Update TinyCap with Gentrap Measures and fixes some typos in the measures (from the merge)

protected/biopet-gatk-pipelines/src/main/scala/nl/lumc/sasc/biopet/pipelines/gatk/Shiva.scala

@@ -6,9 +6,9 @@
 package nl.lumc.sasc.biopet.pipelines.gatk
 
 import nl.lumc.sasc.biopet.core.PipelineCommand
-import nl.lumc.sasc.biopet.utils.config.Configurable
 import nl.lumc.sasc.biopet.extensions.gatk.broad._
-import nl.lumc.sasc.biopet.pipelines.shiva.{ ShivaVariantcallingTrait, ShivaTrait }
+import nl.lumc.sasc.biopet.pipelines.shiva.ShivaTrait
+import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
 /**

public/TinyCap/pom.xml

@@ -17,6 +17,11 @@
             <artifactId>Mapping</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>nl.lumc.sasc</groupId>
+            <artifactId>Gentrap</artifactId>
+            <version>${project.version}</version>
+        </dependency>
     </dependencies>
 
 </project>
\ No newline at end of file

public/TinyCap/src/main/scala/nl/lumc/sasc/biopet/pipelines/tinycap/TinyCap.scala

 package nl.lumc.sasc.biopet.pipelines.tinycap
 
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.annotations.{ AnnotationGff, AnnotationGtf, AnnotationRefFlat }
 import nl.lumc.sasc.biopet.core.report.ReportBuilderExtension
 import nl.lumc.sasc.biopet.core.{ PipelineCommand, Reference }
-import nl.lumc.sasc.biopet.extensions.HtseqCount
+import nl.lumc.sasc.biopet.pipelines.gentrap.measures.{ BaseCounts, FragmentsPerGene }
 import nl.lumc.sasc.biopet.pipelines.mapping.MultisampleMappingTrait
+import nl.lumc.sasc.biopet.pipelines.tinycap.measures.FragmentsPerSmallRna
 import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
@@ -12,12 +16,15 @@ import org.broadinstitute.gatk.queue.QScript
  * Design based on work from Henk Buermans (e-Mir)
  * Implementation by wyleung started 19/01/16
  */
-class TinyCap(val root: Configurable) extends QScript with MultisampleMappingTrait with Reference {
+class TinyCap(val root: Configurable) extends QScript
+  with MultisampleMappingTrait
+  with AnnotationRefFlat
+  with AnnotationGff
+  with AnnotationGtf
+  with Reference {
   qscript =>
   def this() = this(null)
 
-  var annotationGff: File = config("annotation_gff")
-  var annotationGtf: File = config("annotation_gtf")
   var annotateSam: Boolean = config("annotate_sam", default = false)
 
   override def defaults = Map(
@@ -32,6 +39,10 @@ class TinyCap(val root: Configurable) extends QScript with MultisampleMappingTra
       "generate_wig" -> true,
       "skip_markduplicates" -> true
     ),
+    "bammetrics" -> Map(
+      "wgs_metrics" -> false,
+      "rna_metrics" -> true
+    ),
     "bowtie" -> Map(
       "chunkmbs" -> 256,
       "seedmms" -> 3,
@@ -54,38 +65,34 @@ class TinyCap(val root: Configurable) extends QScript with MultisampleMappingTra
     )
   )
 
+  lazy val fragmentsPerGene = Some(new FragmentsPerGene(this))
+  lazy val fragmentsPerSmallRna = Some(new FragmentsPerSmallRna(this))
+  lazy val baseCounts = Some(new BaseCounts(this))
+
+  def executedMeasures = (fragmentsPerGene :: baseCounts :: Nil).flatten
+
+  override def init = {
+    super.init()
+    executedMeasures.foreach(x => x.outputDir = new File(outputDir, "expression_measures" + File.separator + x.name))
+  }
+
   override def makeSample(id: String) = new Sample(id)
 
   class Sample(sampleId: String) extends super.Sample(sampleId) {
     override def addJobs(): Unit = {
       super.addJobs()
 
