Skip to content
GitLab
Commit 2c2e3865 authored by Peter van 't Hof's avatar Peter van 't Hof
Browse files

Removing some meta files from jar

parent 38103728
Hide whitespace changes
Inline Side-by-side
biopet-package/pom.xml
View file @ 2c2e3865
......@@ -155,6 +155,14 @@
</transformer>
</transformers>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
</configuration>
<executions>
......
biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/vcfstats/Stats.scala
View file @ 2c2e3865
......@@ -163,13 +163,20 @@ case class Stats(generalStats: mutable.Map[String, mutable.Map[String, mutable.M
"info" -> infoFields.map(f => f -> getField(f, contig)).toMap,
"sample_distributions" -> sampleDistributions
.map(f => f -> getField("SampleDistribution-" + f, contig))
.toMap,
"sample_compare" -> Map(
"samples" -> samples,
"genotype_overlap" -> samples.map(sample1 => samples.map(sample2 => samplesStats(sample1).sampleToSample(sample2).genotypeOverlap)),
"allele_overlap" -> samples.map(sample1 => samples.map(sample2 => samplesStats(sample1).sampleToSample(sample2).alleleOverlap))
)
)
.toMap
) ++ (if (contig == "total")
Map(
"sample_compare" -> Map(
"samples" -> samples,
"genotype_overlap" -> samples.map(sample1 =>
samples.map(sample2 =>
samplesStats(sample1).sampleToSample(sample2).genotypeOverlap)),
"allele_overlap" -> samples.map(sample1 =>
samples.map(sample2 =>
samplesStats(sample1).sampleToSample(sample2).alleleOverlap))
)
)
else Map())
}
/** This will generate stats for total */
......
biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/vcfstats/VcfStats.scala
View file @ 2c2e3865
......@@ -81,18 +81,18 @@ object VcfStats extends ToolCommand {
)
val genotypeWiggleOptions = List("Total",
"Het",
"HetNonRef",
"Hom",
"HomRef",
"HomVar",
"Mixed",
"NoCall",
"NonInformative",
"Available",
"Called",
"Filtered",
"Variant")
"Het",
"HetNonRef",
"Hom",
"HomRef",
"HomVar",
"Mixed",
"NoCall",
"NonInformative",
"Available",
"Called",
"Filtered",
"Variant")
/** Parsing commandline arguments */
class OptParser extends AbstractOptParser {
......@@ -149,16 +149,16 @@ object VcfStats extends ToolCommand {
if (genotypeWiggleOptions.contains(x)) success else failure(s"""Non-existent field $x""")
} text s"""Create a wiggle track with bin size <binSize> for any of the following genotype fields:
|${genotypeWiggleOptions.mkString(", ")}""".stripMargin
opt[Int]('t',"localThreads")unbounded () action { (x, c) =>
opt[Int]('t', "localThreads") unbounded () action { (x, c) =>
c.copy(localThreads = x)
} text s"Number of local threads to use"
opt[String]("sparkMaster")unbounded () action { (x, c) =>
opt[String]("sparkMaster") unbounded () action { (x, c) =>
c.copy(sparkMaster = Some(x))
} text s"Spark master to use"
}
protected var cmdArgs: Args = _
//protected var cmdArgs: Args = _
val defaultGenotypeFields =
List("DP", "GQ", "AD", "AD-ref", "AD-alt", "AD-used", "AD-not_used", "general")
......@@ -184,7 +184,7 @@ object VcfStats extends ToolCommand {
def main(args: Array[String]): Unit = {
logger.info("Started")
val argsParser = new OptParser
cmdArgs = argsParser.parse(args, Args()) getOrElse (throw new IllegalArgumentException)
val cmdArgs = argsParser.parse(args, Args()) getOrElse (throw new IllegalArgumentException)
logger.info("Init spark context")
......@@ -334,14 +334,14 @@ object VcfStats extends ToolCommand {
// Write general wiggle tracks
for (field <- cmdArgs.generalWiggle) {
val file = new File(cmdArgs.outputDir, "wigs" + File.separator + "general-" + field + ".wig")
writeWiggle(intervals, field, "count", file, genotype = false)
writeWiggle(intervals, field, "count", file, genotype = false, cmdArgs.outputDir)
}
// Write sample wiggle tracks
for (field <- cmdArgs.genotypeWiggle; sample <- samples) {
val file = new File(cmdArgs.outputDir,
"wigs" + File.separator + "genotype-" + sample + "-" + field + ".wig")
