diff --git a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/VariantEffectPredictor.scala b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/VariantEffectPredictor.scala
index 50c15dbabc3b51be862c5a3987704ff10a57106d..20b4ae8422936bfc5a8b3b8310074b01b46445a6 100644
--- a/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/VariantEffectPredictor.scala
+++ b/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/VariantEffectPredictor.scala
@@ -156,9 +156,9 @@ class VariantEffectPredictor(val root: Configurable) extends BiopetCommandLineFu
override def beforeGraph(): Unit = {
super.beforeGraph()
if (!cache && !database) {
- Logging.addError("Must supply either cache or database for VariantEffectPredictor")
+ Logging.addError("Must either set 'cache' or 'database' to true for VariantEffectPredictor")
} else if (cache && dir.isEmpty) {
- Logging.addError("Must supply dir to cache for VariantEffectPredictor")
+ Logging.addError("Must supply 'dir_cache' to cache for VariantEffectPredictor")
}
if (statsText) _summary = new File(output.getAbsolutePath + "_summary.txt")
}
diff --git a/docs/pipelines/toucan.md b/docs/pipelines/toucan.md
index 12f4ea108c54402f51d37e6f673d97e633058d6f..5f362bf13fa083d571f57e03f95351fc1231a16b 100644
--- a/docs/pipelines/toucan.md
+++ b/docs/pipelines/toucan.md
@@ -83,6 +83,25 @@ The following config values are optional:
Annotation queries can be set by the `annotation_queries` config value in the `manwe` config namespace.
By default, a global query is returned.
+
+###Groups
+In case you want to add your samples to a specific group in your varda database, you can use the tagging system in your sample config.
+Specifically, the `varda_group` tag should be a list of strings pointing to group.
+
+E.g. :
+
+```json
+{
+ "samples": {
+ "sample1": {
+ "tags": {
+ "varda_group": ["group1", "group2"]
+ }
+ }
+ }
+}
+```
+
Running the pipeline
---------------
The command to run the pipeline is:
diff --git a/toucan/pom.xml b/toucan/pom.xml
index 781e458c31cc8128843b55873781e3aaa9f8b1e0..62a9699f8f63680d1c8b6bce67a7390907ca8b34 100644
--- a/toucan/pom.xml
+++ b/toucan/pom.xml
@@ -43,5 +43,17 @@
<artifactId>BiopetToolsExtensions</artifactId>
<version>${project.version}</version>
</dependency>
+ <dependency>
+ <groupId>org.testng</groupId>
+ <artifactId>testng</artifactId>
+ <version>6.8</version>
+ <scope>test</scope>
+ </dependency>
+ <dependency>
+ <groupId>org.scalatest</groupId>
+ <artifactId>scalatest_2.10</artifactId>
+ <version>2.2.1</version>
+ <scope>test</scope>
+ </dependency>
</dependencies>
</project>
diff --git a/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala b/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala
index 2e3ffe26a1735dbea0f664bf8c4c957bd7262f7b..58dcaf82447daef751eae0d21ac7c43387026149 100644
--- a/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala
+++ b/toucan/src/main/scala/nl/lumc/sasc/biopet/pipelines/toucan/Toucan.scala
@@ -40,15 +40,17 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
@Input(doc = "Input GVCF file", shortName = "gvcf", required = false)
var inputGvcf: Option[File] = None
- var sampleIds: List[String] = Nil
+ var outputVcf: Option[File] = None
+
+ def sampleInfo: Map[String, Map[String, Any]] = root match {
+ case m: MultiSampleQScript => m.samples.map { case (sampleId, sample) => sampleId -> sample.sampleTags }
+ case null => VcfUtils.getSampleIds(inputVCF).map(x => x -> Map[String, Any]()).toMap
+ case s: SampleLibraryTag => s.sampleId.map(x => x -> Map[String, Any]()).toMap
