Add SVCallers: gridss and CNV: cnvkit,ascat

.github/workflows/build.yml

@@ -13,9 +13,10 @@ on:
 jobs:
   build:
     runs-on: ubuntu-latest
+    timeout-minutes: 2
     strategy:
       matrix:
-        python-version: ["3.9"]
+        python-version: ["3.10"]
 
     steps:
       - uses: actions/checkout@v3
@@ -25,22 +26,29 @@ jobs:
           python-version: ${{ matrix.python-version }}
           cache: "pip"
       - name: Install nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
+        with:
+          version: "24.04.4"
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip setuptools
           pip install .[dev,test]
           python -c 'from logan.src.util import chmod_bins_exec; chmod_bins_exec()'
-      - name: Test stub run
+      - name: Check CLI basics
         run: |
-          mkdir tmp && cd tmp
           which logan
-          logan init
-          logan run -profile ci_stub,docker \
-          --fastq_input "/opt2/.tests/*R{1,2}.fastq.gz" \
-          --vc --cnv --sv \
+          logan --version
+          logan --citation
+      - name: Test stub run for Fastqs
+        run: |
+          logan init 
+          logan run -profile ci_stub \
+          --sample_sheet .tests/pairs.tsv \
+          --fastq_input ".tests/*R{1,2}_001.fastq.gz" \
+          --vc --cnv --sv --gl --qc \
+          --split_regions 2 \
           --genome hg38 \
-          --outdir /opt2/output_tn_fqs \
-          --interval /opt2/.tests/interval.bed \
+          --outdir output_tn_fqs \
+          --intervals .tests/interval.bed \
           -stub
 

.tests/README.md

@@ -2,5 +2,5 @@
 
 These input files are used for continuous integration purposes, specificially to dry run the pipeline whenever commits have been made to the main, master, or unified branches.
 
-**Please Note:** Each of the provided FastQ files and BAM files are empty and are not suitable input to the CCBR GATK4 pipeline!
+**Please Note:** Each of the provided FastQ files and BAM files have only headers and will not work for the LOGAN pipeline
 

.tests/interval.bed

@@ -0,0 +1,10 @@
+chr22	10510000	10784643	. intersection ACGTmer	500	+
+chr22	10834643	10874572	. intersection ACGTmer	500	+
+chr22	10924572	10966724	. intersection ACGTmer	500	+
+chr22	11016724	11068987	. intersection ACGTmer	500	+
+chr22	11118987	11160921	. intersection ACGTmer	500	+
+chr22	11210921	11378056	. intersection ACGTmer	500	+
+chr22	11428056	11497337	. intersection ACGTmer	500	+
+chr22	11547337	11631288	. intersection ACGTmer	500	+
+chr22	11681288	11724629	. intersection ACGTmer	500	+
+chr22	11774629	11977555	. intersection ACGTmer	500	+

.tests/pairs.tsv

@@ -1,3 +1,2 @@
-Tumor   Normal
-Sample10_ARK1_S37   Sample4_CRL1622_S31	
-Sample11_ACI_158_S38    Sample4_CRL1622_S31
+Tumor	Normal
+WGS_NC_T	WGS_NC_N	

CHANGELOG.md

@@ -1,5 +1,15 @@
 # LOGAN development version
 
+## LOGAN 0.2.0
+### New features
+- Added additional SV callers(GRIDSS) and annotation for SV (GRIPSS) + CNV Callers (ASCAT, CNVKit) + SNV (Deepsomatic)
+- Bugfixes for hg19 by fixing references
+- Updated PON for hg38 using TCGA/GDC references
+- In development: adding exome support by using bed file to restrict calling regions
+- Refactored modules to be similar to nf-core
+
+## LOGAN 0.1.0
+### Features
 - Changed over to Nextflow CCBR template and pip packaging
     - Processes moved to `modules/local` directory
     - Workflows under the `subworkflows/local` directory

CITATION.cff

@@ -9,6 +9,10 @@ authors:
     given-names: Kelly
     orcid: https://orcid.org/0000-0003-3283-829X
     affiliation: Advanced Biomedical Computational Science, Frederick National Laboratory for Cancer Research, Frederick, MD 21702, USA
+  - family-names: Mathur
+    given-names: Samarth
+    orcid: https://orcid.org/0000-0002-6446-5718
+    affiliation: Advanced Biomedical Computational Science, Frederick National Laboratory for Cancer Research, Frederick, MD 21702, USA
   - family-names: Koparde
     given-names: Vishal
     orcid: https://orcid.org/0000-0001-8978-8495

README.md

@@ -19,19 +19,20 @@ Original pipelining and code forked from the CCBR Exome-seek Pipeline [Exome-see
 [singularity](https://singularity.lbl.gov/all-releases) must be installed on the target system. Snakemake orchestrates the execution of each step in the pipeline. To guarantee the highest level of reproducibility, each step relies on versioned images from [DockerHub](https://hub.docker.com/orgs/nciccbr/repositories). Nextflow uses singularity to pull these images onto the local filesystem prior to job execution, and as so, nextflow and singularity are the only two dependencies.
 
