[String, Long]) {
val sorted: SortedMap[String, Long] = SortedMap(counts.toArray: _*)
if (file != null) {
val writer = new PrintWriter(file)
for ((gene, count) <- sorted) {
if (count > 0) writer.println(gene + "\t" + count)
}
- writer.close
+ writer.close()
}
}
writeFile(commandArgs.countSense, senseCounts)
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SamplesTsvToJson.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SamplesTsvToJson.scala
index 8f03a2d85b280f2a13989330bb980283ed073bb7..46cd2b40cd8645a432aee54081f54e9dd0ec3351 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SamplesTsvToJson.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SamplesTsvToJson.scala
@@ -29,22 +29,19 @@ object SamplesTsvToJson extends ToolCommand {
case class Args(inputFiles: List[File] = Nil) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('i', "inputFiles") required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('i', "inputFiles") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(inputFiles = x :: c.inputFiles)
- } text ("Input must be a tsv file, first line is seen as header and must at least have a 'sample' column, 'library' column is optional, multiple files allowed")
+ } text "Input must be a tsv file, first line is seen as header and must at least have a 'sample' column, 'library' column is optional, multiple files allowed"
}
- /**
- * Executes SamplesTsvToJson
- * @param args
- */
+ /** Executes SamplesTsvToJson */
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
val fileMaps = for (inputFile <- commandArgs.inputFiles) yield {
val reader = Source.fromFile(inputFile)
- val lines = reader.getLines.toList.filter(!_.isEmpty)
+ val lines = reader.getLines().toList.filter(!_.isEmpty)
val header = lines.head.split("\t")
val sampleColumn = header.indexOf("sample")
val libraryColumn = header.indexOf("library")
@@ -55,9 +52,8 @@ object SamplesTsvToJson extends ToolCommand {
val sample = values(sampleColumn)
val library = if (libraryColumn != -1) values(libraryColumn) else null
val valuesMap = (for (
- t <- 0 until values.size;
- if !values(t).isEmpty && t != sampleColumn && t != libraryColumn
- ) yield (header(t) -> values(t))).toMap
+ t <- 0 until values.size if !values(t).isEmpty && t != sampleColumn && t != libraryColumn
+ ) yield header(t) -> values(t)).toMap
val map: Map[String, Any] = if (library != null) {
Map("samples" -> Map(sample -> Map("libraries" -> Map(library -> valuesMap))))
} else {
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SeqStat.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SeqStat.scala
index d04ba91a0d788556b0f63d71ec8239bccc839d36..f232117acef51c5a5c1f09a1143cb318dc402f21 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SeqStat.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SeqStat.scala
@@ -227,7 +227,7 @@ object SeqStat extends ToolCommand {
def summarize(): Unit = {
// for every position to the max length of any read
- for (pos <- 0 until baseStats.length) {
+ for (pos <- baseStats.indices) {
// list all qualities at this particular position `pos`
// fix the length of `quals`
if (quals.length <= baseStats(pos).qual.length) {
@@ -244,7 +244,7 @@ object SeqStat extends ToolCommand {
detectPhredEncoding(quals)
logger.debug("Detected '" + phredEncoding.toString.toLowerCase + "' encoding in fastq file ...")
- for (pos <- 0 until nucs.length) {
+ for (pos <- nucs.indices) {
// always export the N-nucleotide
if (nucs(pos) > 0 || pos.toChar == 'N') {
nucleotideHistoMap += (pos.toChar -> nucs(pos))
@@ -257,14 +257,14 @@ object SeqStat extends ToolCommand {
readHistogram.append(0)
}
- for (pos <- 0 until quals.length) {
+ for (pos <- quals.indices) {
val key: Int = pos - phredEncoding.id
if (key >= 0) {
baseHistogram(key) += quals(pos)
}
}
- for (pos <- 0 until readStats.qual.length) {
+ for (pos <- readStats.qual.indices) {
val key: Int = pos - phredEncoding.id
if (key > 0) {
// count till the max of baseHistogram.length
@@ -274,7 +274,7 @@ object SeqStat extends ToolCommand {
}
}
- for (pos <- 0 until readHistogram.length) {
+ for (pos <- readHistogram.indices) {
readQualHistoMap += (pos -> readHistogram(pos))
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SummaryToTsv.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SummaryToTsv.scala
index 731e7039e2092d927d2a0ebe5146371a50453d5b..56a9f7289b58138e7dfad2f944a5e9b526a6dd08 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SummaryToTsv.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/SummaryToTsv.scala
@@ -6,6 +6,8 @@ import nl.lumc.sasc.biopet.core.ToolCommand
import nl.lumc.sasc.biopet.core.summary.Summary
/**
+ * This is a tools to extract values from a summary to a tsv file
+ *
* Created by pjvan_thof on 4/23/15.
