Add extension wrapper for biopet, Allow to skipNames in reporting for concise...

Add extension wrapper for biopet, Allow to skipNames in reporting for concise report containing only counts and taxonID's

public/biopet-tools-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/tools/KrakenReportToJson.scala

+package nl.lumc.sasc.biopet.extensions.tools
+
+/**
+ * Created by waiyileung on 05-10-15.
+ */
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.ToolCommandFuntion
+import nl.lumc.sasc.biopet.core.summary.Summarizable
+import nl.lumc.sasc.biopet.utils.ConfigUtils
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{Argument, Output, Input}
+
+/**
+ * KrakenReportToJson function class for usage in Biopet pipelines
+ *
+ * @param root Configuration object for the pipeline
+ */
+class KrakenReportToJson(val root: Configurable) extends ToolCommandFuntion with Summarizable {
+  def toolObject = nl.lumc.sasc.biopet.tools.KrakenReportToJson
+
+  @Input(doc = "Input Kraken Full report", shortName = "inputReport", required = true)
+  var inputReport: File = null
+
+  @Argument(required = false)
+  var skipNames: Boolean = true
+
+  @Output(doc = "Output JSON", shortName = "output", required = true)
+  var output: File = null
+
+  override def defaultCoreMemory = 1.0
+
+  override def commandLine = super.commandLine + required("-i", inputReport) + required("-o", output)
+
+  def summaryStats: Map[String, Any] = {
+    val map = ConfigUtils.fileToConfigMap(output)
+
+    ConfigUtils.any2map(map.getOrElse("stats", Map()))
+  }
+
+  def summaryFiles: Map[String, File] = Map()
+
+}
+
+object KrakenReportToJson {
+  def apply(root: Configurable, input: File, output: File): KrakenReportToJson = {
+    val report = new KrakenReportToJson(root)
+    report.inputReport = input
+    report.output = new File(output, input.getName.substring(0, input.getName.lastIndexOf(".")) + ".kraken.json")
+    report
+  }
+
+  def apply(root: Configurable, input: File, outDir: String): KrakenReportToJson = {
+    val report = new KrakenReportToJson(root)
+    report.inputReport = input
+    report.output = new File(outDir, input.getName.substring(0, input.getName.lastIndexOf(".")) + ".kraken.json")
+    report
+  }
+}
+

public/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools/KrakenReportToJson.scala

@@ -56,7 +56,7 @@ object KrakenReportToJson extends ToolCommand {
   var cladeIDs: mutable.ArrayBuffer[Long] = mutable.ArrayBuffer.fill(32)(0)
   val spacePattern = "^( +)".r
 
-  case class Args(krakenreport: File = null, outputJson: Option[File] = None) extends AbstractArgs
+  case class Args(krakenreport: File = null, outputJson: Option[File] = None, skipNames: Boolean = true) extends AbstractArgs
 
   class OptParser extends AbstractOptParser {
 
@@ -70,9 +70,15 @@ object KrakenReportToJson extends ToolCommand {
     } validate {
       x => if (x.exists) success else failure("Krakenreport not found")
     } text "Kraken report to generate stats from"
+
     opt[File]('o', "output") unbounded () valueName "<json>" action { (x, c) =>
       c.copy(outputJson = Some(x))
     } text "File to write output to, if not supplied output go to stdout"
+
+    opt[Boolean]('n', "skipnames") unbounded () valueName "<skipnames>" action { (x, c) =>
+      c.copy(skipNames = x)
+    } text "Don't report the scientific name of the taxon."
+
   }
 
   /**
@@ -85,7 +91,7 @@ object KrakenReportToJson extends ToolCommand {
     .parse(args, Args())
     .getOrElse(sys.exit(1))
 
