Merge pull request #15 from biowdl/BIOWDL-25

Biowdl 25

biopet.wdl

 # PLEASE ADD TASKS IN ALPHABETIC ORDER.
 # This makes searching a lot easier.
+
 task BaseCounter {
     String? preCommand
-    String tool_jar #Should this be of type File?
+    File toolJar
     File bam
+    File bamIndex
     File refFlat
     String outputDir
     String prefix
@@ -14,9 +16,9 @@ task BaseCounter {
     Int mem = ceil(select_first([memory, 12.0]))
     command {
         set -e -o pipefail
-        ${preCommand}
         mkdir -p ${outputDir}
-        java -Xmx${mem}G -jar ${tool_jar} \
+        ${preCommand}
+        java -Xmx${mem}G -jar ${toolJar} \
         -b ${bam} \
         -r ${refFlat} \
         -o ${outputDir} \
@@ -61,7 +63,7 @@ task BaseCounter {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -121,6 +123,7 @@ task SampleConfig {
     String? preCommand
     String tool_jar
     Array[File]+ inputFiles
+    String keyFilePath
     String? sample
     String? library
     String? readgroup
@@ -141,11 +144,12 @@ task SampleConfig {
         ${"--library " + library} \
         ${"--readgroup " + readgroup} \
         ${"--jsonOutput " + jsonOutputPath} \
-        ${"--tsvOutput " + tsvOutputPath}
+        ${"--tsvOutput " + tsvOutputPath} \
+        > ${keyFilePath}
     }
 
     output {
-        File keysFile = stdout()
+        File keysFile = keyFilePath
         File? jsonOutput = jsonOutputPath
         File? tsvOutput = tsvOutputPath
     }
@@ -184,7 +188,7 @@ task ScatterRegions {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 2.0]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 

gatk.wdl

@@ -34,7 +34,7 @@ task BaseRecalibrator {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -78,7 +78,7 @@ task ApplyBQSR {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -107,7 +107,7 @@ task GatherBqsrReports {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -149,7 +149,7 @@ task HaplotypeCallerGvcf {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -198,7 +198,7 @@ task GenotypeGVCFs {
     }
 
     runtime{
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -245,7 +245,7 @@ task CombineGVCFs {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -282,6 +282,6 @@ task SplitNCigarReads {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }

htseq.wdl

@@ -11,6 +11,7 @@ task HTSeqCount {
 
     command {
         set -e -o pipefail
+        mkdir -p ${sub(outputTable, basename(outputTable), "")}
         ${preCommand}
         htseq-count \
         -f ${default="bam" format} \

mergecounts.wdl

@@ -3,29 +3,38 @@ task MergeCounts {
 
     Array[File] inputFiles
     String outputFile
-    String idVar
-    String measurementVar
+    Int featureColumn
+    Int valueColumn
+    Boolean inputHasHeader
 
     # Based on a script by Szymon Kielbasa/Ioannis Moustakas
     command <<<
         set -e -o pipefail
+        mkdir -p ${sub(outputFile, basename(outputFile) + "$", "")}
         ${preCommand}
-        R --no-save --slave <<CODE > ${outputFile}
+        R --no-save <<CODE
             library(dplyr)
             library(reshape2)
 
             listOfFiles <- c("${sep='", "' inputFiles}")
 
+            valueI <- ${valueColumn}
+            featureI <- ${featureColumn}
+            header <- ${true="TRUE" false="FALSE" inputHasHeader}
+
             d <- do.call(rbind, lapply(listOfFiles, function(file){
-                d <- read.table(file, header=TRUE, comment.char="#")
-                colI <- grep(${measurementVar}, colnames(d))
-                colnames(d)[colI] <- strsplit(file, "/")[[1]][3]
-                d <- d %>% melt(id.vars=${idVar}, measure.vars=colI,
-                    variable.name="sample", value.name="count")
+                d <- read.table(file, sep="\t", header=header, comment.char="#")
+
+                splitPath <- strsplit(file, "/")[[1]]
+                colnames(d)[valueI] <- sub("\\\.[^\\\.]*$", "",
+                    splitPath[length(splitPath)])
+                colnames(d)[featureI] <- "feature"
+
+                d <- d %>% melt(id.vars=featureI, variable.name="sample", value.name="count")
             }))
 
-            d <- d %>% dcast(paste0(${idVar}, " ~ sample"), value.var="count")
-            write.table(d, sep="\t", quote=FALSE, row.names=FALSE)
+            d <- d %>% dcast(feature ~ sample, value.var="count")
+            write.table(d, file="${outputFile}", sep="\t", quote=FALSE, row.names=FALSE)
         CODE
     >>>
 

picard.wdl

@@ -28,7 +28,7 @@ task ScatterIntervalList {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -63,7 +63,7 @@ task GatherBamFiles {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -113,7 +113,7 @@ task MarkDuplicates {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -148,7 +148,7 @@ task MergeVCFs {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
 
@@ -183,6 +183,6 @@ task SamToFastq {
     }
 
     runtime {
-        memory: ceil(mem * select_first([memoryMultiplier, 1.5]))
+        memory: ceil(mem * select_first([memoryMultiplier, 3.0]))
     }
 }
\ No newline at end of file

samtools.wdl

 task Index {
     String? preCommand
-    String bamFilePath
+    File bamFilePath
+    String? bamIndexPath
 
     command {
         set -e -o pipefail
         ${preCommand}
-        samtools index ${bamFilePath}
+        samtools index ${bamFilePath} ${bamIndexPath}
     }
 
     output {
-        File indexFile = bamFilePath + ".bai"
+        File indexFile = if defined(bamIndexPath) then select_first([bamIndexPath]) else bamFilePath + ".bai"
     }
 }
 
@@ -21,12 +22,7 @@ task Merge {
     command {
         set -e -o pipefail
         ${preCommand}
-        if [ ${length(bamFiles)} -gt 1 ]
-          then
-            samtools merge ${outputBamPath} ${sep=' ' bamFiles}
-          else
-            ln -sf ${bamFiles} ${outputBamPath}
-        fi
+        samtools merge ${outputBamPath} ${sep=' ' bamFiles}
     }
 
     output {

star.wdl

@@ -47,4 +47,19 @@ task Star {
         cpu: select_first([runThreadN, 1])
         memory: select_first([memory, 10])
     }
-}
\ No newline at end of file
+}
+
+task makeStarRGline {
+    String sample
+    String library
+    String? platform
+    String readgroup
+
+    command {
+        printf '"ID:${readgroup}" "LB:${library}" "PL:${default="ILLUMINA" platform}" "SM:${sample}"'
+    }
+
+    output {
+        String rgLine = read_string(stdout())
+    }
+}

stringtie.wdl

@@ -10,6 +10,7 @@ task Stringtie {
 
     command {
         set -e -o pipefail
+        mkdir -p $(dirname ${assembledTranscriptsFile})
         ${preCommand}
         stringtie \
         ${"-p " + threads} \