writeWiggle(intervals, field, sample, file, genotype = true)
writeWiggle(intervals, field, sample, file, genotype = true, cmdArgs.outputDir)
}
writeOverlap(stats,
......@@ -362,7 +362,8 @@ object VcfStats extends ToolCommand {
row: String,
column: String,
outputFile: File,
genotype: Boolean): Unit = {
genotype: Boolean,
outputDir: File): Unit = {
val groupedIntervals =
intervals.groupBy(_.getContig).map { case (k, v) => k -> v.sortBy(_.getStart) }
outputFile.getParentFile.mkdirs()
......@@ -375,11 +376,11 @@ object VcfStats extends ToolCommand {
val file = {
if (genotype)
new File(
cmdArgs.outputDir,
outputDir,
"bins" + File.separator + chr + File.separator + "genotype-" + interval.getStart + "-" + interval.getEnd + "-general.tsv")
else
new File(
cmdArgs.outputDir,
outputDir,
"bins" + File.separator + chr + File.separator + interval.getStart + "-" + interval.getEnd + "-general.tsv")
}
writer.println(valueFromTsv(file, row, column).getOrElse(0))
......@@ -639,7 +640,8 @@ object VcfStats extends ToolCommand {
def writeOverlap(stats: Stats,
function: SampleToSampleStats => Int,
prefix: String,
samples: List[String]): Unit = {
samples: List[String],
plots: Boolean = true): Unit = {
val absFile = new File(prefix + ".abs.tsv")
val relFile = new File(prefix + ".rel.tsv")
......@@ -662,7 +664,7 @@ object VcfStats extends ToolCommand {
absWriter.close()
relWriter.close()
plotHeatmap(relFile)
if (plots) plotHeatmap(relFile)
}
/** Plots heatmaps on target tsv file */
......
biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/vcfstats/VcfStatsSpark.scala
View file @ 2c2e3865
......@@ -9,7 +9,9 @@ import nl.lumc.sasc.biopet.utils.intervals.{BedRecord, BedRecordList}
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection.JavaConversions._
import scala.concurrent.{Await, Future}
import scala.concurrent.ExecutionContext.Implicits.global
import scala.concurrent.duration.Duration
/**
* Created by pjvanthof on 14/07/2017.
......@@ -73,15 +75,14 @@ object VcfStatsSpark extends ToolCommand {
if (genotypeWiggleOptions.contains(x)) success else failure(s"""Non-existent field $x""")
} text s"""Create a wiggle track with bin size <binSize> for any of the following genotype fields:
|${genotypeWiggleOptions.mkString(", ")}""".stripMargin
opt[Int]('t',"localThreads")unbounded () action { (x, c) =>
opt[Int]('t', "localThreads") unbounded () action { (x, c) =>
c.copy(localThreads = x)
} text s"Number of local threads to use"
opt[String]("sparkMaster")unbounded () action { (x, c) =>
opt[String]("sparkMaster") unbounded () action { (x, c) =>
c.copy(sparkMaster = Some(x))
} text s"Spark master to use"
}
def main(args: Array[String]): Unit = {
logger.info("Started")
......@@ -97,7 +98,7 @@ object VcfStatsSpark extends ToolCommand {
val adInfoTags = {
(for (infoTag <- cmdArgs.infoTags if !defaultInfoFields.contains(infoTag)) yield {
require(header.getInfoHeaderLine(infoTag) != null,
"Info tag '" + infoTag + "' not found in header of vcf file")
"Info tag '" + infoTag + "' not found in header of vcf file")
infoTag
}) ::: (for (line <- header.getInfoHeaderLines if cmdArgs.allInfoTags
if !defaultInfoFields.contains(line.getID)
......@@ -109,7 +110,7 @@ object VcfStatsSpark extends ToolCommand {
val adGenotypeTags = (for (genotypeTag <- cmdArgs.genotypeTags
if !defaultGenotypeFields.contains(genotypeTag)) yield {
require(header.getFormatHeaderLine(genotypeTag) != null,
"Format tag '" + genotypeTag + "' not found in header of vcf file")
"Format tag '" + genotypeTag + "' not found in header of vcf file")
genotypeTag
}) ::: (for (line <- header.getFormatHeaderLines if cmdArgs.allGenotypeTags
if !defaultGenotypeFields.contains(line.getID)
......@@ -118,7 +119,6 @@ object VcfStatsSpark extends ToolCommand {
line.getID
}).toList ::: defaultGenotypeFields
logger.info("Init spark context")