-  def parseLine(krakenRawHit: String): Map[Long, KrakenHit] = {
+  def parseLine(krakenRawHit: String, skipNames: Boolean): Map[Long, KrakenHit] = {
     val values: Array[String] = krakenRawHit.stripLineEnd.split("\t")
     val scientificName: String = values(5)
     val cladeLevel = spacePattern.findFirstIn(scientificName).getOrElse("").length / 2
@@ -98,7 +104,7 @@ object KrakenReportToJson extends ToolCommand {
     Map(
       values(4).toLong -> new KrakenHit(
         taxonomyID = values(4).toLong,
-        taxonomyName = scientificName.trim,
+        taxonomyName = if (skipNames) "" else scientificName.trim,
         cladeCount = values(2).toLong,
         cladeSize = values(1).toLong,
         taxonRank = values(3),
@@ -108,7 +114,7 @@ object KrakenReportToJson extends ToolCommand {
       ))
   }
 
-  def reportToJson(reportRaw: File): String = {
+  def reportToJson(reportRaw: File, skipNames: Boolean): String = {
     val reader = Source.fromFile(reportRaw)
     //    val lines = reader.getLines().toList.filter(!_.isEmpty)
 
@@ -124,7 +130,7 @@ object KrakenReportToJson extends ToolCommand {
     * */
 
     val lines = reader.getLines()
-      .map(line => parseLine(line))
+      .map(line => parseLine(line, skipNames))
       .filter(p => p.head._2.cladeSize > 0)
       .foldLeft(Map.empty[Long, KrakenHit])((a, b) => {
         a + b.head
@@ -142,7 +148,7 @@ object KrakenReportToJson extends ToolCommand {
   def main(args: Array[String]): Unit = {
     val commandArgs: Args = parseArgs(args)
 
-    val jsonString: String = reportToJson(commandArgs.krakenreport)
+    val jsonString: String = reportToJson(commandArgs.krakenreport, skipNames = commandArgs.skipNames)
     commandArgs.outputJson match {
       case Some(file) => {
         val writer = new PrintWriter(file)

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/Gears.scala

@@ -20,16 +20,16 @@ import nl.lumc.sasc.biopet.core.summary.SummaryQScript
 import nl.lumc.sasc.biopet.extensions.kraken.{ Kraken, KrakenReport }
 import nl.lumc.sasc.biopet.extensions.picard.SamToFastq
 import nl.lumc.sasc.biopet.extensions.sambamba.SambambaView
-import nl.lumc.sasc.biopet.extensions.tools.FastqSync
+import nl.lumc.sasc.biopet.extensions.tools.{KrakenReportToJson, FastqSync}
 import nl.lumc.sasc.biopet.utils.config.Configurable
-import nl.lumc.sasc.biopet.tools.KrakenReportToJson
 import org.broadinstitute.gatk.queue.QScript
 
 /**
  * This is a trait for the Gears pipeline
  * The ShivaTrait is used as template for this pipeline
  */
-class Gears(val root: Configurable) extends QScript with SummaryQScript { qscript =>
+class Gears(val root: Configurable) extends QScript with SummaryQScript {
+  qscript =>
   def this() = this(null)
 
   @Input(shortName = "R1", required = false)
@@ -115,10 +115,16 @@ class Gears(val root: Configurable) extends QScript with SummaryQScript { qscrip
     add(krakenReport)
 
     val krakenReportJSON = new KrakenReportToJson(qscript)
-    krakenReportJSON.input = krakenReport.output
+    krakenReportJSON.inputReport = krakenAnalysis.output
     krakenReportJSON.output = new File(outputDir, s"$outputName.krkn.json")
+    krakenReportJSON.skipNames = config("skipNames", default = true)
     add(krakenReportJSON)
 
+//    val krakenReportJSON = new KrakenReportToJson(qscript)
+//    krakenReportJSON.input = krakenReport.output
+//    krakenReportJSON.output = new File(outputDir, s"$outputName.krkn.json")
+//    add(krakenReportJSON)
+
     addSummaryJobs()
   }
 
@@ -129,7 +135,8 @@ class Gears(val root: Configurable) extends QScript with SummaryQScript { qscrip
   def summarySettings = Map()
 
   /** Files for the summary */
-  def summaryFiles = Map()
+  def summaryFiles = (if (bamFile.isDefined) Map("input_bam" -> bamFile.get) else Map()) ++
+    (if (fastqFileR1.isDefined) Map("input_R1" -> fastqFileR1.get) else Map())
 }
 
 /** This object give a default main method to the pipelines */