-      // Do expression counting for miRNA and siRNA
-      val htseqCount = new HtseqCount(qscript)
-      htseqCount.inputAlignment = bamFile.get
-      htseqCount.inputAnnotation = annotationGff
-      htseqCount.format = Option("bam")
-      htseqCount.stranded = Option("yes")
-      htseqCount.featuretype = Option("miRNA")
-      htseqCount.idattr = Option("Name")
-      htseqCount.output = createFile("exprcount.mirna.tsv")
-      if (annotateSam) htseqCount.samout = Option(createFile("htseqannot.mirna.sam"))
-      add(htseqCount)
-
-      val htseqCountGTF = new HtseqCount(qscript)
-      htseqCountGTF.inputAlignment = bamFile.get
-      htseqCountGTF.inputAnnotation = annotationGtf
-      htseqCountGTF.format = Option("bam")
-      htseqCountGTF.stranded = Option("yes")
-      htseqCountGTF.output = createFile("exprcount.tsv")
-      if (annotateSam) htseqCountGTF.samout = Option(createFile("htseqannot.sam"))
-      add(htseqCountGTF)
+      preProcessBam.foreach { file =>
+        executedMeasures.foreach(_.addBamfile(sampleId, file))
+      }
     }
   }
 
   override def summaryFile = new File(outputDir, "tinycap.summary.json")
 
   override def summaryFiles: Map[String, File] = super.summaryFiles ++ Map(
+    "annotation_refflat" -> annotationRefFlat(),
+    "annotationGtf" -> annotationGtf,
     "annotationGff" -> annotationGff
   )
 
@@ -98,6 +105,7 @@ class TinyCap(val root: Configurable) extends QScript with MultisampleMappingTra
 
   override def addMultiSampleJobs = {
     super.addMultiSampleJobs
+    executedMeasures.foreach(add)
   }
 }
 

public/TinyCap/src/main/scala/nl/lumc/sasc/biopet/pipelines/tinycap/measures/FragmentsPerSmallRna.scala

+package nl.lumc.sasc.biopet.pipelines.tinycap.measures
+
+import nl.lumc.sasc.biopet.core.annotations.AnnotationGff
+import nl.lumc.sasc.biopet.extensions.HtseqCount
+import nl.lumc.sasc.biopet.pipelines.gentrap.measures.Measurement
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.queue.QScript
+
+/**
+ * Created by wyleung on 11-2-16.
+ */
+class FragmentsPerSmallRna(val root: Configurable) extends QScript with Measurement with AnnotationGff {
+  def mergeArgs = MergeArgs(List(1), 2, numHeaderLines = 1, fallback = "0")
+
+  /** Pipeline itself */
+  def biopetScript(): Unit = {
+    val jobs = bamFiles.map {
+      case (id, file) =>
+        // Do expression counting for miRNA and siRNA
+        val job = new HtseqCount(this)
+        job.inputAlignment = file
+        job.inputAnnotation = annotationGff
+        job.format = Option("bam")
+        job.stranded = Option("yes")
+        job.featuretype = Option("miRNA")
+        job.idattr = Option("Name")
+        job.output = new File(outputDir, s"$id.$name.mirna.counts.tsv")
+        add(job)
+
+        id -> job
+    }
+
+    addMergeTableJob(jobs.values.map(_.output).toList, mergedTable, "mirna.fragments_per_gene", s".$name.mirna.counts")
+    addHeatmapJob(mergedTable, heatmap, "mirna.fragments_per_gene")
+
+    addSummaryJobs()
+  }
+
+  def mergedTable = new File(outputDir, s"$name.mirna.fragments_per_gene.tsv")
+  def heatmap = new File(outputDir, s"$name.mirna.fragments_per_gene.png")
+}

public/bammetrics/src/test/scala/nl/lumc/sasc/biopet/pipelines/bammetrics/BamMetricsTest.scala