 ## Setup
-LOGAN can be used with the Nextflow pipelining software
+LOGAN can be used with the Nextflow pipelining software in 
 Please clone this repository to your local filesystem using the following command on Biowulf:
+
 ```bash
 # start an interactive node
 sinteractive --mem=2g --cpus-per-task=2 --gres=lscratch:200
+
 git clone https://github.com/CCBR/LOGAN
 module load nextflow
 ##Example run 
-nextflow run /data/LOGAN//main.nf
+nextflow run LOGAN/main.nf -profile ci_stub -preview
 ```
 
 ## Usage
-LOGAN supports 
 
 ### Input Files
 LOGAN supports inputs of either 
@@ -68,10 +69,10 @@ c130889189_PBMC  /data/nousomedr/c130889189_PBMC.bam  /data/nousomedr/c130889189
 `--genome hg19` and `--genome mm10` are also supported 
 
 #### hg38 has options for either  
-`--genome hg38` - Based off the GRCh38.d1.vd1.fa which is consistent with TCGA and other GDC processing pipelines  
+`--genome hg38` - Based off the GRCh38.d1.vd1.fa which is consistent with TCGA/GDC processing pipelines  
 
 `--genome hg38_sf` - Based off the Homo_sapiens_assembly38.fasta which is derived from the Broad Institute/NCI Sequencing Facility
-The biggest difference between the two is that GRCh38.d1.vd1.fa has fewer contigs (especially related to HLA regions), so reads should map to chr6 vs the HLA contig directly
+The biggest difference between the two is that GRCh38.d1.vd1.fa only the GCA_000001405.15_GRCh38_no_alt_analysis_set, Sequence Decoys (GenBank Accession GCA_000786075), and Virus Sequences. Homo_sapiens_assembly38.fasta has HLA specific contigs which may not be compatible with certain downstream tools.
 
 
 ### Operating Modes
@@ -97,48 +98,51 @@ No addtional flags for sample sheet are required as all samples will be used to
 
 Adding flags determines SNV (germline and/or somatic), SV, and/or CNV calling modes
 
-`--vc`- Enables somatic SNV calling using mutect2, vardict, varscan, octopus, strelka (TN only), MUSE (TN only), and lofreq (TN only)
+`--vc`- Enables somatic SNV calling using mutect2, deepsomatic, vardict, varscan, octopus, strelka (TN only), MUSE (TN only), and lofreq (TN only)
 
-`--germline`- Enables germline using Deepvariant
+`--germline`- Enables germline calling using Deepvariant
 
-`--sv`- Enables somatic SV calling using Manta, SVABA, and GRIDSS (coming soon)
+`--sv`- Enables somatic SV calling using Manta, GRIDSS, and SVABA
 
-`--cnv`- Enables somatic CNV calling using FREEC, Sequenza, and Purple (hg19/hg38 only)
+`--cnv`- Enables somatic CNV calling using FREEC, Sequenza, CNVKit, ASCAT(hg19/hg38 only), and Purple (hg19/hg38 only)
 
 
 
 #### Optional Arguments
 `--indelrealign` - Enables indel realignment when running alignment steps. May be helpful for certain callers (VarScan, VarDict)
 
-`--callers`- Comma separated argument for callers, the default is to use all available.  
+`--callers`- Comma separated argument for selecting only specified callers, the default is to use all available.  
 Example: `--callers mutect2,octopus`
 
-`--cnvcallers`- - Comma separated argument for CNV callers to use. Adding flag allows only certain callers to run.  
+`--cnvcallers`- - Comma separated argument for selecting only specified CNV callers. Adding flag allows only certain callers to run.  
 Example: `--cnvcallers purple`
 
-`--svcallers`- - Comma separated argument for SV callers. Adding flag allows only certain callers to run.  
-Example: `--cnvcallers manta`
+`--svcallers`- - Comma separated argument for selecting only specified SV vallers. Adding flag allows only certain callers to run.  
+Example: `--svcallers gridss`
+
+`--ffpe`- - Adds additional filtering for FFPE by detecting strand orientation bias using SOBDetector. 
 
+`--exome`- - Limits calling to intervals provided in target bed to reduce time and to account for exome sequencing specific parameters.
 
