Merge pull request #606 from SusiJo/ascat

Include new module ASCAT

Author: FriederikeHanssen

CHANGELOG.md

@@ -70,6 +70,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#581](https://github.com/nf-core/sarek/pull/581) - `TIDDIT` is updated to `3.1.0`
 - [#593](https://github.com/nf-core/sarek/pull/593) - update `ensembl-vep` cache version and module
 - [#600](https://github.com/nf-core/sarek/pull/600) - Remove `TODO` in awsfulltest
+- [#606](https://github.com/nf-core/sarek/pull/606) - Updated `ASCAT` to version `3.0` as module
 - [#608](https://github.com/nf-core/sarek/pull/608) - Prevent candidate VCFs from getting published in manta
 
 ### Fixed

bin/convertAlleleCounts.r

@@ -12,8 +12,11 @@ params {
     // illumina iGenomes reference file paths
     genomes {
         'GATK.GRCh37' {
-            ac_loci               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/1000G_phase3_20130502_SNP_maf0.3.loci"
-            ac_loci_gc            = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/1000G_phase3_20130502_SNP_maf0.3.loci.gc"
+            ascat_alleles         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/G1000_alleles_hg19.zip"
+            ascat_genome          = 'hg19'
+            ascat_loci            = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/G1000_loci_hg19.zip"
+            ascat_loci_gc         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/GC_G1000_hg19.zip"
+            ascat_loci_rt         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/RT_G1000_hg19.zip"
             bwa                   = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/BWAIndex/"
             chr_dir               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/Chromosomes"
             dbsnp                 = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf"
@@ -34,8 +37,11 @@ params {
             vep_species           = 'homo_sapiens'
         }
         'GATK.GRCh38' {
-            ac_loci               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/ASCAT/1000G_phase3_GRCh38_maf0.3.loci"
-            ac_loci_gc            = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/ASCAT/1000G_phase3_GRCh38_maf0.3.loci.gc"
+            ascat_alleles         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/G1000_alleles_hg38.zip"
+            ascat_genome          = 'hg38'
+            ascat_loci            = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/G1000_loci_hg38.zip"
+            ascat_loci_gc         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/GC_G1000_hg38.zip"
+            ascat_loci_rt         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/ASCAT/RT_G1000_hg38.zip"
             bwa                   = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAIndex/"
             bwamem2               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAmem2Index/"
             dragmap               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/dragmap/"

bin/run_ascat.r

@@ -923,25 +923,25 @@ process{
 // PAIR_VARIANT_CALLING
 
     //ASCAT
-    if (params.tools && params.tools.contains('ascat')) {
-        withName: 'ASCAT' {
-            ext.args = {
-                [
-                "gender": meta.sex,
-                //"genomeVersion": "hg19"
-                //"purity": (optional),
-                //"ploidy": params.ploidy,
-                //"gc_files": (optional),
-                //"minCounts": (optional),
-                //"chrom_names": (optional),
-                //"min_base_qual": (optional),
-                //"min_map_qual": (optional),
-                //"ref_fasta": (optional),
-                //"skip_allele_counting_tumour": (optional),
-                //"skip_allele_counting_normal": (optional)
-                ]
-            }
-        }
+    withName: 'ASCAT' {
+
+        ext.args = {[
+            "gender": meta.gender,
+            "genomeVersion": params.ascat_genome,
+            "purity": params.ascat_purity,
+            "ploidy": params.ploidy,
+            "minCounts": params.ascat_min_counts,
+            "chrom_names": meta.gender == 'XX' ? params.ascat_chromosomes : "c(1:22, 'X', 'Y')",
+            "min_base_qual": params.ascat_min_base_qual,
+            "min_map_qual": params.ascat_min_map_qual
+            ]}
+        ext.when         = { params.tools && params.tools.contains('ascat') }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/${meta.id}/ascat" },
+            pattern: "*{png,cnvs.txt,metrics.txt,purityploidy.txt,segments.txt,LogR.txt,BAF.txt}"
+        ]
+
     }
 
     //CONTROLFREEC

conf/igenomes.config

@@ -147,6 +147,25 @@ profiles {
 
         params.nucleotides_per_second = 20
     }
+    // can only be tested locally due to too large cram files for GHA
+    // download corresponding input files (ascat_somatic.csv) from ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/phase3/data/
+    // test works only without chromosome annotated loci files available at https://github.com/VanLoo-lab/ascat/tree/master/ReferenceFiles/WGS
+    tools_somatic_ascat{
+        params.input               = "${baseDir}/tests/csv/3.0/ascat_somatic.csv"
+        params.chr_dir             = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
+        params.ascat_loci          = "/mnt/volume/repos/modules/test_ascat2/G1000_loci_hg19.zip"
+        params.ascat_chromosomes   = 'c("21", "22")'
+        params.ascat_min_base_qual = 30
+        params.germline_resource   = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
+        params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
+        params.step                = 'variant_calling'
+        params.joint_germline      = true
+        params.wes                 = false
+        params.tools               = 'ascat'
+        params.igenomes_ignore     = false
+        params.genome             = 'GATK.GRCh37'
+
+    }
     trimming {
         params.clip_r1             = 1
         params.clip_r2             = 1

conf/modules.config

@@ -42,7 +42,6 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
     - [TIDDIT](#tiddit)
     - [Sentieon DNAscope SV](#sentieon-dnascope-sv)
   - [Sample heterogeneity, ploidy and CNVs](#sample-heterogeneity-ploidy-and-cnvs)
-    - [ConvertAlleleCounts](#convertallelecounts)
     - [ASCAT](#ascat)
     - [Control-FREEC](#control-freec)
   - [MSI status](#msi-status)
@@ -432,51 +431,45 @@ For further reading and documentation see the [Sentieon DNAscope user guide](htt
 