+ case _ => throw new IllegalArgumentException("")
+ }
+
def init(): Unit = {
inputFiles :+= new InputFile(inputVCF)
- sampleIds = root match {
- case m: MultiSampleQScript => m.samples.keys.toList
- case null => VcfUtils.getSampleIds(inputVCF)
- case s: SampleLibraryTag => s.sampleId.toList
- case _ => throw new IllegalArgumentException("You don't have any samples")
- }
}
override def defaults = Map(
@@ -79,29 +81,29 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
val gonlVcfFile: Option[File] = config("gonl_vcf")
val exacVcfFile: Option[File] = config("exac_vcf")
- var outputFile = normalizer.outputVcf
+ outputVcf = Some(normalizer.outputVcf)
gonlVcfFile match {
case Some(gonlFile) =>
val vcfWithVcf = new VcfWithVcf(this)
- vcfWithVcf.input = outputFile
+ vcfWithVcf.input = outputVcf.getOrElse(new File(""))
vcfWithVcf.secondaryVcf = gonlFile
vcfWithVcf.output = swapExt(outputDir, normalizer.outputVcf, ".vcf.gz", ".gonl.vcf.gz")
vcfWithVcf.fields ::= ("AF", "AF_gonl", None)
add(vcfWithVcf)
- outputFile = vcfWithVcf.output
+ outputVcf = Some(vcfWithVcf.output)
case _ =>
}
exacVcfFile match {
case Some(exacFile) =>
val vcfWithVcf = new VcfWithVcf(this)
- vcfWithVcf.input = outputFile
+ vcfWithVcf.input = outputVcf.getOrElse(new File(""))
vcfWithVcf.secondaryVcf = exacFile
- vcfWithVcf.output = swapExt(outputDir, outputFile, ".vcf.gz", ".exac.vcf.gz")
+ vcfWithVcf.output = swapExt(outputDir, outputVcf.getOrElse(new File("")), ".vcf.gz", ".exac.vcf.gz")
vcfWithVcf.fields ::= ("AF", "AF_exac", None)
add(vcfWithVcf)
- outputFile = vcfWithVcf.output
+ outputVcf = Some(vcfWithVcf.output)
case _ =>
}
@@ -116,7 +118,7 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
* @param annotation: ManweDownloadAnnotateVcf object of annotated vcf
* @return
*/
- def importAndActivateSample(sampleID: String, inputVcf: File,
+ def importAndActivateSample(sampleID: String, sampleGroups: List[String], inputVcf: File,
gVCF: File, annotation: ManweAnnotateVcf): ManweActivateAfterAnnotImport = {
val minGQ: Int = config("minimum_genome_quality", default = 20, namespace = "manwe")
@@ -165,6 +167,7 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
imported.beds = List(bgzippedBed.output)
imported.name = Some(sampleID)
imported.public = isPublic
+ imported.group = sampleGroups
imported.waitToComplete = false
imported.isIntermediate = true
imported.output = swapExt(outputDir, intersected.output, ".vcf.gz", ".manwe.import")
@@ -186,7 +189,6 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
def varda(vcf: File, gVcf: File): File = {
val annotationQueries: List[String] = config("annotation_queries", default = List("GLOBAL *"), namespace = "manwe")
- //TODO: add groups!!! Need sample-specific group tags for this
val annotate = new ManweAnnotateVcf(this)
annotate.vcf = vcf
@@ -202,7 +204,14 @@ class Toucan(val root: Configurable) extends QScript with BiopetQScript with Sum
annotatedVcf.output = swapExt(outputDir, annotate.output, ".manwe.annot", "manwe.annot.vcf.gz")
add(annotatedVcf)
- val activates = sampleIds map { x => importAndActivateSample(x, vcf, gVcf, annotate) }
+ val activates = sampleInfo map { x =>
+ val sampleGroup = x._2.getOrElse("varda_group", Nil) match {
+ case x: List[String] => x
+ case Nil => Nil
+ case _ => throw new IllegalArgumentException("Sample tag 'varda_group' is not a list of strings")
+ }
+ importAndActivateSample(x._1, sampleGroup, vcf, gVcf, annotate)
+ }
val finalLn = new Ln(this)
activates.foreach(x => finalLn.deps :+= x.output)