*/
object SummaryToTsv extends ToolCommand {
@@ -15,16 +17,16 @@ object SummaryToTsv extends ToolCommand {
mode: String = "root") extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('s', "summary") required () unbounded () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ opt[File]('s', "summary") required () unbounded () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(summary = x)
}
- opt[File]('o', "output") maxOccurs (1) unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('o', "output") maxOccurs 1 unbounded () valueName "<file>" action { (x, c) =>
c.copy(outputFile = Some(x))
}
- opt[String]('p', "path") required () unbounded () valueName ("<value>") action { (x, c) =>
+ opt[String]('p', "path") required () unbounded () valueName "<value>" action { (x, c) =>
c.copy(values = c.values ::: x :: Nil)
}
- opt[String]('m', "mode") maxOccurs (1) unbounded () valueName ("<root|sample|lib>") action { (x, c) =>
+ opt[String]('m', "mode") maxOccurs 1 unbounded () valueName "<root|sample|lib>" action { (x, c) =>
c.copy(mode = x)
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
index 4b89bf22fbb3daad5c7ce490c44fce80ebbd5e56..5b31736e9bb1144a49b34fd949e15f185b321d55 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfFilter.scala
@@ -269,7 +269,7 @@ object VcfFilter extends ToolCommand {
def minAlternateDepth(record: VariantContext, minAlternateDepth: Int, minSamplesPass: Int = 1): Boolean = {
record.getGenotypes.count(genotype => {
val AD = if (genotype.hasAD) List(genotype.getAD: _*) else Nil
- if (!AD.isEmpty) AD.tail.count(_ >= minAlternateDepth) > 0 else true
+ if (AD.nonEmpty) AD.tail.count(_ >= minAlternateDepth) > 0 else true
}) >= minSamplesPass
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfStats.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfStats.scala
index 01ae908102df1aec7d92f2ed292b07bd6e7dac6e..33bbf42f209f661a74bf21882da27f01b30925b4 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfStats.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfStats.scala
@@ -33,6 +33,8 @@ import scala.sys.process.{ Process, ProcessLogger }
import scala.util.Random
/**
+ * This tool will generate statistics from a vcf file
+ *
* Created by pjvan_thof on 1/10/15.
*/
class VcfStats(val root: Configurable) extends ToolCommandFuntion with Summarizable with Reference {
@@ -61,7 +63,7 @@ class VcfStats(val root: Configurable) extends ToolCommandFuntion with Summariza
var allGenotypeTags = false
var reference: File = _
- override def beforeGraph: Unit = {
+ override def beforeGraph(): Unit = {
reference = referenceFasta()
index = new File(input.getAbsolutePath + ".tbi")
}
@@ -104,7 +106,7 @@ class VcfStats(val root: Configurable) extends ToolCommandFuntion with Summariza
for (s <- 1 until data(0).size) {
val sample = data(0)(s)
- val stats = Map("genotype" -> (for (f <- 1 until data.size) yield {
+ val stats = Map("genotype" -> (for (f <- 1 until data.length) yield {
data(f)(0) -> data(f)(s)
}).toMap)
@@ -135,13 +137,13 @@ object VcfStats extends ToolCommand {
/** Parsing commandline arguments */
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('I', "inputFile") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(inputFile = x)
}
- opt[File]('R', "referenceFile") required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('R', "referenceFile") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(referenceFile = x)
}
- opt[File]('o', "outputDir") required () unbounded () valueName ("<file>") action { (x, c) =>
+ opt[File]('o', "outputDir") required () unbounded () valueName "<file>" action { (x, c) =>
c.copy(outputDir = x)
}
//TODO: add interval argument
@@ -150,10 +152,10 @@ object VcfStats extends ToolCommand {
c.copy(intervals = Some(x))
}
*/
- opt[String]("infoTag") unbounded () valueName ("<tag>") action { (x, c) =>
+ opt[String]("infoTag") unbounded () valueName "<tag>" action { (x, c) =>
c.copy(infoTags = x :: c.infoTags)
}
- opt[String]("genotypeTag") unbounded () valueName ("<tag>") action { (x, c) =>
+ opt[String]("genotypeTag") unbounded () valueName "<tag>" action { (x, c) =>
c.copy(genotypeTags = x :: c.genotypeTags)
}
opt[Unit]("allInfoTags") unbounded () action { (x, c) =>
@@ -195,8 +197,8 @@ object VcfStats extends ToolCommand {
* @param genotypeStats Stores all genotype relative stats
* @param sampleToSample Stores sample to sample compare stats
*/
- case class SampleStats(val genotypeStats: mutable.Map[String, mutable.Map[String, mutable.Map[Any, Int]]] = mutable.Map(),
- val sampleToSample: mutable.Map[String, SampleToSampleStats] = mutable.Map()) {
+ case class SampleStats(genotypeStats: mutable.Map[String, mutable.Map[String, mutable.Map[Any, Int]]] = mutable.Map(),
+ sampleToSample: mutable.Map[String, SampleToSampleStats] = mutable.Map()) {
/** Add an other class */
def +=(other: SampleStats): Unit = {
for ((key, value) <- other.sampleToSample) {
@@ -217,8 +219,8 @@ object VcfStats extends ToolCommand {
