Merge branch '8-makeBigWig' of git.biohpc.swmed.edu:GUDMAP_RBK/RNA-seq into 35-RSeQC

.gitlab-ci.yml

@@ -64,8 +64,16 @@ alignData:
 dedupData:
   stage: unit
   script:
-  - singularity exec 'docker://bicf/picard2.21.7:2.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates I=./test_data/bam/small/Q-Y5JA_1M.se.sorted.bam O=Q-Y5JA_1M.se.deduped.bam M=Q-Y5JA_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
+  - singularity run 'docker://bicf/gudmaprbkdedup:2.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates I=./test_data/bam/small/Q-Y5JA_1M.se.sorted.bam O=Q-Y5JA_1M.se.deduped.bam M=Q-Y5JA_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
+  - singularity run 'docker://bicf/gudmaprbkdedup:2.0.0' samtools sort -@ `nproc` -O BAM -o Q-Y5JA_1M.se.sorted.deduped.bam ./test_data/bam/small/Q-Y5JA_1M.se.deduped.bam
+  - singularity run 'docker://bicf/gudmaprbkdedup:2.0.0' samtools index -@ `nproc` -b ./test_data/bam/small/Q-Y5JA_1M.se.sorted.deduped.bam Q-Y5JA_1M.se.sorted.deduped.bai
   - pytest -m dedupData
+  
+makeBigWig:
+  stage: unit
+  script:
+  - singularity run 'docker://bicf/deeptools3.3:2.0.0' bamCoverage -p `nproc` -b ./test_data/bam/small/Q-Y5JA_1M.se.sorted.deduped.bam -o Q-Y5JA_1M.se.bw
+  - pytest -m makeBigWig
 
 fastqc:
   stage: unit

workflow/conf/biohpc.config

@@ -16,13 +16,13 @@ process {
     executor = 'local'
   }
   withName:trimData {
-    queue = 'super'
+    queue = '128GB,256GB,256GBv1'
   }
   withName:alignData {
     queue = '256GB,256GBv1'
   }
   withName: dedupData {
-    queue = 'super'
+    queue = '128GB,256GB,256GBv1'
   }
   withName: fastqc {
     queue = 'super'

workflow/nextflow.config

@@ -30,11 +30,14 @@ process {
     container = 'bicf/gudmaprbkaligner:2.0.0'
   }
   withName: dedupData {
-    container = 'bicf/picard2.21.7:2.0.0'
+    container = 'bicf/gudmaprbkdedup:2.0.0'
   }
   withName: fastqc {
     container = 'bicf/fastqc:2.0.0'
   }
+  withName: makeBigWig {
+    container = 'bicf/deeptools3.3:2.0.0'
+  }
 }
 
 trace {
@@ -64,4 +67,4 @@ manifest {
   mainScript = 'rna-seq.nf'
   version = 'v0.0.1_indev'
   nextflowVersion = '>=19.09.0'
-}
\ No newline at end of file
+}

workflow/rna-seq.nf

@@ -340,7 +340,7 @@ process dedupData {
     path rawBam
 
   output:
-    path ("${repRID}.deduped.bam") into dedupBam
+    tuple val ("${repRID}"), path ("${repRID}.sorted.deduped.bam"), path ("${repRID}.sorted.deduped.bai") into dedupBam
     path ("${repRID}.dedup.out")
     path ("${repRID}.dedup.err")
 
@@ -351,6 +351,8 @@ process dedupData {
 
     # remove duplicated reads
     java -jar /picard/build/libs/picard.jar MarkDuplicates I=${rawBam} O=${repRID}.deduped.bam M=${repRID}.deduped.Metrics.txt REMOVE_DUPLICATES=true 1>>${repRID}.dedup.out 2>> ${repRID}.dedup.err
+    samtools sort -@ `nproc` -O BAM -o ${repRID}.sorted.deduped.bam ${repRID}.deduped.bam 1>>${repRID}.dedup.out 2>> ${repRID}.dedup.err
+    samtools index -@ `nproc` -b ${repRID}.sorted.deduped.bam ${repRID}.sorted.deduped.bai 1>>${repRID}.dedup.out 2>> ${repRID}.dedup.err
     """
 }
 
@@ -376,4 +378,23 @@ process fastqc {
     # run fastqc
     fastqc *.fastq.gz -o . >>${repRID}.fastqc.err
     """
-}
\ No newline at end of file
+}
+
+/*
+ *Make BigWig files for later processes
+*/
+process makeBigWig {
+  tag "${repRID}"
+  publishDir "${logsDir}", mode: 'copy', pattern: "*.makeBigWig.err"
+
+  input:
+    set val (repRID), path (inBam), path (inBai) from dedupBam
+
+  output:
+    path ("${repRID}.bw")
+
+  script:
+    """
+    bamCoverage -p `nproc` -b ${inBam} -o ${repRID}.bw
+    """
+}

workflow/tests/test_makeBigWig.py

+#!/usr/bin/env python3
+
+import pytest
+import pandas as pd
+import os
+import utils
+
+data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
+	'/../../'
+
+
+@pytest.mark.makeBigWig
+def test_makeBigWig():
+	assert os.path.exists(os.path.join(data_output_path, 'Q-Y5JA_1M.se.bw'))