 ### Sample heterogeneity, ploidy and CNVs
 
-#### ConvertAlleleCounts
-
-Running ASCAT on NGS data requires that the `BAM` files are converted into BAF and LogR values.
-This can be done using the software [AlleleCount](https://github.com/cancerit/alleleCount) followed by the provided [ConvertAlleleCounts](https://github.com/nf-core/sarek/blob/master/bin/convertAlleleCounts.r) R-script.
-
-For a Tumor/Normal pair:
-
-**Output directory: `results/VariantCalling/[TUMOR_vs_NORMAL]/ASCAT`**
-
-- `[TUMORSAMPLE].BAF` and `[NORMALSAMPLE].BAF`
-  - file with beta allele frequencies
-- `[TUMORSAMPLE].LogR` and `[NORMALSAMPLE].LogR`
-  - file with total copy number on a logarithmic scale
-
 #### ASCAT
 
 [ASCAT](https://github.com/Crick-CancerGenomics/ascat) is a software for performing allele-specific copy number analysis of tumor samples and for estimating tumor ploidy and purity (normal contamination).
 It infers tumor purity and ploidy and calculates whole-genome allele-specific copy number profiles.
 `ASCAT` is written in `R` and available here: [github.com/Crick-CancerGenomics/ascat](https://github.com/Crick-CancerGenomics/ascat).
 The `ASCAT` process gives several images as output, described in detail in this [book chapter](http://www.ncbi.nlm.nih.gov/pubmed/22130873).
+Running ASCAT on NGS data requires that the `BAM` files are converted into BAF and LogR values.
+This is done internally using the software [AlleleCount](https://github.com/cancerit/alleleCount).
 
 For a Tumor/Normal pair:
 
-**Output directory: `results/VariantCalling/[TUMOR_vs_NORMAL]/ASCAT`**
+**Output directory: `results/variant_calling/[TUMOR_vs_NORMAL]/ascat`**
 
-- `[TUMORSAMPLE].aberrationreliability.png`
-  - Image with information about aberration reliability
-- `[TUMORSAMPLE].ASCATprofile.png`
-  - Image with information about ASCAT profile
-- `[TUMORSAMPLE].ASPCF.png`
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].tumour.ASPCF.png`
   - Image with information about ASPCF
-- `[TUMORSAMPLE].rawprofile.png`
-  - Image with information about raw profile
-- `[TUMORSAMPLE].sunrise.png`
-  - Image with information about sunrise
-- `[TUMORSAMPLE].tumour.png`
-  - Image with information about tumor
-- `[TUMORSAMPLE].cnvs.txt`
-  - file with information about CNVS
-- `[TUMORSAMPLE].LogR.PCFed.txt`
-  - file with information about LogR
-- `[TUMORSAMPLE].purityploidy.txt`
-  - file with information about purity ploidy
-
-The text file `[TUMORSAMPLE].cnvs.txt` countains predictions about copy number state for all the segments.
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].before_correction.[TUMORSAMPLE_VS_NORMALSAMPLE].tumour.png`
+  - Image with information about raw profile of tumor sample of logR and BAF values
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].before_correction.[TUMORSAMPLE_VS_NORMALSAMPLE].germline.png`
+  - Image with information about raw profile of normal sample of logR and BAF values
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].after_correction_gc_rt.[TUMORSAMPLE_VS_NORMALSAMPLE].tumour.png`
+  - Image with information about GC and RT corrected logR and BAF values of tumor sample
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].after_correction_gc_rt.[TUMORSAMPLE_VS_NORMALSAMPLE].germline.png`
+  - Image with information about GC and RT corrected logR and BAF values of normal sample
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].sunrise.png`
+  - Image visualising the range of ploidy and tumor percentage values
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].metrics.txt`
+  - File with information about different metrics from ASCAT profiles
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].cnvs.txt`
+  - File with information about CNVS
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].purityploidy.txt`
+  - File with information about purity and ploidy
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].segments.txt`
+  - File with information about copy number segments
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].tumour_tumourBAF.txt` and `[TUMORSAMPLE_VS_NORMALSAMPLE].tumour_normalBAF.txt`
+  - file with beta allele frequencies
+- `[TUMORSAMPLE_VS_NORMALSAMPLE].tumour_tumourLogR.txt` and `[TUMORSAMPLE_VS_NORMALSAMPLE].tumour_normalLogR.txt`
+  - File with total copy number on a logarithmic scale
+
+The text file `[TUMORSAMPLE_VS_NORMALSAMPLE].cnvs.txt` contains predictions about copy number state for all the segments.
 The output is a tab delimited text file with the following columns:
 
 - _chr_: chromosome number