Merge branch 'master' into vardict-java

modules/custom/getchromsizes/main.nf

@@ -2,10 +2,10 @@ process CUSTOM_GETCHROMSIZES {
     tag "$fasta"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::samtools=1.15" : null)
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/samtools:1.15--h1170115_1' :
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
-        'quay.io/biocontainers/samtools:1.15--h1170115_1' }"
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
 
     input:
     path fasta

modules/gatk4/splitncigarreads/main.nf

@@ -8,7 +8,7 @@ process GATK4_SPLITNCIGARREADS {
         'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(bam)
+    tuple val(meta), path(bam), path(bai), path(intervals)
     path  fasta
     path  fai
     path  dict
@@ -23,6 +23,7 @@ process GATK4_SPLITNCIGARREADS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def interval_command = intervals ? "--intervals $intervals" : ""
 
     def avail_mem = 3
     if (!task.memory) {
@@ -35,6 +36,7 @@ process GATK4_SPLITNCIGARREADS {
         --input $bam \\
         --output ${prefix}.bam \\
         --reference $fasta \\
+        $interval_command \\
         --tmp-dir . \\
         $args
 

modules/gatk4/splitncigarreads/meta.yml

@@ -23,6 +23,13 @@ input:
       type: list
       description: BAM/SAM/CRAM file containing reads
       pattern: "*.{bam,sam,cram}"
+  - bai:
+      type: list
+      description: BAI/SAI/CRAI index file (optional)
+      pattern: "*.{bai,sai,crai}"
+  - intervals:
+      type: file
+      description: Bed file with the genomic regions included in the library (optional)
   - fasta:
       type: file
       description: The reference fasta file

modules/rsem/calculateexpression/main.nf

@@ -2,10 +2,10 @@ process RSEM_CALCULATEEXPRESSION {
     tag "$meta.id"
     label 'process_high'
 
-    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null)
+    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' :
+        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' :
-        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' }"
+        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }"
 
     input:
     tuple val(meta), path(reads)

modules/rsem/preparereference/main.nf

@@ -2,10 +2,10 @@ process RSEM_PREPAREREFERENCE {
     tag "$fasta"
     label 'process_high'
 
-    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null)
+    conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' :
+        'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' :
-        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' }"
+        'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }"
 
     input:
     path fasta, stageAs: "rsem/*"

tests/config/test_data.config

@@ -245,8 +245,8 @@ params {
                 test2_2_fastq_gz                               = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
                 test2_umi_1_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
                 test2_umi_2_fastq_gz                           = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
-                test_rnaseq_1_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.rnaseq_1.fastq.gz"
+                test_rnaseq_1_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz"
-                test_rnaseq_2_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.rnaseq_2.fastq.gz"
+                test_rnaseq_2_fastq_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz"
 
                 test_baserecalibrator_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
                 test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"

tests/modules/gatk4/splitncigarreads/main.nf

@@ -6,7 +6,23 @@ include { GATK4_SPLITNCIGARREADS } from '../../../../modules/gatk4/splitncigarre
 
 workflow test_gatk4_splitncigarreads {
     input = [ [ id:'test' ], // meta map
-              [ file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ] 
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true),
+                [],
+                []
+            ]
+
+    fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_SPLITNCIGARREADS ( input, fasta, fai, dict )
+}
+
+workflow test_gatk4_splitncigarreads_intervals {
+    input = [ [ id:'test' ], // meta map
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true),
+                file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
             ]
     fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true)

tests/modules/gatk4/splitncigarreads/test.yml

@@ -5,5 +5,14 @@
     - gatk4/splitncigarreads
   files:
     - path: output/gatk4/test.bam
-      md5sum: ceed15c0bd64ff5c38d3816905933b0b
+      md5sum: 436d8e31285c6b588bdd1c7f1d07f6f2
+    - path: output/gatk4/versions.yml
+- name: gatk4 splitncigarreads test_gatk4_splitncigarreads_intervals
+  command: nextflow run tests/modules/gatk4/splitncigarreads -entry test_gatk4_splitncigarreads_intervals -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/splitncigarreads
+  files:
+    - path: output/gatk4/test.bam
+      md5sum: cd56e3225950f519fd47164cca60a0bb
     - path: output/gatk4/versions.yml

tests/modules/rsem/calculateexpression/test.yml

@@ -42,7 +42,7 @@
     - path: output/rsem/rsem/genome.transcripts.fa
       md5sum: 050c521a2719c2ae48267c1e65218f29
     - path: output/rsem/rsem/genomeParameters.txt
-      md5sum: 2fe3a030e1706c3e8cd4df3818e6dd2f
+      md5sum: df5a456e3242520cc36e0083a6a7d9dd
     - path: output/rsem/rsem/sjdbInfo.txt
       md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
     - path: output/rsem/rsem/sjdbList.fromGTF.out.tab
@@ -63,4 +63,4 @@
     - path: output/rsem/test.stat/test.theta
       md5sum: de2e4490c98cc5383a86ae8225fd0a28
     - path: output/rsem/test.transcript.bam
-      md5sum: 7846491086c478858419667d60f18edd
+      md5sum: ed681d39f5700ffc74d6321525330d93