@@ -18,13 +18,10 @@ package nl.lumc.sasc.biopet.pipelines.bammetrics
 import java.io.{ File, FileOutputStream }
 
 import com.google.common.io.Files
-import nl.lumc.sasc.biopet.utils.config.Config
-import nl.lumc.sasc.biopet.extensions.bedtools.{ BedtoolsCoverage, BedtoolsIntersect }
 import nl.lumc.sasc.biopet.extensions.picard._
-import nl.lumc.sasc.biopet.extensions.samtools.SamtoolsFlagstat
-import nl.lumc.sasc.biopet.pipelines.bammetrics.scripts.CoverageStats
 import nl.lumc.sasc.biopet.extensions.tools.BiopetFlagstat
 import nl.lumc.sasc.biopet.utils.ConfigUtils
+import nl.lumc.sasc.biopet.utils.config.Config
 import org.apache.commons.io.FileUtils
 import org.broadinstitute.gatk.queue.QSettings
 import org.scalatest.Matchers

public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/annotations/Annotations.scala

@@ -16,6 +16,14 @@ trait AnnotationGtf extends BiopetQScript { qscript: QScript =>
     file
   }
 }
+trait AnnotationGff extends BiopetQScript { qscript: QScript =>
+  /** GFF reference file in GFF3 format */
+  lazy val annotationGff: File = {
+    val file: File = config("annotation_gff", freeVar = true)
+    inputFiles :+ InputFile(file, config("annotation_gff_md5", freeVar = true))
+    file
+  }
+}
 
 trait AnnotationRefFlat extends BiopetQScript { qscript: QScript =>
   /** GTF reference file */

public/biopet-utils/src/main/scala/nl/lumc/sasc/biopet/utils/LazyCheck.scala

@@ -7,9 +7,9 @@ class LazyCheck[T](function: => T) {
   private var _isSet = false
   def isSet = _isSet
   lazy val value = {
-    val chache = function
+    val cache = function
     _isSet = true
-    chache
+    cache
   }
   def apply() = value
   def get = value

public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/Gentrap.scala

@@ -177,7 +177,7 @@ class Gentrap(val root: Configurable) extends QScript
     if (removeRibosomalReads && ribosomalRefFlat().isEmpty)
       Logging.addError("removeRibosomalReads is enabled but no ribosomalRefFlat is given")
 
-    executedMeasures.foreach(x => x.outputDir = new File(outputDir, "expresion_measures" + File.separator + x.name))
+    executedMeasures.foreach(x => x.outputDir = new File(outputDir, "expression_measures" + File.separator + x.name))
   }
 
   /** Pipeline run for multiple samples */
@@ -208,8 +208,8 @@ class Gentrap(val root: Configurable) extends QScript
       val job = new WipeReads(qscript)
       job.inputBam = bamFile.get
       ribosomalRefFlat().foreach(job.intervalFile = _)
-      job.outputBam = createFile(".cleaned.bam")
-      job.discardedBam = createFile(".rrna.bam")
+      job.outputBam = createFile("cleaned.bam")
+      job.discardedBam = createFile("rrna.bam")
       add(job)
       Some(job.outputBam)
     } else bamFile

public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/BaseCounts.scala

@@ -2,7 +2,6 @@ package nl.lumc.sasc.biopet.pipelines.gentrap.measures
 
 import nl.lumc.sasc.biopet.core.annotations.AnnotationRefFlat
 import nl.lumc.sasc.biopet.extensions.tools.BaseCounter
-import nl.lumc.sasc.biopet.pipelines.gentrap.Gentrap
 import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 

public/gentrap/src/main/scala/nl/lumc/sasc/biopet/pipelines/gentrap/measures/Measurement.scala

@@ -14,7 +14,7 @@ trait Measurement extends SummaryQScript with Reference { qscript: QScript =>
 
   /**
    * Method to add a bamFile to the pipeline
-   * @param id Uniqe id used for this bam file, most likly to be a sampleName
+   * @param id Unique id used for this bam file, most likely to be a sampleName
    * @param file Location of the bam file
    */
   def addBamfile(id: String, file: File): Unit = {