 ## Running LOGAN
 Example of Tumor_Normal calling mode 
 ```bash
 # preview the logan jobs that will run 
-nextflow run /data/LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" -preview --vc --sv --cnv
+nextflow run LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" -preview --vc --sv --cnv
 # run a stub/dryrun of the logan jobs 
-nextflow run /data/LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" -stub --vc --sv --cnv
+nextflow run LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" -stub --vc --sv --cnv
 # launch a logan run on slurm with the test dataset
-nextflow run /data/LOGAN/main.nf --mode slurm -profile biowulf,slurm --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" --vc --sv --cnv 
+nextflow run LOGAN/main.nf --mode slurm -profile biowulf,slurm --genome hg38 --sample_sheet samplesheet.tsv --outdir out --fastq_input "*R{1,2}.fastq.gz" --vc --sv --cnv 
 ```
 
 Example of Tumor only calling mode 
 ```bash
 # preview the logan jobs that will run 
-nextflow run /data/LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 -preview --vc --sv --cnv
+nextflow run LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 -preview --vc --sv --cnv
 # run a stub/dryrun of the logan jobs 
-nextflow run /data/LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 -stub --vc --sv --cnv
+nextflow run LOGAN/main.nf --mode local -profile ci_stub --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 -stub --vc --sv --cnv
 # launch a logan run on slurm with the test dataset
-nextflow run /data/LOGAN/main.nf --mode slurm -profile biowulf,slurm --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 --vc --sv --cnv
+nextflow run LOGAN/main.nf --mode slurm -profile biowulf,slurm --genome hg38 --outdir out --fastq_input "*R{1,2}.fastq.gz" --callers octopus,mutect2 --vc --sv --cnv
 ```
 
 

VERSION

@@ -1 +1 @@
-0.1.0-dev
+0.2.0

bin/ascat.R

@@ -10,38 +10,60 @@ library(RColorBrewer)
 
 args = commandArgs(trailingOnly=TRUE)
 tumor_bam=args[1]
-normal_bam=args[2]
+tumor_name=args[2]
+normal_bam=args[3]
+normal_name=args[4]
+genome=args[5]
+bed=args[6]
+exome=args[7]
+#chroms=scan(text=args[4],sep=",",quiet=T)
+cpus=as.numeric(Sys.getenv("SLURM_CPUS_PER_TASK"))
+cpus=ifelse(is.na(cpus),2,cpus)
 
-genome="hg38"
+if (exists(exome)){
+  genomebasedir=sprintf("/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/%s/ASCAT/WES",genome)
+}else{
+  genomebasedir=sprintf("/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/%s/ASCAT",genome)
+
+}
+
+##DETERMINE SEX
+system(sprintf('alleleCounter -l %s/gender_chr.loci -b %s -c chrX -o %s_temp_gender.out',
+  genomebasedir,normal_bam,normal_name))
+s=read.table(sprintf("%s_temp_gender.out",normal_name))
+gender=ifelse(sum(s$V7)>5,"XY","XX")
+print(gender)
 
 ascat.prepareHTS(
   tumourseqfile = tumor_bam,
   normalseqfile = normal_bam,
   tumourname = tumor_name,
   normalname = normal_name,
-  allelecounter_exe = "/PATH/TO/allelecounter",
-  alleles.prefix = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/ASCAT/G1000_alleles",
-  loci.prefix = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/ASCAT_G1000_loci",
-  nthreads = 10
-  gender = "XX",
+  allelecounter_exe = "alleleCounter",
+  alleles.prefix = sprintf("%s/G1000_alleles/G1000_alleles_%s_chr",genomebasedir,genome),
+  loci.prefix = sprintf("%s/G1000_loci/G1000_loci_%s_chr",genomebasedir,genome),
+  gender = gender,
   genomeVersion = genome,
-  nthreads = 8,
-  tumourLogR_file = "Tumor_LogR.txt",
-  tumourBAF_file = "Tumor_BAF.txt",
-  normalLogR_file = "Germline_LogR.txt",
-  normalBAF_file = "Germline_BAF.txt")
+  nthreads = cpus,
+  tumourLogR_file = sprintf("%s_LogR.txt",tumor_name),
+  tumourBAF_file = sprintf("%s_BAF.txt",tumor_name),
+  normalLogR_file = sprintf("%s_LogR.txt",normal_name),
+  normalBAF_file = sprintf("%s_BAF.txt",normal_name),
+  BED_file=bed)
 
