Add msisensor (#95)

.github/workflows/ci.yml

@@ -131,7 +131,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        tool: [Haplotypecaller, Freebayes, Manta, mpileup, Strelka, TIDDIT]
+        tool: [Haplotypecaller, Freebayes, Manta, mpileup, Strelka, TIDDIT, msisensor]
     steps:
       - uses: actions/checkout@v2
       - name: Install Nextflow

CHANGELOG.md

@@ -15,6 +15,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a
 - [#141](https://github.com/nf-core/sarek/pull/141) - Add containers for `WBcel235`
 - [#150](https://github.com/nf-core/sarek/pull/150), [#151](https://github.com/nf-core/sarek/pull/151), [#154](https://github.com/nf-core/sarek/pull/154) - Add AWS mega test GitHub Actions
 - [#158](https://github.com/nf-core/sarek/pull/158) - Added `ggplot2` v `3.3.0`
+- [#163](https://github.com/nf-core/sarek/pull/163) - Add [msisensor](https://github.com/ding-lab/msisensor) in tools and container
 
 ### `Changed`
 

README.md

@@ -105,6 +105,7 @@ Helpful contributors:
 * [gulfshores](https://github.com/gulfshores)
 * [pallolason](https://github.com/pallolason)
 * [silviamorins](https://github.com/silviamorins)
+* [David Mas-Ponte](https://github.com/davidmasp)
 
 ## Contributions & Support
 

bin/scrape_software_versions.py

@@ -13,6 +13,7 @@
     'GATK': ['v_gatk.txt', r"Version:(\S+)"],
     'htslib': ['v_samtools.txt', r"htslib (\S+)"],
     'Manta': ['v_manta.txt', r"([0-9.]+)"],
+    'msisensor': ["v_msisensor.txt", r"Version: v(\S+)"],
     'MultiQC': ['v_multiqc.txt', r"multiqc, version (\S+)"],
     'Nextflow': ['v_nextflow.txt', r"(\S+)"],
     'nf-core/sarek': ['v_pipeline.txt', r"(\S+)"],
@@ -38,6 +39,7 @@
 results['GATK'] = '<span style="color:#999999;\">N/A</span>'
 results['htslib'] = '<span style="color:#999999;\">N/A</span>'
 results['Manta'] = '<span style="color:#999999;\">N/A</span>'
+results['msisensor'] = '<span style="color:#999999;\">N/A</span>'
 results['MultiQC'] = '<span style="color:#999999;\">N/A</span>'
 results['Qualimap'] = '<span style="color:#999999;\">N/A</span>'
 results['R'] = '<span style="color:#999999;\">N/A</span>'

docs/containers.md

@@ -26,6 +26,7 @@ For annotation, the main container can be used, but the cache has to be download
 - Contain **[ggplot2](https://github.com/tidyverse/ggplot2)** 3.3.0
 - Contain **[HTSlib](https://github.com/samtools/htslib)** 1.9
 - Contain **[Manta](https://github.com/Illumina/manta)** 1.6.0
+- Contain **[msisensor](https://github.com/ding-lab/msisensor)** 0.5
 - Contain **[MultiQC](https://github.com/ewels/MultiQC/)** 1.8
 - Contain **[Qualimap](http://qualimap.bioinfo.cipf.es)** 2.2.2d
 - Contain **[samtools](https://github.com/samtools/samtools)** 1.9

docs/output.md

@@ -34,6 +34,8 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
     - [ConvertAlleleCounts](#convertallelecounts)
     - [ASCAT](#ascat)
     - [Control-FREEC](#control-freec)
+  - [MSI status](#msi-status)
+    - [msisensor](#msisensor)
 - [Variant annotation](#variant-annotation)
   - [snpEff](#snpeff)
   - [VEP](#vep)
@@ -424,6 +426,36 @@ For a Tumor/Normal pair only:
 - `[TUMORSAMPLE].pileup.gz_BAF.txt` and `[NORMALSAMPLE].pileup.gz_BAF.txt`
   - file with beta allele frequencies for each possibly heterozygous SNP position
 
+### MSI status
+
+[Microsatellite instability](https://en.wikipedia.org/wiki/Microsatellite_instability)
+is a genetic condition associated to deficienceies in the
+mismatch repair (MMR) system which causes a tendency to accumulate a high
+number of mutations (SNVs and indels).
+
+#### msisensor
+
+[msisensor](https://github.com/ding-lab/msisensor) is a tool to detect the MSI
+status of a tumor scaning the length of the microsatellite regions. An altered
+distribution of  microsatellite length is associated to a missed replication
+slippage which would be corrected under normal MMR conditions. It requires
+a normal sample for each tumour to differentiate the somatic and germline
+cases.
+
+For further reading see the [msisensor paper](https://www.ncbi.nlm.nih.gov/pubmed/24371154).
+
+For a Tumor/Normal pair only:
+**Output directory: `results/MSI/[TUMORSAMPLE]_vs_[NORMALSAMPLE]/msisensor`**
+
+- `[TUMORSAMPLE]_vs_[NORMALSAMPLE]`_msisensor
+  - MSI score output, contains information about the number of somatic sites.
+- `[TUMORSAMPLE]_vs_[NORMALSAMPLE]`_msisensor_dis
+  - The normal and tumor length distribution for each microsatellite position.
+- `[TUMORSAMPLE]_vs_[NORMALSAMPLE]`_msisensor_germline
+  - somatic sites detected
+- `[TUMORSAMPLE]_vs_[NORMALSAMPLE]`_msisensor_somatic
+  - germ line sites detected
+
 ## Variant annotation
 
