diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala
index 4a41248e5653ee9dd6a1e32e64845447b4198b06..344f88b89e902bad748628d8e591b79c2daec5d1 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/BiopetCommandLineFunction.scala
@@ -73,6 +73,15 @@ trait BiopetCommandLineFunction extends CommandLineResources { biopetFunction =>
def beforeGraph() {}
override def freezeFieldValues() {
+
+ this match {
+ case r: Reference =>
+ if (r.dictRequired) deps :+= r.referenceDict
+ if (r.faiRequired) deps :+= r.referenceFai
+ deps = deps.distinct
+ case _ =>
+ }
+
preProcessExecutable()
beforeGraph()
internalBeforeGraph()
diff --git a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala
index 6a39ca3eb9c68205cf1b5354829b4bb87944bfa9..f00de9e17af5564d23a73bac0ad6645d1535ab24 100644
--- a/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala
+++ b/public/biopet-core/src/main/scala/nl/lumc/sasc/biopet/core/Reference.scala
@@ -61,25 +61,25 @@ trait Reference extends Configurable {
}
/** When set override this on true the pipeline with raise an exception when fai index is not found */
- protected def faiRequired = false
+ def faiRequired = false
/** When set override this on true the pipeline with raise an exception when dict index is not found */
- protected def dictRequired = this.isInstanceOf[Summarizable] || this.isInstanceOf[SummaryQScript]
+ def dictRequired = this.isInstanceOf[Summarizable] || this.isInstanceOf[SummaryQScript]
+
+ /** Returns the dict file belonging to the fasta file */
+ def referenceDict = new File(referenceFasta().getAbsolutePath
+ .stripSuffix(".fa")
+ .stripSuffix(".fasta")
+ .stripSuffix(".fna") + ".dict")
+
+ /** Returns the fai file belonging to the fasta file */
+ def referenceFai = new File(referenceFasta().getAbsolutePath + ".fai")
/** Returns the fasta file */
def referenceFasta(): File = {
val file: File = config("reference_fasta")
- if (config.contains("reference_fasta")) {
- checkFasta(file)
-
- val dict = new File(file.getAbsolutePath.stripSuffix(".fa").stripSuffix(".fasta").stripSuffix(".fna") + ".dict")
- val fai = new File(file.getAbsolutePath + ".fai")
-
- this match {
- case c: BiopetCommandLineFunction => c.deps :::= dict :: fai :: Nil
- case _ =>
- }
- } else {
+ if (config.contains("reference_fasta")) checkFasta(file)
+ else {
val defaults = ConfigUtils.mergeMaps(this.defaults, this.internalDefaults)
def getReferences(map: Map[String, Any]): Set[(String, String)] = (for (
diff --git a/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SortVcf.scala b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SortVcf.scala
new file mode 100644
index 0000000000000000000000000000000000000000..eb36ba9faad4980d28df0308162237b655e7ad4c
--- /dev/null
+++ b/public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/SortVcf.scala
@@ -0,0 +1,61 @@
+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.extensions.picard
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.Reference
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.{ Input, Output }
+
+/** Extension for picard SortVcf */
+class SortVcf(val root: Configurable) extends Picard with Reference {
+ javaMainClass = new picard.vcf.SortVcf().getClass.getName
+
+ @Input(doc = "Input VCF(s) to be sorted. Multiple inputs must have the same sample names (in order)", required = true)
+ var input: File = _
+
+ @Output(doc = "Output VCF to be written.", required = true)
+ var output: File = _
+
+ @Input(doc = "Sequence dictionary to use", required = true)
+ var sequenceDictionary: File = _
+
+ override val dictRequired = true
+
+ override def beforeGraph(): Unit = {
+ super.beforeGraph()
+ if (sequenceDictionary == null) sequenceDictionary = referenceDict
+ }
+
+ /** Returns command to execute */
+ override def cmdLine = super.cmdLine +
+ (if (inputAsStdin) required("INPUT=", new File("/dev/stdin"), spaceSeparated = false)
+ else required("INPUT=", input, spaceSeparated = false)) +
+ (if (outputAsStsout) required("OUTPUT=", new File("/dev/stdout"), spaceSeparated = false)
+ else required("OUTPUT=", output, spaceSeparated = false)) +
+ required("SEQUENCE_DICTIONARY=", sequenceDictionary, spaceSeparated = false)
+}
+
+object SortVcf {
+ /** Returns default SortSam */
+ def apply(root: Configurable, input: File, output: File): SortVcf = {
+ val sortVcf = new SortVcf(root)
+ sortVcf.input = input
+ sortVcf.output = output
+ sortVcf
+ }
+}
\ No newline at end of file
diff --git a/public/tinycap/src/test/resources/log4j.properties b/public/tinycap/src/test/resources/log4j.properties
new file mode 100644
index 0000000000000000000000000000000000000000..501af67582a546db584c8538b28cb6f9e07f1692
--- /dev/null
+++ b/public/tinycap/src/test/resources/log4j.properties
@@ -0,0 +1,25 @@
+#
+# Biopet is built on top of GATK Queue for building bioinformatic
+# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+# should also be able to execute Biopet tools and pipelines.
+#
+# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+#
+# Contact us at: sasc@lumc.nl
+#
+# A dual licensing mode is applied. The source code within this project that are
+# not part of GATK Queue is freely available for non-commercial use under an AGPL
+# license; For commercial users or users who do not want to follow the AGPL
+# license, please contact us to obtain a separate license.
+#
+
+# Set root logger level to DEBUG and its only appender to A1.
+log4j.rootLogger=ERROR, A1
+
+# A1 is set to be a ConsoleAppender.
+log4j.appender.A1=org.apache.log4j.ConsoleAppender
+
+# A1 uses PatternLayout.
+log4j.appender.A1.layout=org.apache.log4j.PatternLayout
+log4j.appender.A1.layout.ConversionPattern=%-5p [%d] [%C{1}] - %m%n
\ No newline at end of file