-ascat.bc = ascat.loadData(Tumor_LogR_file = "Tumor_LogR.txt", Tumor_BAF_file = "Tumor_BAF.txt", 
-    Germline_LogR_file = "Germline_LogR.txt", Germline_BAF_file = "Germline_BAF.txt", gender = 'XX', genomeVersion = "hg19")
+ascat.bc = ascat.loadData(Tumor_LogR_file = sprintf("%s_LogR.txt",tumor_name), 
+    Tumor_BAF_file = sprintf("%s_BAF.txt",tumor_name), 
+    Germline_LogR_file = sprintf("%s_LogR.txt",normal_name), Germline_BAF_file = sprintf("%s_BAF.txt",normal_name), 
+    gender = gender, genomeVersion = genome)
 
 ascat.plotRawData(ascat.bc, img.prefix = "Before_correction_")
-ascat.bc = ascat.correctLogR(ascat.bc, GCcontentfile = "GC_file.txt", replictimingfile = "RT_file.txt")
+ascat.bc = ascat.correctLogR(ascat.bc, 
+  GCcontentfile = sprintf("%s/GC_G1000/GC_G1000_%s.txt",genomebasedir,genome), 
+  replictimingfile = sprintf("%s/RT_G1000/RT_G1000_%s.txt",genomebasedir,genome))
 ascat.plotRawData(ascat.bc, img.prefix = "After_correction_")
 ascat.bc = ascat.aspcf(ascat.bc)
 ascat.plotSegmentedData(ascat.bc)
 ascat.output = ascat.runAscat(ascat.bc, gamma=1, write_segments = T)
 QC = ascat.metrics(ascat.bc,ascat.output)
-save(ascat.bc, ascat.output, QC, file = 'ASCAT_objects.Rdata')
-
-
-#####
+write.table(QC,sprintf("%s.qc.txt",paste0(tumor_name,"_vs_",normal_name)))
+save(ascat.bc, ascat.output, QC, file = sprintf('%s_vs_%s_ascat.Rdata',tumor_name,normal_name))

bin/hello-world.py

@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+
+"""
+Example script that could be used by a nextflow process
+"""
+
+import sys
+
+
+def main():
+    print("Hello world!")
+
+
+if __name__ == "__main__":
+    main(sys.argv)

bin/logan

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+# script that allows the CLI to work out-of-the-box
+# without the need to install it via pip first
+
+TOOLDIR=$(realpath $(dirname $(dirname ${BASH_SOURCE})))
+
+${TOOLDIR}/main.py "$@"

bin/make_freec_exome_paired.pl

@@ -0,0 +1,50 @@
+#!/usr/bin/perl -w
+use strict;
+use List::Util 'shuffle';
+
+#INPUT
+
+#my $mergedmaf = $ARGV[1] . '_out/oncotator_out/' . $ARGV[1] . '_merged.maf'; #to fix...
+#open C, ">$mergedmaf";
+
+my $outfile = $ARGV[0] . '/freec_exome_config.txt';
+my $chrLenFile = $ARGV[1];
+my $chrFiles = $ARGV[2];
+my $tumormateFile = $ARGV[3];
+my $controlmateFile = $ARGV[4];
+my $makePileup = $ARGV[5];
+my $fastaFile = $ARGV[6];
+my $SNPfile = $ARGV[7];
+my $targets = $ARGV[8];
+
+open C, ">$outfile";
+
+print C '[general]' . "\n\n";
+
+print C "BedGraphOutput = TRUE\ndegree = 1\nforceGCcontentNormalization = 1\nminCNAlength = 3\nnoisyData = TRUE\nreadCountThreshold = 50\n";
+print C "chrLenFile = $chrLenFile\n";
+print C "ploidy = 2\nbreakPointThreshold = 0.8\nwindow = 0\n";
+print C "chrFiles = $chrFiles\n";
+print C "minimalSubclonePresence = 30\nprintNA = FALSE\ncontaminationAdjustment = TRUE\nmaxThreads = 24\nnumberOfProcesses = 24\n";
+print C "outputDir = $ARGV[0]\n\n";
+
+print C '[sample]' . "\n\n";
+
+print C "mateFile = $tumormateFile\n";
+print C "inputFormat = BAM\nmateOrientation = FR\n\n";
+
+print C '[control]' . "\n\n";
+
+print C "mateFile = $controlmateFile\n";
+print C "inputFormat = BAM\nmateOrientation = FR\n\n";
+
+print C '[target]' . "\n\n";
+
+print C "captureRegions = $targets\n\n";
+
+print C '[BAF]' . "\n\n";
+
+print C "makePileup = $makePileup\n";
+print C "fastaFile = $fastaFile\n";
+print C "minimalCoveragePerPosition = 20\nminimalQualityPerPosition = 20\n";
+print C "SNPfile = $SNPfile";