 This directory contains results from the final annotation steps: two software are used for annotation, [snpEff](http://snpeff.sourceforge.net/) and [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html).

environment.yml

@@ -21,6 +21,7 @@ dependencies:
   - bioconda::genesplicer=1.0
   - bioconda::htslib=1.9
   - bioconda::manta=1.6.0
+  - bioconda::msisensor=0.5
   - bioconda::multiqc=1.8
   - bioconda::qualimap=2.2.2d
   - bioconda::samtools=1.9

main.nf

@@ -618,6 +618,7 @@ process Get_software_versions {
     trim_galore -v &> v_trim_galore.txt 2>&1 || true
     vcftools --version &> v_vcftools.txt 2>&1 || true
     vep --help &> v_vep.txt 2>&1 || true
+    msisensor &> v_msisensor.txt 2>&1 || true
 
     scrape_software_versions.py &> software_versions_mqc.yaml
     """
@@ -2069,8 +2070,8 @@ pairBam = bamNormal.cross(bamTumor).map {
 
 pairBam = pairBam.dump(tag:'BAM Somatic Pair')
 
-// Manta, Strelka, Mutect2
-(pairBamManta, pairBamStrelka, pairBamStrelkaBP, pairBamCalculateContamination, pairBamFilterMutect2, pairBamTNscope, pairBam) = pairBam.into(7)
+// Manta, Strelka, Mutect2, MSIsensor
+(pairBamManta, pairBamStrelka, pairBamStrelkaBP, pairBamCalculateContamination, pairBamFilterMutect2, pairBamTNscope, pairBamMsisensor, pairBam) = pairBam.into(8)
 
 intervalPairBam = pairBam.spread(bedIntervals)
 
@@ -2605,6 +2606,64 @@ process StrelkaBP {
 
 vcfStrelkaBP = vcfStrelkaBP.dump(tag:'Strelka BP')
 
+// STEP MSISENSOR.1 - SCAN
+
+// Scan reference genome for microsattelites
+process msisensorScan {
+    label 'cpus_1'
+    label 'memory_max'
+    // memory '20 GB'
+
+    tag {fasta}
+
+    input:
+    file(fasta) from ch_fasta
+    file(fastaFai) from ch_fai
+
+    output:
+    file "microsatellites.list" into msi_scan_ch
+
+    when: 'msisensor' in tools
+
+    script:
+    """
+    msisensor scan -d ${fasta} -o microsatellites.list
+    """
+}
+
+// STEP MSISENSOR.2 - SCORE
+
+// Score the normal vs somatic pair of bams
+
+process msisensor {
+    label 'cpus_4'
+    label 'memory_max'
+    // memory '10 GB'
+
+    tag {idSampleTumor + "_vs_" + idSampleNormal}
+
+    publishDir "${params.outdir}/MSI/${idSampleTumor}_vs_${idSampleNormal}/msisensor", mode: params.publishDirMode
+
+    input:
+    set idPatient, idSampleNormal, file(bamNormal), file(baiNormal), idSampleTumor, file(bamTumor), file(baiTumor) from pairBamMsisensor
+    file msiSites from msi_scan_ch
+
+    output:
+    set val("Msisensor"), idPatient, file("${idSampleTumor}_vs_${idSampleNormal}_msisensor"), file("${idSampleTumor}_vs_${idSampleNormal}_msisensor_dis"), file("${idSampleTumor}_vs_${idSampleNormal}_msisensor_germline"), file("${idSampleTumor}_vs_${idSampleNormal}_msisensor_somatic") into msisensor_out_ch
+
+    when:
+    when: 'msisensor' in tools
+
+    script:
+    """
+    msisensor msi -d ${msiSites} \
+                  -b 4 \
+                  -n ${bamNormal} \
+                  -t ${bamTumor} \
+                  -o ${idSampleTumor}_vs_${idSampleNormal}_msisensor
+    """
+}
+
 // STEP ASCAT.1 - ALLELECOUNTER
 
 // Run commands and code from Malin Larsson
@@ -3595,7 +3654,8 @@ def defineToolList() {
         'strelka',
         'tiddit',
         'tnscope',
-        'vep'
+        'vep',
+        'msisensor'
     ]
 }