From 052f9e1125b9972e1209c934eb3afc3ce5acc96c Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Tue, 17 May 2016 11:11:06 +0200
Subject: [PATCH] Added mapping to gears testing
---
.../pipelines/mapping/MappingTest.scala | 33 ++++++++++++-----
.../mapping/MultisampleMappingTest.scala | 35 +++++++++++++------
.../shiva/ShivaVariantcallingTest.scala | 14 ++++----
3 files changed, 57 insertions(+), 25 deletions(-)
diff --git a/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MappingTest.scala b/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MappingTest.scala
index 7b8f289df..cc2ba1b9e 100644
--- a/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MappingTest.scala
+++ b/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MappingTest.scala
@@ -18,6 +18,7 @@ package nl.lumc.sasc.biopet.pipelines.mapping
import java.io.{ File, FileOutputStream }
import com.google.common.io.Files
+import nl.lumc.sasc.biopet.extensions.kraken.Kraken
import nl.lumc.sasc.biopet.pipelines.flexiprep.Fastqc
import nl.lumc.sasc.biopet.utils.ConfigUtils
import nl.lumc.sasc.biopet.utils.config.Config
@@ -25,7 +26,7 @@ import org.apache.commons.io.FileUtils
import org.broadinstitute.gatk.queue.QSettings
import org.scalatest.Matchers
import org.scalatest.testng.TestNGSuite
-import org.testng.annotations.{ BeforeClass, AfterClass, DataProvider, Test }
+import org.testng.annotations.{ AfterClass, BeforeClass, DataProvider, Test }
/**
* Test class for [[Mapping]]
@@ -42,14 +43,15 @@ abstract class AbstractTestMapping(val aligner: String) extends TestNGSuite with
}
}
+ def paired = Array(true, false)
+ def chunks = Array(1, 5)
+ def skipMarkDuplicates = Array(true, false)
+ def skipFlexipreps = Array(true, false)
+ def zipped = Array(true, false)
+ def unmappedToGears = false
+
@DataProvider(name = "mappingOptions")
def mappingOptions = {
- val paired = Array(true, false)
- val chunks = Array(1, 5)
- val skipMarkDuplicates = Array(true, false)
- val skipFlexipreps = Array(true, false)
- val zipped = Array(true, false)
-
for (
pair <- paired;
chunk <- chunks;
@@ -68,7 +70,8 @@ abstract class AbstractTestMapping(val aligner: String) extends TestNGSuite with
"aligner" -> aligner,
"number_chunks" -> chunks,
"skip_markduplicates" -> skipMarkDuplicate,
- "skip_flexiprep" -> skipFlexiprep
+ "skip_flexiprep" -> skipFlexiprep,
+ "unmapped_to_gears" -> unmappedToGears
), Map(executables.toSeq: _*))
val mapping: Mapping = initPipeline(map)
@@ -85,6 +88,8 @@ abstract class AbstractTestMapping(val aligner: String) extends TestNGSuite with
//Flexiprep
mapping.functions.count(_.isInstanceOf[Fastqc]) shouldBe (if (skipFlexiprep) 0 else if (paired) 4 else 2)
+
+ mapping.functions.count(_.isInstanceOf[Kraken]) shouldBe (if (unmappedToGears) 1 else 0)
}
val outputDir = Files.createTempDir()
@@ -133,6 +138,8 @@ abstract class AbstractTestMapping(val aligner: String) extends TestNGSuite with
"bowtie2" -> Map("exe" -> "test"),
"stampy" -> Map("exe" -> "test", "genome" -> "test", "hash" -> "test"),
"samtools" -> Map("exe" -> "test"),
+ "kraken" -> Map("exe" -> "test", "db" -> "test"),
+ "krakenreport" -> Map("exe" -> "test", "db" -> "test"),
"md5sum" -> Map("exe" -> "test")
)
@@ -151,3 +158,13 @@ class MappingBowtie2Test extends AbstractTestMapping("bowtie2")
class MappingStampyTest extends AbstractTestMapping("stampy")