val conf = new SparkConf()
......@@ -135,11 +135,31 @@ object VcfStatsSpark extends ToolCommand {
.scatter(cmdArgs.binSize)
.flatten
val regionStats = sc.parallelize(regions, regions.size).groupBy(_.chr).map { case (contig, records) => contig -> records.map(readBin(_, samples, cmdArgs, adInfoTags, adGenotypeTags))}
val regionStats = sc.parallelize(regions, regions.size).groupBy(_.chr).map {
case (contig, records) =>
contig -> records.map(readBin(_, samples, cmdArgs, adInfoTags, adGenotypeTags))
}
val chrStats = regionStats.map {case (contig, stats) => contig -> stats.reduce(_ += _)}
val chrStats =
regionStats.map { case (contig, stats) => contig -> stats.reduce(_ += _) }.cache()
val contigOverlap = chrStats.map {
case (contig, stats) =>
writeOverlap(stats,
_.genotypeOverlap,
cmdArgs.outputDir + s"/sample_compare/contigs/$contig/genotype_overlap",
samples,
cmdArgs.contigSampleOverlapPlots)
writeOverlap(stats,
_.alleleOverlap,
cmdArgs.outputDir + s"/sample_compare/contigs/$contig/allele_overlap",
samples,
cmdArgs.contigSampleOverlapPlots)
}
val totalStats = chrStats.values.reduce(_ += _)
val totalStats = chrStats.values.reduce(_ += _) // Blocking
//Await.ready(contigOverlap, Duration.Inf)
val allWriter = new PrintWriter(new File(cmdArgs.outputDir, "stats.json"))
val json = ConfigUtils.mapToJson(
......@@ -155,19 +175,21 @@ object VcfStatsSpark extends ToolCommand {
//TODO: write wig files
writeOverlap(totalStats,
_.genotypeOverlap,
cmdArgs.outputDir + "/sample_compare/genotype_overlap",
samples)
_.genotypeOverlap,
cmdArgs.outputDir + "/sample_compare/genotype_overlap",
samples)
writeOverlap(totalStats,
_.alleleOverlap,
cmdArgs.outputDir + "/sample_compare/allele_overlap",
samples)
_.alleleOverlap,
cmdArgs.outputDir + "/sample_compare/allele_overlap",
samples)
Thread.sleep(1000000)
sc.stop
logger.info("Done")
}
def readBin(bedRecord: BedRecord, samples: List[String],
def readBin(bedRecord: BedRecord,
samples: List[String],
cmdArgs: Args,
adInfoTags: List[String],
adGenotypeTags: List[String]): Stats = {
......@@ -184,7 +206,7 @@ object VcfStatsSpark extends ToolCommand {
Stats.mergeNestedStatsMap(stats.generalStats, fillGeneral(adInfoTags))
for (sample <- samples) yield {
Stats.mergeNestedStatsMap(stats.samplesStats(sample).genotypeStats,
fillGenotype(adGenotypeTags))
fillGenotype(adGenotypeTags))
}
chunkCounter += 1
}
......@@ -194,7 +216,7 @@ object VcfStatsSpark extends ToolCommand {
for (sample1 <- samples) yield {
val genotype = record.getGenotype(sample1)
Stats.mergeNestedStatsMap(stats.samplesStats(sample1).genotypeStats,
checkGenotype(record, genotype, adGenotypeTags))
checkGenotype(record, genotype, adGenotypeTags))
for (sample2 <- samples) {
val genotype2 = record.getGenotype(sample2)
if (genotype.getAlleles == genotype2.getAlleles)
......@@ -213,16 +235,17 @@ object VcfStatsSpark extends ToolCommand {
/** Commandline argument */
case class VcfStatsArgs(inputFile: File = null,
outputDir: File = null,
referenceFile: File = null,
intervals: Option[File] = None,
infoTags: List[String] = Nil,
genotypeTags: List[String] = Nil,
allInfoTags: Boolean = false,
allGenotypeTags: Boolean = false,
binSize: Int = 10000000,
writeBinStats: Boolean = false,
generalWiggle: List[String] = Nil,
genotypeWiggle: List[String] = Nil,
localThreads: Int = 1,
sparkMaster: Option[String] = None)
outputDir: File = null,
referenceFile: File = null,
intervals: Option[File] = None,
infoTags: List[String] = Nil,
genotypeTags: List[String] = Nil,
allInfoTags: Boolean = false,
allGenotypeTags: Boolean = false,
binSize: Int = 10000000,
writeBinStats: Boolean = false,
generalWiggle: List[String] = Nil,
genotypeWiggle: List[String] = Nil,
localThreads: Int = 1,
sparkMaster: Option[String] = None,
contigSampleOverlapPlots: Boolean = false)
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment