From a61296b2fd0fdd5c64ca8ac1e9868c5c9a4c322a Mon Sep 17 00:00:00 2001
From: Peter van 't Hof <p.j.van_t_hof@lumc.nl>
Date: Thu, 19 Feb 2015 13:06:56 +0100
Subject: [PATCH] Added Markduplicates to summary
---
.../extensions/picard/MarkDuplicates.scala | 19 ++-
.../src/test/resources/picard.dedup.metrics | 112 ++++++++++++++++++
.../picard/MarkDuplicatesTest.scala | 23 ++++
.../biopet/pipelines/mapping/Mapping.scala | 13 +-
4 files changed, 164 insertions(+), 3 deletions(-)
create mode 100644 public/biopet-framework/src/test/resources/picard.dedup.metrics
create mode 100644 public/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicatesTest.scala
diff --git a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicates.scala b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicates.scala
index 181494ae1..fd0f28e73 100644
--- a/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicates.scala
+++ b/public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicates.scala
@@ -17,9 +17,10 @@ package nl.lumc.sasc.biopet.extensions.picard
import java.io.File
import nl.lumc.sasc.biopet.core.config.Configurable
+import nl.lumc.sasc.biopet.core.summary.Summarizable
import org.broadinstitute.gatk.utils.commandline.{ Input, Output, Argument }
-class MarkDuplicates(val root: Configurable) extends Picard {
+class MarkDuplicates(val root: Configurable) extends Picard with Summarizable {
javaMainClass = "picard.sam.MarkDuplicates"
@Input(doc = "The input SAM or BAM files to analyze. Must be coordinate sorted.", required = true)
@@ -91,6 +92,22 @@ class MarkDuplicates(val root: Configurable) extends Picard {
optional("SORTING_COLLECTION_SIZE_RATIO=", sortingCollectionSizeRatio, spaceSeparated = false) +
optional("READ_NAME_REGEX=", readNameRegex, spaceSeparated = false) +
optional("OPTICAL_DUPLICATE_PIXEL_DISTANCE=", opticalDuplicatePixelDistance, spaceSeparated = false)
+
+ def summaryFiles: Map[String, File] = Map()
+
+ def summaryStats: Map[String, Any] = {
+ val (header, content) = Picard.getMetrics(outputMetrics)
+
+ (for (category <- 0 until content.size) yield {
+ content(category)(0) -> (
+ for (
+ i <- 1 until header.size if i < content(category).size
+ ) yield {
+ header(i).toLowerCase -> content(category)(i)
+ }).toMap
+ }
+ ).toMap
+ }
}
object MarkDuplicates {
def apply(root: Configurable, input: List[File], outputDir: String): MarkDuplicates = {
diff --git a/public/biopet-framework/src/test/resources/picard.dedup.metrics b/public/biopet-framework/src/test/resources/picard.dedup.metrics
new file mode 100644
index 000000000..5734917b1
--- /dev/null
+++ b/public/biopet-framework/src/test/resources/picard.dedup.metrics
@@ -0,0 +1,112 @@
+## htsjdk.samtools.metrics.StringHeader
+# picard.sam.MarkDuplicates INPUT=[/data/DIV5/SASC/project-049-SNPtypingbac/analysis/runs/sp/samples/8080_2#43/lib_8080_1/8080_2#43-8080_1.bam] OUTPUT=/data/DIV5/SASC/project-049-SNPtypingbac/analysis/runs/sp/samples/8080_2#43/lib_8080_1/8080_2#43-8080_1.dedup.bam METRICS_FILE=/data/DIV5/SASC/project-049-SNPtypingbac/analysis/runs/sp/samples/8080_2#43/lib_8080_1/8080_2#43-8080_1.dedup.metrics TMP_DIR=[/data/DIV5/SASC/project-049-SNPtypingbac/analysis/runs/sp/.queue/tmp] CREATE_INDEX=true PROGRAM_RECORD_ID=MarkDuplicates PROGRAM_GROUP_NAME=MarkDuplicates REMOVE_DUPLICATES=false ASSUME_SORTED=false MAX_SEQUENCES_FOR_DISK_READ_ENDS_MAP=50000 MAX_FILE_HANDLES_FOR_READ_ENDS_MAP=8000 SORTING_COLLECTION_SIZE_RATIO=0.25 READ_NAME_REGEX=[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).* OPTICAL_DUPLICATE_PIXEL_DISTANCE=100 VERBOSITY=INFO QUIET=false VALIDATION_STRINGENCY=STRICT COMPRESSION_LEVEL=5 MAX_RECORDS_IN_RAM=500000 CREATE_MD5_FILE=false
+## htsjdk.samtools.metrics.StringHeader
+# Started on: Wed Feb 18 17:32:02 CET 2015
+
+## METRICS CLASS picard.sam.DuplicationMetrics
+LIBRARY UNPAIRED_READS_EXAMINED READ_PAIRS_EXAMINED UNMAPPED_READS UNPAIRED_READ_DUPLICATES READ_PAIR_DUPLICATES READ_PAIR_OPTICAL_DUPLICATES PERCENT_DUPLICATION ESTIMATED_LIBRARY_SIZE