class MappingGsnapTest extends AbstractTestMapping("gsnap")
class MappingTophatTest extends AbstractTestMapping("tophat")
+
+class MappingGearsTest extends AbstractTestMapping("bwa-mem") {
+ override def unmappedToGears = true
+
+ override def paired = Array(true)
+ override def chunks = Array(1)
+ override def skipMarkDuplicates = Array(true)
+ override def skipFlexipreps = Array(true)
+ override def zipped = Array(true)
+}
diff --git a/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTest.scala b/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTest.scala
index abb3bf59e..beac59c9c 100644
--- a/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTest.scala
+++ b/mapping/src/test/scala/nl/lumc/sasc/biopet/pipelines/mapping/MultisampleMappingTest.scala
@@ -1,8 +1,9 @@
package nl.lumc.sasc.biopet.pipelines.mapping
-import java.io.{File, FileOutputStream}
+import java.io.{ File, FileOutputStream }
import com.google.common.io.Files
+import nl.lumc.sasc.biopet.extensions.kraken.Kraken
import nl.lumc.sasc.biopet.extensions.picard.{ MarkDuplicates, MergeSamFiles }
import nl.lumc.sasc.biopet.utils.ConfigUtils
import nl.lumc.sasc.biopet.utils.config.Config
@@ -12,8 +13,8 @@ import org.scalatest.testng.TestNGSuite
import org.testng.annotations.{ DataProvider, Test }
/**
- * Created by pjvanthof on 15/05/16.
- */
+ * Created by pjvanthof on 15/05/16.
+ */
trait MultisampleMappingTestTrait extends TestNGSuite with Matchers {
def initPipeline(map: Map[String, Any]): MultisampleMapping = {
new MultisampleMapping() {
@@ -36,7 +37,7 @@ trait MultisampleMappingTestTrait extends TestNGSuite with Matchers {
@DataProvider(name = "mappingOptions")
def mappingOptions = {
for (
- merge <- mergeStrategies.toArray; s1 <- sample1 ; s2 <- sample2
+ merge <- mergeStrategies.toArray; s1 <- sample1; s2 <- sample2
) yield Array(merge, s1, s2)
}
@@ -76,13 +77,18 @@ trait MultisampleMappingTestTrait extends TestNGSuite with Matchers {
(if (sample2 && (merge == MergeStrategy.MarkDuplicates || merge == MergeStrategy.PreProcessMarkDuplicates)) 1 else 0))
pipeline.functions.count(_.isInstanceOf[MergeSamFiles]) shouldBe (
(if (sample2 && (merge == MergeStrategy.MergeSam || merge == MergeStrategy.PreProcessMergeSam)) 1 else 0))
- pipeline.samples.foreach { case (sampleName, sample) =>
- if (merge == MergeStrategy.None) sample.bamFile shouldBe None
- sample.summaryStats shouldBe Map()
- sample.libraries.foreach { case (libraryId, library) =>
- library.summaryStats shouldBe Map()
- }
+ pipeline.samples.foreach {
+ case (sampleName, sample) =>
+ if (merge == MergeStrategy.None) sample.bamFile shouldBe None
+ sample.summaryStats shouldBe Map()
+ sample.libraries.foreach {
+ case (libraryId, library) =>
+ library.summaryStats shouldBe Map()
+ }
}
+
+ pipeline.functions.count(_.isInstanceOf[Kraken]) shouldBe (if (unmappedToGears) (numberFastqLibs + numberSamples) else 0)
+
pipeline.summarySettings.get("merge_strategy") shouldBe Some(merge.toString)
}
}
@@ -98,6 +104,13 @@ class MultisampleMappingNoSamplesTest extends MultisampleMappingTestTrait {
override def mergeStrategies = MultisampleMapping.MergeStrategy.values.filter(_ == MultisampleMapping.MergeStrategy.PreProcessMarkDuplicates)
}
+class MultisampleMappingGearsTest extends MultisampleMappingTestTrait {