* @param generalStats Stores are general stats
* @param samplesStats Stores all sample/genotype specific stats
*/
- case class Stats(val generalStats: mutable.Map[String, mutable.Map[String, mutable.Map[Any, Int]]] = mutable.Map(),
- val samplesStats: mutable.Map[String, SampleStats] = mutable.Map()) {
+ case class Stats(generalStats: mutable.Map[String, mutable.Map[String, mutable.Map[Any, Int]]] = mutable.Map(),
+ samplesStats: mutable.Map[String, SampleStats] = mutable.Map()) {
/** Add an other class */
def +=(other: Stats): Stats = {
for ((key, value) <- other.samplesStats) {
@@ -281,24 +283,24 @@ object VcfStats extends ToolCommand {
val adInfoTags = {
(for (
- infoTag <- commandArgs.infoTags if !defaultInfoFields.exists(_ == infoTag)
+ infoTag <- commandArgs.infoTags if !defaultInfoFields.contains(infoTag)
) yield {
require(header.getInfoHeaderLine(infoTag) != null, "Info tag '" + infoTag + "' not found in header of vcf file")
infoTag
}) ::: (for (
- line <- header.getInfoHeaderLines if commandArgs.allInfoTags if !defaultInfoFields.exists(_ == line.getID) if !commandArgs.infoTags.exists(_ == line.getID)
+ line <- header.getInfoHeaderLines if commandArgs.allInfoTags if !defaultInfoFields.contains(line.getID) if !commandArgs.infoTags.contains(line.getID)
) yield {
line.getID
}).toList ::: defaultInfoFields
}
val adGenotypeTags = (for (
- genotypeTag <- commandArgs.genotypeTags if !defaultGenotypeFields.exists(_ == genotypeTag)
+ genotypeTag <- commandArgs.genotypeTags if !defaultGenotypeFields.contains(genotypeTag)
) yield {
require(header.getFormatHeaderLine(genotypeTag) != null, "Format tag '" + genotypeTag + "' not found in header of vcf file")
genotypeTag
}) ::: (for (
- line <- header.getFormatHeaderLines if commandArgs.allGenotypeTags if !defaultGenotypeFields.exists(_ == line.getID) if !commandArgs.genotypeTags.exists(_ == line.getID) if line.getID != "PL"
+ line <- header.getFormatHeaderLines if commandArgs.allGenotypeTags if !defaultGenotypeFields.contains(line.getID) if !commandArgs.genotypeTags.contains(line.getID) if line.getID != "PL"
) yield {
line.getID
}).toList ::: defaultGenotypeFields
@@ -356,8 +358,7 @@ object VcfStats extends ToolCommand {
logger.info("Starting on: " + interval)
for (
- record <- reader.query(interval.getSequence, interval.getStart, interval.getEnd);
- if record.getStart <= interval.getEnd
+ record <- reader.query(interval.getSequence, interval.getStart, interval.getEnd) if record.getStart <= interval.getEnd
) {
mergeNestedStatsMap(stats.generalStats, checkGeneral(record, adInfoTags))
for (sample1 <- samples) yield {
@@ -394,7 +395,7 @@ object VcfStats extends ToolCommand {
// Writing info fields to tsv files
val infoOutputDir = new File(commandArgs.outputDir, "infotags")
writeField(stats, "general", commandArgs.outputDir)
- for (field <- (adInfoTags).distinct.par) {
+ for (field <- adInfoTags.distinct.par) {
writeField(stats, field, infoOutputDir)
for (line <- referenceFile.getSequenceDictionary.getSequences) {
val chr = line.getSequenceName
@@ -405,7 +406,7 @@ object VcfStats extends ToolCommand {
// Write genotype field to tsv files
val genotypeOutputDir = new File(commandArgs.outputDir, "genotypetags")
writeGenotypeField(stats, samples, "general", commandArgs.outputDir, prefix = "genotype")
- for (field <- (adGenotypeTags).distinct.par) {
+ for (field <- adGenotypeTags.distinct.par) {
writeGenotypeField(stats, samples, field, genotypeOutputDir)
for (line <- referenceFile.getSequenceDictionary.getSequences) {
val chr = line.getSequenceName
@@ -422,13 +423,13 @@ object VcfStats extends ToolCommand {
// Write general wiggle tracks
for (field <- commandArgs.generalWiggle) {
val file = new File(commandArgs.outputDir, "wigs" + File.separator + "general-" + field + ".wig")
- writeWiggle(intervals, field, "count", file, false)
+ writeWiggle(intervals, field, "count", file, genotype = false)
}
// Write sample wiggle tracks
for (field <- commandArgs.genotypeWiggle; sample <- samples) {
val file = new File(commandArgs.outputDir, "wigs" + File.separator + "genotype-" + sample + "-" + field + ".wig")
- writeWiggle(intervals, field, sample, file, true)
+ writeWiggle(intervals, field, sample, file, genotype = true)
}
writeOverlap(stats, _.genotypeOverlap, commandArgs.outputDir + "/sample_compare/genotype_overlap", samples)
@@ -474,13 +475,7 @@ object VcfStats extends ToolCommand {
value.collect { case x => x.split("\t")(index) }
}
- /**
- * Give back the number of alleles that overlap
- * @param g1
- * @param g2
- * @param start start always at 0
- * @return
- */
+ /** Give back the number of alleles that overlap */
def alleleOverlap(g1: List[Allele], g2: List[Allele], start: Int = 0): Int = {
if (g1.isEmpty) start
else {
@@ -501,25 +496,25 @@ object VcfStats extends ToolCommand {
def addToBuffer(key: String, value: Any, found: Boolean): Unit = {
val map = buffer.getOrElse(key, Map())
if (found) buffer += key -> (map + (value -> (map.getOrElse(value, 0) + 1)))