+8080_1 5238 603803 115660 1077 5760 26 0.010386 31586584
+
+## HISTOGRAM java.lang.Double
+BIN VALUE
+1.0 1.000043
+2.0 1.98115
+3.0 2.943681
+4.0 3.887988
+5.0 4.814414
+6.0 5.723299
+7.0 6.614976
+8.0 7.489769
+9.0 8.347998
+10.0 9.189977
+11.0 10.016015
+12.0 10.826412
+13.0 11.621464
+14.0 12.401463
+15.0 13.166693
+16.0 13.917434
+17.0 14.653961
+18.0 15.376541
+19.0 16.085441
+20.0 16.780918
+21.0 17.463226
+22.0 18.132615
+23.0 18.78933
+24.0 19.433611
+25.0 20.065693
+26.0 20.685806
+27.0 21.294179
+28.0 21.891032
+29.0 22.476584
+30.0 23.051049
+31.0 23.614637
+32.0 24.167554
+33.0 24.710002
+34.0 25.24218
+35.0 25.76428
+36.0 26.276495
+37.0 26.779012
+38.0 27.272014
+39.0 27.755681
+40.0 28.230191
+41.0 28.695716
+42.0 29.152426
+43.0 29.60049
+44.0 30.040069
+45.0 30.471325
+46.0 30.894416
+47.0 31.309496
+48.0 31.716716
+49.0 32.116227
+50.0 32.508172
+51.0 32.892697
+52.0 33.269941
+53.0 33.640042
+54.0 34.003135
+55.0 34.359354
+56.0 34.708828
+57.0 35.051684
+58.0 35.388049
+59.0 35.718046
+60.0 36.041794
+61.0 36.359412
+62.0 36.671016
+63.0 36.97672
+64.0 37.276636
+65.0 37.570873
+66.0 37.859539
+67.0 38.14274
+68.0 38.420578
+69.0 38.693155
+70.0 38.960572
+71.0 39.222925
+72.0 39.480311
+73.0 39.732823
+74.0 39.980554
+75.0 40.223595
+76.0 40.462034
+77.0 40.695958
+78.0 40.925453
+79.0 41.150602
+80.0 41.371489
+81.0 41.588193
+82.0 41.800794
+83.0 42.00937
+84.0 42.213996
+85.0 42.414748
+86.0 42.611699
+87.0 42.804921
+88.0 42.994484
+89.0 43.180458
+90.0 43.362911
+91.0 43.541909
+92.0 43.717518
+93.0 43.889802
+94.0 44.058824
+95.0 44.224645
+96.0 44.387327
+97.0 44.546929
+98.0 44.703508
+99.0 44.857123
+100.0 45.00783
+
diff --git a/public/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicatesTest.scala b/public/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicatesTest.scala
new file mode 100644
index 000000000..ca34b83d8
--- /dev/null
+++ b/public/biopet-framework/src/test/scala/nl/lumc/sasc/biopet/extensions/picard/MarkDuplicatesTest.scala
@@ -0,0 +1,23 @@
+package nl.lumc.sasc.biopet.extensions.picard
+
+import java.io.File
+import java.nio.file.Paths
+
+import org.scalatest.Matchers
+import org.scalatest.testng.TestNGSuite
+import org.testng.annotations.Test
+
+/**
+ * Created by pjvan_thof on 2/19/15.
+ */
+class MarkDuplicatesTest extends TestNGSuite with Matchers {
+
+ @Test
+ def summaryData: Unit = {
+ val file = new File(Paths.get(getClass.getResource("/picard.dedup.metrics").toURI).toString)
+ val job = new MarkDuplicates(null)
+ job.outputMetrics = file
+
+ job.summaryStats
+ }
+}
\ No newline at end of file
diff --git a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
index 307b160a6..3ee791dc2 100644
--- a/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
+++ b/public/mapping/src/main/scala/nl/lumc/sasc/biopet/pipelines/mapping/Mapping.scala
@@ -96,7 +96,14 @@ class Mapping(val root: Configurable) extends QScript with SummaryQScript with S
def summaryFiles = Map()
- def summarySettings = Map()
+ def summarySettings = Map(
+ "skip_metrics" -> skipMetrics,
+ "skip_flexiprep" -> skipFlexiprep,
+ "skip_markduplicates" -> skipMarkduplicates,
+ "aligner" -> aligner,
+ "chunking" -> chunking,
+ "numberChunks" -> numberChunks.getOrElse(1)
+ )
def init() {
require(outputDir != null, "Missing output directory on mapping module")
@@ -208,7 +215,9 @@ class Mapping(val root: Configurable) extends QScript with SummaryQScript with S
var bamFile = bamFiles.head
if (!skipMarkduplicates) {
bamFile = new File(outputDir, outputName + ".dedup.bam")
- add(MarkDuplicates(this, bamFiles, bamFile))
+ val md = MarkDuplicates(this, bamFiles, bamFile)
+ add(md)
+ addSummarizable(md, "mark_duplicates")
} else if (skipMarkduplicates && chunking) {
val mergeSamFile = MergeSamFiles(this, bamFiles, outputDir)
add(mergeSamFile)
--
GitLab