+ override def sample1 = Array(true)
+ override def sample2 = Array(false)
+ override def unmappedToGears = true
+ override def mergeStrategies = MultisampleMapping.MergeStrategy.values.filter(_ == MultisampleMapping.MergeStrategy.PreProcessMarkDuplicates)
+}
+
class MultisampleMappingBamTest extends MultisampleMappingTestTrait {
override def sample1 = Array(false)
override def sample2 = Array(false)
@@ -168,6 +181,8 @@ object MultisampleMappingTestTrait {
"samtools" -> Map("exe" -> "test"),
"igvtools" -> Map("exe" -> "test"),
"wigtobigwig" -> Map("exe" -> "test"),
+ "kraken" -> Map("exe" -> "test", "db" -> "test"),
+ "krakenreport" -> Map("exe" -> "test", "db" -> "test"),
"md5sum" -> Map("exe" -> "test")
)
diff --git a/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala b/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
index 46f3061c4..2904d79a6 100644
--- a/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
+++ b/shiva/src/test/scala/nl/lumc/sasc/biopet/pipelines/shiva/ShivaVariantcallingTest.scala
@@ -5,21 +5,21 @@
*/
package nl.lumc.sasc.biopet.pipelines.shiva
-import java.io.{File, FileOutputStream}
+import java.io.{ File, FileOutputStream }
import com.google.common.io.Files
import nl.lumc.sasc.biopet.core.BiopetPipe
import nl.lumc.sasc.biopet.extensions.Freebayes
-import nl.lumc.sasc.biopet.extensions.bcftools.{BcftoolsCall, BcftoolsMerge}
-import nl.lumc.sasc.biopet.extensions.gatk.{CombineVariants, GenotypeConcordance, HaplotypeCaller, UnifiedGenotyper}
+import nl.lumc.sasc.biopet.extensions.bcftools.{ BcftoolsCall, BcftoolsMerge }
+import nl.lumc.sasc.biopet.extensions.gatk.{ CombineVariants, GenotypeConcordance, HaplotypeCaller, UnifiedGenotyper }
import nl.lumc.sasc.biopet.utils.config.Config
-import nl.lumc.sasc.biopet.extensions.tools.{MpileupToVcf, VcfFilter, VcfStats}
-import nl.lumc.sasc.biopet.extensions.vt.{VtDecompose, VtNormalize}
+import nl.lumc.sasc.biopet.extensions.tools.{ MpileupToVcf, VcfFilter, VcfStats }
+import nl.lumc.sasc.biopet.extensions.vt.{ VtDecompose, VtNormalize }
import nl.lumc.sasc.biopet.utils.ConfigUtils
import org.broadinstitute.gatk.queue.QSettings
import org.scalatest.Matchers
import org.scalatest.testng.TestNGSuite
-import org.testng.annotations.{DataProvider, Test}
+import org.testng.annotations.{ DataProvider, Test }
import scala.collection.mutable.ListBuffer
@@ -117,7 +117,7 @@ trait ShivaVariantcallingTestTrait extends TestNGSuite with Matchers {
(if (haplotypeCallerAllele) 1 else 0) + (if (haplotypeCallerGvcf) bams else 0)
pipeline.functions.count(_.isInstanceOf[UnifiedGenotyper]) shouldBe (if (unifiedGenotyper) 1 else 0) +
(if (unifiedGenotyperAllele) 1 else 0)
- pipeline.functions.count(_.isInstanceOf[VcfStats]) shouldBe (1 + callers.size + (roiBedFiles ++ ampliconBedFile).length * (1+ callers.size))
+ pipeline.functions.count(_.isInstanceOf[VcfStats]) shouldBe (1 + callers.size + (roiBedFiles ++ ampliconBedFile).length * (1 + callers.size))
pipeline.functions.count(_.isInstanceOf[VtNormalize]) shouldBe (if (normalize) callers.size else 0)
pipeline.functions.count(_.isInstanceOf[VtDecompose]) shouldBe (if (decompose) callers.size else 0)
pipeline.functions.count(_.isInstanceOf[GenotypeConcordance]) shouldBe (if (referenceVcf.isDefined) 1 + callers.size else 0)
--
GitLab