- else buffer += key -> (map + (value -> (map.getOrElse(value, 0))))
+ else buffer += key -> (map + (value -> map.getOrElse(value, 0)))
}
buffer += "QUAL" -> Map(record.getPhredScaledQual -> 1)
- addToBuffer("SampleDistribution-Het", record.getGenotypes.count(genotype => genotype.isHet), true)
- addToBuffer("SampleDistribution-HetNonRef", record.getGenotypes.count(genotype => genotype.isHetNonRef), true)
- addToBuffer("SampleDistribution-Hom", record.getGenotypes.count(genotype => genotype.isHom), true)
- addToBuffer("SampleDistribution-HomRef", record.getGenotypes.count(genotype => genotype.isHomRef), true)
- addToBuffer("SampleDistribution-HomVar", record.getGenotypes.count(genotype => genotype.isHomVar), true)
- addToBuffer("SampleDistribution-Mixed", record.getGenotypes.count(genotype => genotype.isMixed), true)
- addToBuffer("SampleDistribution-NoCall", record.getGenotypes.count(genotype => genotype.isNoCall), true)
- addToBuffer("SampleDistribution-NonInformative", record.getGenotypes.count(genotype => genotype.isNonInformative), true)
- addToBuffer("SampleDistribution-Available", record.getGenotypes.count(genotype => genotype.isAvailable), true)
- addToBuffer("SampleDistribution-Called", record.getGenotypes.count(genotype => genotype.isCalled), true)
- addToBuffer("SampleDistribution-Filtered", record.getGenotypes.count(genotype => genotype.isFiltered), true)
- addToBuffer("SampleDistribution-Variant", record.getGenotypes.count(genotype => genotype.isHetNonRef || genotype.isHet || genotype.isHomVar), true)
-
- addToBuffer("general", "Total", true)
+ addToBuffer("SampleDistribution-Het", record.getGenotypes.count(genotype => genotype.isHet), found = true)
+ addToBuffer("SampleDistribution-HetNonRef", record.getGenotypes.count(genotype => genotype.isHetNonRef), found = true)
+ addToBuffer("SampleDistribution-Hom", record.getGenotypes.count(genotype => genotype.isHom), found = true)
+ addToBuffer("SampleDistribution-HomRef", record.getGenotypes.count(genotype => genotype.isHomRef), found = true)
+ addToBuffer("SampleDistribution-HomVar", record.getGenotypes.count(genotype => genotype.isHomVar), found = true)
+ addToBuffer("SampleDistribution-Mixed", record.getGenotypes.count(genotype => genotype.isMixed), found = true)
+ addToBuffer("SampleDistribution-NoCall", record.getGenotypes.count(genotype => genotype.isNoCall), found = true)
+ addToBuffer("SampleDistribution-NonInformative", record.getGenotypes.count(genotype => genotype.isNonInformative), found = true)
+ addToBuffer("SampleDistribution-Available", record.getGenotypes.count(genotype => genotype.isAvailable), found = true)
+ addToBuffer("SampleDistribution-Called", record.getGenotypes.count(genotype => genotype.isCalled), found = true)
+ addToBuffer("SampleDistribution-Filtered", record.getGenotypes.count(genotype => genotype.isFiltered), found = true)
+ addToBuffer("SampleDistribution-Variant", record.getGenotypes.count(genotype => genotype.isHetNonRef || genotype.isHet || genotype.isHomVar), found = true)
+
+ addToBuffer("general", "Total", found = true)
addToBuffer("general", "Biallelic", record.isBiallelic)
addToBuffer("general", "ComplexIndel", record.isComplexIndel)
addToBuffer("general", "Filtered", record.isFiltered)
@@ -543,8 +538,8 @@ object VcfStats extends ToolCommand {
for (tag <- additionalTags if !skipTags.contains(tag)) {
val value = record.getAttribute(tag)
- if (value == null) addToBuffer(tag, "notset", true)
- else addToBuffer(tag, value, true)
+ if (value == null) addToBuffer(tag, "notset", found = true)
+ else addToBuffer(tag, value, found = true)
}
Map(record.getChr -> buffer.toMap, "total" -> buffer.toMap)
@@ -557,7 +552,7 @@ object VcfStats extends ToolCommand {
def addToBuffer(key: String, value: Any, found: Boolean): Unit = {
val map = buffer.getOrElse(key, Map())
if (found) buffer += key -> (map + (value -> (map.getOrElse(value, 0) + 1)))
- else buffer += key -> (map + (value -> (map.getOrElse(value, 0))))
+ else buffer += key -> (map + (value -> map.getOrElse(value, 0)))
}
buffer += "DP" -> Map((if (genotype.hasDP) genotype.getDP else "not set") -> 1)
@@ -565,7 +560,7 @@ object VcfStats extends ToolCommand {
val usedAlleles = (for (allele <- genotype.getAlleles) yield record.getAlleleIndex(allele)).toList
- addToBuffer("general", "Total", true)
+ addToBuffer("general", "Total", found = true)
addToBuffer("general", "Het", genotype.isHet)
addToBuffer("general", "HetNonRef", genotype.isHetNonRef)
addToBuffer("general", "Hom", genotype.isHom)
@@ -582,11 +577,11 @@ object VcfStats extends ToolCommand {
if (genotype.hasAD) {
val ad = genotype.getAD
for (i <- 0 until ad.size if ad(i) > 0) {
- addToBuffer("AD", ad(i), true)
- if (i == 0) addToBuffer("AD-ref", ad(i), true)
- if (i > 0) addToBuffer("AD-alt", ad(i), true)
- if (usedAlleles.exists(_ == i)) addToBuffer("AD-used", ad(i), true)
- else addToBuffer("AD-not_used", ad(i), true)
+ addToBuffer("AD", ad(i), found = true)
+ if (i == 0) addToBuffer("AD-ref", ad(i), found = true)
+ if (i > 0) addToBuffer("AD-alt", ad(i), found = true)
+ if (usedAlleles.contains(i)) addToBuffer("AD-used", ad(i), found = true)
+ else addToBuffer("AD-not_used", ad(i), found = true)
}
}
@@ -594,8 +589,8 @@ object VcfStats extends ToolCommand {
for (tag <- additionalTags if !skipTags.contains(tag)) {
val value = genotype.getAnyAttribute(tag)
- if (value == null) addToBuffer(tag, "notset", true)
- else addToBuffer(tag, value, true)
+ if (value == null) addToBuffer(tag, "notset", found = true)
+ else addToBuffer(tag, value, found = true)
}
Map(record.getChr -> buffer.toMap, "total" -> buffer.toMap)
@@ -615,7 +610,7 @@ object VcfStats extends ToolCommand {
val writer = new PrintWriter(file)
writer.println(samples.mkString(field + "\t", "\t", ""))
val keySet = (for (sample <- samples) yield stats.samplesStats(sample).genotypeStats.getOrElse(chr, Map[String, Map[Any, Int]]()).getOrElse(field, Map[Any, Int]()).keySet).fold(Set[Any]())(_ ++ _)
- for (key <- keySet.toList.sortWith(sortAnyAny(_, _))) {
+ for (key <- keySet.toList.sortWith(sortAnyAny)) {
val values = for (sample <- samples) yield stats.samplesStats(sample).genotypeStats.getOrElse(chr, Map[String, Map[Any, Int]]()).getOrElse(field, Map[Any, Int]()).getOrElse(key, 0)
writer.println(values.mkString(key + "\t", "\t", ""))
}
@@ -639,7 +634,7 @@ object VcfStats extends ToolCommand {
file.getParentFile.mkdirs()
val writer = new PrintWriter(file)
writer.println("value\tcount")
- for (key <- data.keySet.toList.sortWith(sortAnyAny(_, _))) {
+ for (key <- data.keySet.toList.sortWith(sortAnyAny)) {
writer.println(key + "\t" + data(key))
}
writer.close()
@@ -649,24 +644,17 @@ object VcfStats extends ToolCommand {
/** Function to sort Any values */
def sortAnyAny(a: Any, b: Any): Boolean = {
a match {
- case ai: Int => {
+ case ai: Int =>
b match {
case bi: Int => ai < bi
case bi: Double => ai < bi
case _ => a.toString < b.toString
}
- }
case _ => a.toString < b.toString
}
}
- /**
- * Function to write sample to sample compare tsv's / heatmaps
- * @param stats
- * @param function function to extract targeted var in SampleToSampleStats
- * @param prefix
- * @param samples
- */
+ /** Function to write sample to sample compare tsv's / heatmaps */
def writeOverlap(stats: Stats, function: SampleToSampleStats => Int,
prefix: String, samples: List[String]): Unit = {
val absFile = new File(prefix + ".abs.tsv")
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala
index 0783e65ff63abb2138c186b19f3d666b3957d899..ab1f9d8cb2d1845efc3dbe3df52a419283b62e6a 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfToTsv.scala
@@ -22,6 +22,7 @@ import htsjdk.variant.vcf.VCFFileReader
import nl.lumc.sasc.biopet.core.ToolCommand
import scala.collection.JavaConversions._
+import scala.collection.mutable
import scala.collection.mutable.{ ListBuffer, Map }
class VcfToTsv {
@@ -35,12 +36,12 @@ object VcfToTsv extends ToolCommand {
separator: String = "\t", listSeparator: String = ",", maxDecimals: Int = 2) extends AbstractArgs
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ 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) =>
+ opt[File]('o', "outputFile") maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(outputFile = x)
- } text ("output file, default to stdout")
+ } text "output file, default to stdout"
opt[String]('f', "field") unbounded () action { (x, c) =>
c.copy(fields = x :: c.fields)
}
@@ -59,15 +60,15 @@ object VcfToTsv extends ToolCommand {
opt[Unit]('d', "disable_defaults") unbounded () action { (x, c) =>
c.copy(disableDefaults = true)
}
- opt[String]("separator") maxOccurs (1) action { (x, c) =>
+ opt[String]("separator") maxOccurs 1 action { (x, c) =>
c.copy(separator = x)
- } text ("Optional separator. Default is tab-delimited")
- opt[String]("list_separator") maxOccurs (1) action { (x, c) =>
+ } text "Optional separator. Default is tab-delimited"
+ opt[String]("list_separator") maxOccurs 1 action { (x, c) =>
c.copy(listSeparator = x)
- } text ("Optional list separator. By default, lists are separated by a comma")
- opt[Int]("max_decimals") maxOccurs (1) action { (x, c) =>
+ } text "Optional list separator. By default, lists are separated by a comma"
+ opt[Int]("max_decimals") maxOccurs 1 action { (x, c) =>
c.copy(maxDecimals = x)
- } text ("Number of decimal places for numbers. Default is 2")
+ } text "Number of decimal places for numbers. Default is 2"
}
val defaultFields = List("CHROM", "POS", "ID", "REF", "ALT", "QUAL")
@@ -94,7 +95,7 @@ object VcfToTsv extends ToolCommand {
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.sampleFields); sample <- samples) {
+ for (f <- if (commandArgs.allFormat) allFormatFields else commandArgs.sampleFields; sample <- samples) {
buffer += sample + "-" + f
}
buffer.toSet[String]
@@ -107,7 +108,7 @@ object VcfToTsv extends ToolCommand {
writer.println(sortedFields.mkString("#", commandArgs.separator, ""))
for (vcfRecord <- reader) {
- val values: Map[String, Any] = Map()
+ val values: mutable.Map[String, Any] = mutable.Map()
values += "CHROM" -> vcfRecord.getChr
values += "POS" -> vcfRecord.getStart
values += "ID" -> vcfRecord.getID
@@ -158,7 +159,7 @@ object VcfToTsv extends ToolCommand {
* @return DecimalFormat formatter
*/
def createFormatter(len: Int): DecimalFormat = {
- val patternString = "###." + (for (x <- (1 to len)) yield "#").mkString("")
+ val patternString = "###." + (for (x <- 1 to len) yield "#").mkString("")
new DecimalFormat(patternString)
}
@@ -173,31 +174,29 @@ object VcfToTsv extends ToolCommand {
def sortFields(fields: Set[String], samples: List[String]): List[String] = {
def fieldType(x: String) = x match {
case _ if x.startsWith("INFO-") => 'i'
- case _ if (samples.exists(y => x.startsWith(y + "-"))) => 'f'
+ case _ if samples.exists(y => x.startsWith(y + "-")) => 'f'
case _ => 'g'
}
fields.toList.sortWith((a, b) => {
(fieldType(a), fieldType(b)) match {
- case ('g', 'g') => {
+ case ('g', 'g') =>
val ai = defaultFields.indexOf(a)
val bi = defaultFields.indexOf(b)
if (bi < 0) true else ai <= bi
- }
- case ('f', 'f') => {
+ case ('f', 'f') =>
val sampleA = a.split("-").head
val sampleB = b.split("-").head
sampleA.compareTo(sampleB) match {
- case 0 => !(a.compareTo(b) > 0)
- case i if (i > 0) => false
- case _ => true
+ case 0 => !(a.compareTo(b) > 0)
+ case i if i > 0 => false
+ case _ => true
}
- }
- case ('g', _) => true
- case (_, 'g') => false
- case (a, b) if a == b => !(a.compareTo(b) > 0)
- case ('i', _) => true
- case _ => false
+ case ('g', _) => true
+ case (_, 'g') => false
+ case (a2, b2) if a2 == b2 => !(a2.compareTo(b2) > 0)
+ case ('i', _) => true
+ case _ => false
}
})
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala
index 94bb8fa20078238839953c7a119beaebc0611a51..f78dd804028168f04980fa9ba8ec9d925ab3ee2d 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VcfWithVcf.scala
@@ -10,6 +10,8 @@ import nl.lumc.sasc.biopet.core.ToolCommand
import scala.collection.JavaConversions._
/**
+ * This is a tool to annotate a vcf file with info value from a other vcf file
+ *
* Created by ahbbollen on 11-2-15.
*/
object VcfWithVcf extends ToolCommand {
@@ -26,30 +28,29 @@ object VcfWithVcf extends ToolCommand {
}
class OptParser extends AbstractOptParser {
- opt[File]('I', "inputFile") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ 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) =>
+ opt[File]('O', "outputFile") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(outputFile = x)
}
- opt[File]('S', "secondaryVcf") required () maxOccurs (1) valueName ("<file>") action { (x, c) =>
+ opt[File]('S', "secondaryVcf") required () maxOccurs 1 valueName "<file>" action { (x, c) =>
c.copy(secondaryVcf = x)
}
- opt[String]('f', "field") unbounded () valueName ("<field> or <input_field:output_field> or <input_field:output_field:method>") action { (x, c) =>
+ opt[String]('f', "field") unbounded () valueName "<field> or <input_field:output_field> or <input_field:output_field:method>" action { (x, c) =>
val values = x.split(":")
if (values.size > 2) c.copy(fields = Fields(values(0), values(1), FieldMethod.withName(values(2))) :: c.fields)
else if (values.size > 1) c.copy(fields = Fields(values(0), values(1)) :: c.fields)
else c.copy(fields = Fields(x, x) :: c.fields)
- } text ("""| If only <field> is given, the field's identifier in the output VCF will be identical to <field>.
- | By default we will return all values found for a given field.
- | With <method> the values will processed after getting it from the secondary VCF file, posible methods are:
- | - max : takes maximum of found value, only works for numeric (integer/float) fields
- | - min : takes minemal of found value, only works for numeric (integer/float) fields
- | - unique: takes only unique values """.stripMargin
- )
- opt[Boolean]("match") valueName ("<Boolean>") maxOccurs (1) action { (x, c) =>
+ } text """| If only <field> is given, the field's identifier in the output VCF will be identical to <field>.
+ | By default we will return all values found for a given field.
+ | With <method> the values will processed after getting it from the secondary VCF file, posible methods are:
+ | - max : takes maximum of found value, only works for numeric (integer/float) fields
+ | - min : takes minemal of found value, only works for numeric (integer/float) fields
+ | - unique: takes only unique values """.stripMargin
+ opt[Boolean]("match") valueName "<Boolean>" maxOccurs 1 action { (x, c) =>
c.copy(matchAllele = x)
- } text ("Match alternative alleles; default true")
+ } text "Match alternative alleles; default true"
}
def main(args: Array[String]): Unit = {
@@ -88,18 +89,16 @@ object VcfWithVcf extends ToolCommand {
for (record <- reader) {
val secondaryRecords = if (commandArgs.matchAllele) {
secondaryReader.query(record.getChr, record.getStart, record.getEnd).toList.
- filter(x => record.getAlternateAlleles.exists(x.hasAlternateAllele(_)))
+ filter(x => record.getAlternateAlleles.exists(x.hasAlternateAllele))
} else {
secondaryReader.query(record.getChr, record.getStart, record.getEnd).toList
}
val fieldMap = (for (
- f <- commandArgs.fields;
- if secondaryRecords.exists(_.hasAttribute(f.inputField))
+ f <- commandArgs.fields if secondaryRecords.exists(_.hasAttribute(f.inputField))
) yield {
f.outputField -> (for (
- secondRecord <- secondaryRecords;
- if (secondRecord.hasAttribute(f.inputField))
+ secondRecord <- secondaryRecords if secondRecord.hasAttribute(f.inputField)
) yield {
secondRecord.getAttribute(f.inputField) match {
case l: List[_] => l
@@ -110,20 +109,18 @@ object VcfWithVcf extends ToolCommand {
writer.add(fieldMap.foldLeft(new VariantContextBuilder(record))((builder, attribute) => {
builder.attribute(attribute._1, commandArgs.fields.filter(_.outputField == attribute._1).head.fieldMethod match {
- case FieldMethod.max => {
+ case FieldMethod.max =>
header.getInfoHeaderLine(attribute._1).getType match {
case VCFHeaderLineType.Integer => Array(attribute._2.map(_.toString.toInt).max)
case VCFHeaderLineType.Float => Array(attribute._2.map(_.toString.toFloat).max)
case _ => throw new IllegalArgumentException("Type of field " + attribute._1 + " is not numeric")
}
- }
- case FieldMethod.min => {
+ case FieldMethod.min =>
header.getInfoHeaderLine(attribute._1).getType match {
case VCFHeaderLineType.Integer => Array(attribute._2.map(_.toString.toInt).min)
case VCFHeaderLineType.Float => Array(attribute._2.map(_.toString.toFloat).min)
case _ => throw new IllegalArgumentException("Type of field " + attribute._1 + " is not numeric")
}
- }
case FieldMethod.unique => attribute._2.distinct.toArray
case _ => attribute._2.toArray
})
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VepNormalizer.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VepNormalizer.scala
index c1c090e26aaf24861d009150dcb426a2d9b5675b..b953184bd7db2c67faaa85cc01cb9d5968e77d7c 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VepNormalizer.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/VepNormalizer.scala
@@ -191,7 +191,7 @@ object VepNormalizer extends ToolCommand {
def explodeTranscripts(record: VariantContext, csqInfos: Array[String], removeCsq: Boolean): Array[VariantContext] = {
for (transcript <- parseCsq(record)) yield {
(for (
- fieldId <- 0 until csqInfos.size if transcript.isDefinedAt(fieldId);
+ fieldId <- csqInfos.indices if transcript.isDefinedAt(fieldId);
value = transcript(fieldId) if value.nonEmpty
) yield csqInfos(fieldId) -> value)
.filterNot(_._2.isEmpty)
@@ -203,7 +203,7 @@ object VepNormalizer extends ToolCommand {
def standardTranscripts(record: VariantContext, csqInfos: Array[String], removeCsq: Boolean): VariantContext = {
val attribs = parseCsq(record)
- (for (fieldId <- 0 until csqInfos.size) yield csqInfos(fieldId) -> {
+ (for (fieldId <- csqInfos.indices) yield csqInfos(fieldId) -> {
for (
transcript <- attribs if transcript.isDefinedAt(fieldId);
value = transcript(fieldId) if value.nonEmpty
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala
index d047b3d8ba997e6bcab52c583ae5d003310cb641..4060560236166e49d80d104b09a682d116afb16f 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/tools/WipeReads.scala
@@ -257,7 +257,7 @@ object WipeReads extends ToolCommand {
/** filter function for read IDs */
val rgFilter =
- if (readGroupIds.size == 0)
+ if (readGroupIds.isEmpty)
(r: SAMRecord) => true
else
(r: SAMRecord) => readGroupIds.contains(r.getReadGroup.getReadGroupId)
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala
index 4e08cfecb11fdaba1b845de0bd3a1fe40eb3121d..12167b9b9a60fa379b100d8b1280d8fa0fc8e990 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/ConfigUtils.scala
@@ -44,17 +44,16 @@ object ConfigUtils extends Logging {
else if (!map1.contains(key)) newMap += (key -> map2(key))
else {
map1(key) match {
- case m1: Map[_, _] => {
+ case m1: Map[_, _] =>
map2(key) match {
case m2: Map[_, _] => newMap += (key -> mergeMaps(any2map(m1), any2map(m2)))
case _ => newMap += (key -> map1(key))
}
- }
case _ => newMap += (key -> resolveConflict(map1(key), map2(key), key))
}
}
}
- return newMap
+ newMap
}
/**
@@ -79,7 +78,7 @@ object ConfigUtils extends Logging {
*/
def getValueFromPath(map: Map[String, Any], path: List[String]): Option[Any] = {
val value = map.get(path.head)
- if (path.tail == Nil || value == None) value
+ if (path.tail.isEmpty || value.isEmpty) value
else value.get match {
case map: Map[_, _] => getValueFromPath(map.asInstanceOf[Map[String, Any]], path.tail)
case map: java.util.LinkedHashMap[_, _] => getValueFromPath(map.toMap.asInstanceOf[Map[String, Any]], path.tail)
@@ -107,7 +106,7 @@ object ConfigUtils extends Logging {
else jsonToMap(fileToJson(configFile))
}
logger.debug("Contain: " + configMap)
- return configMap
+ configMap
}
/** Convert a yaml file to map[String, Any] */
@@ -126,23 +125,23 @@ object ConfigUtils extends Logging {
output += (key -> value)
}
} else throw new IllegalStateException("Given value is no json object: " + json)
- return output
+ output
}
/** Convert json value to native scala value */
def jsonToAny(json: Json): Any = {
- if (json.isObject) return jsonToMap(json)
+ if (json.isObject) jsonToMap(json)
else if (json.isArray) {
var list: List[Any] = List()
for (value <- json.array.get) list ::= jsonToAny(value)
- return list.reverse
- } else if (json.isBool) return json.bool.get
- else if (json.isString) return json.string.get.toString
+ list.reverse
+ } else if (json.isBool) json.bool.get
+ else if (json.isString) json.string.get.toString
else if (json.isNumber) {
val num = json.number.get
- if (num % 1 > 0) return num.toDouble
- else return num.toLong
- } else if (json.isNull) return None
+ if (num % 1 > 0) num.toDouble
+ else num.toLong
+ } else if (json.isNull) None
else throw new IllegalStateException("Config value type not supported, value: " + json)
}
@@ -163,7 +162,7 @@ object ConfigUtils extends Logging {
case None => Json.jNull
case Some(x) => anyToJson(x)
case m: Map[_, _] => mapToJson(m.map(m => m._1.toString -> anyToJson(m._2)))
- case l: List[_] => Json.array(l.map(anyToJson(_)): _*)
+ case l: List[_] => Json.array(l.map(anyToJson): _*)
case b: Boolean => Json.jBool(b)
case n: Int => Json.jNumberOrString(n)
case n: Double => Json.jNumberOrString(n)
@@ -190,10 +189,9 @@ object ConfigUtils extends Logging {
case i: Int => i
case i: Double => i.toInt
case i: Long => i.toInt
- case i: String => {
+ case i: String =>
logger.warn("Value '" + any + "' is a string insteadof int in json file, trying auto convert")
i.toInt
- }
case _ => throw new IllegalStateException("Value '" + any + "' is not an int")
}
}
@@ -204,10 +202,9 @@ object ConfigUtils extends Logging {
case l: Double => l.toLong
case l: Int => l.toLong
case l: Long => l
- case l: String => {
+ case l: String =>
logger.warn("Value '" + any + "' is a string insteadof int in json file, trying auto convert")
l.toLong
- }
case _ => throw new IllegalStateException("Value '" + any + "' is not an int")
}
}
@@ -219,10 +216,9 @@ object ConfigUtils extends Logging {
case d: Float => d.toDouble
case d: Int => d.toDouble
case f: Long => f.toDouble
- case d: String => {
+ case d: String =>
logger.warn("Value '" + any + "' is a string insteadof int in json file, trying auto convert")
- return d.toDouble
- }
+ d.toDouble
case _ => throw new IllegalStateException("Value '" + any + "' is not an number")
}
}
@@ -234,10 +230,9 @@ object ConfigUtils extends Logging {
case f: Int => f.toFloat
case f: Long => f.toFloat
case f: Float => f
- case f: String => {
+ case f: String =>
logger.warn("Value '" + any + "' is a string insteadof int in json file, trying auto convert")
f.toFloat
- }
case _ => throw new IllegalStateException("Value '" + any + "' is not an number")
}
}
@@ -246,14 +241,12 @@ object ConfigUtils extends Logging {
def any2boolean(any: Any): Boolean = {
any match {
case b: Boolean => b
- case b: String => {
+ case b: String =>
logger.warn("Value '" + any + "' is a string insteadof boolean in json file, trying auto convert")
b.contains("true")
- }
- case b: Int => {
+ case b: Int =>
logger.warn("Value '" + any + "' is a int insteadof boolean in json file, trying auto convert")
- (b > 0)
- }
+ b > 0
case _ => throw new IllegalStateException("Value '" + any + "' is not an boolean")
}
}
@@ -308,7 +301,7 @@ object ConfigUtils extends Logging {
if (!exist)
BiopetQScript.addError("Value does not exist but is required, key: " + value.requestIndex.key +
" module: " + value.requestIndex.module,
- (if (value.requestIndex.path != Nil) " path: " + value.requestIndex.path.mkString("->") else null))
+ if (value.requestIndex.path != Nil) " path: " + value.requestIndex.path.mkString("->") else null)
exist
}
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/IoUtils.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/IoUtils.scala
index 6333763bb35421ebace6a758cddb705f90ab64ef..49bf3fe86cd5664aea9e96000ebd2291ed5fa9b2 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/IoUtils.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/IoUtils.scala
@@ -3,6 +3,8 @@ package nl.lumc.sasc.biopet.utils
import java.io.{ File, FileInputStream, FileOutputStream, InputStream }
/**
+ * This object contains generic io methods
+ *
* Created by pjvan_thof on 6/4/15.
*/
object IoUtils {
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/VcfUtils.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/VcfUtils.scala
index 886d3985a17f5454c83cb73c48ef1190162d132d..9074ff1f3bcc71fda5ad5c8aa9ba5ae5867fc6c8 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/VcfUtils.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/utils/VcfUtils.scala
@@ -41,6 +41,6 @@ object VcfUtils {
* @return
*/
def fillAllele(bases: String, newSize: Int, fillWith: Char = '-'): String = {
- bases + (Array.fill[Char](newSize - bases.size)(fillWith)).mkString
+ bases + Array.fill[Char](newSize - bases.length)(fillWith).mkString
}
}