Merge pull request #223 from uclahs-cds/sfitz-update-readme

Sfitz update readme

CHANGELOG.md

@@ -18,6 +18,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Add `split_VCF_bcftools` to `Mutect2` workflow, separating SNVs, MNVs and Indels
 
 ### Changed
+- Update `README.md`
 - Use `set_env` from `pipeline-Nextflow-config`
 - Update resource allocation to include new processes
 - Reconfigure `intersect_regions` to use all contigs except `decoy`

docs/flowcharts.md

@@ -0,0 +1,67 @@
+# pipeline-call-sSNV Flow Diagrams and Tool Links
+
+- [Variant Calling](#variant-calling)
+  - [SomaticSniper](#somaticsniper)
+  - [Strelka2](#strelka2)
+  - [Mutect2](#mutect2)
+  - [MuSE](#muse)
+- [Variant Intersection](#variant-intersection)
+  - [BCFtools, VennDiagram and vcf2maf](#variant-intersection)
+
+---
+
+## Variant Calling
+### SomaticSniper
+![Diagram](somatic-sniper.svg)
+#### Tools
+##### SomaticSniper
+SomaticSniper source: https://github.com/genome/somatic-sniper
+Version: SomaticSniper v1.0.5.0 (Released on Jul 16, 2015)
+GitHub Package: ghcr.io/uclahs-cds/somaticsniper:1.0.5.0
+##### bam-readcount
+bam-readcount source: https://github.com/genome/bam-readcount
+Version: v0.8.0 Release (Released on Oct 21, 2016)
+GitHub Package: ghcr.io/uclahs-cds/bam-readcount:0.8.0
+
+### Strelka2
+![Diagram](strelka2.svg)
+#### Tools
+##### Manta
+Manta source: https://github.com/Illumina/manta
+Version: v1.6.0 (Released on Jul 9, 2019)
+GitHub Package: ghcr.io/uclahs-cds/manta:1.6.0
+##### Strelka2
+Strelka2 source: https://github.com/Illumina/strelka
+Version: v2.9.10 (Released on Nov 7, 2018)
+GitHub Package: ghcr.io/uclahs-cds/strelka2:2.9.10
+
+### Mutect2
+![alt text](mutect2_chart.svg)
+#### Tools
+##### GATK
+GATK source: https://github.com/broadinstitute/gatk
+Version: 4.2.4.1 (Released on Jan 4, 2022)
+Docker Image: broadinstitute/gatk:4.2.4.1
+
+### MuSE
+![alt text](muse_chart.svg?raw=true)
+#### Tools
+##### MuSE
+MuSE source: https://github.com/wwylab/MuSE
+Version: 2.0 (Released on Aug 25, 2021)
+GitHub Package: https://github.com/uclahs-cds/docker-MuSE/pkgs/container/muse
+
+## Variant Intersection
+![alt text](intersect_chart.svg?raw=true)
+#### Tools
+##### BCFtools
+BCFtools source: https://samtools.github.io/bcftools
+Version: 1.17 (Released on Feb 21, 2023)
+GitHub Package: https://github.com/uclahs-cds/bcftools:1.17
+##### VennDiagram
+VennDiagram source: https://github.com/uclahs-cds/public-R-VennDiagram
+Version: 1.7.3 (Released on Apr 12, 2022)
+##### vcf2maf
+vcf2maf source: ghcr.io/mskcc/vcf2maf/vcf2maf
+Version: v1.6.18
+GitHub Package: https://github.com/mskcc/vcf2maf

docs/intersect_flowchart.puml

@@ -0,0 +1,34 @@
+@startuml intersect_chart
+
+!include pipeline_elements.iuml!string_functions
+!include pipeline_elements.iuml!input_rect
+!include pipeline_elements.iuml!output_rect
+!include pipeline_elements.iuml!intermediate_rect
+!include pipeline_elements.iuml!qc_rect
+!include pipeline_elements.iuml!test_rect
+!include pipeline_elements.iuml!process_legend
+
+skinparam linetype ortho
+
+$test_process(num_algos, '', 'Results from two or more algorithms?')
+$input_process(input_vcfs, 'filtered VCFs', 'Input: VCFs for all selected algorithms')
+$output_process(done, 'Exit', 'Intersect is only run if two or %newline()more algorithms were selected')
+
+$intermediate_process(intersect_vcfs_2, "BCFtools isec -n +2", "Output: SNVs found by 2 or more algorithms: %newline()* 1 VCF per algorithm %newline() * list of SNVS (README.txt, sites.txt)")
+$intermediate_process(intersect_vcfs_1, "BCFtools isec -n +1", "Output: All SNVs, including private: %newline() * list of SNVS (README.txt, sites.txt)")
+
+$output_process(plot_venn, 'VennDiagram', 'Output: plot in TIFF format showing %newline()intersection counts for all SNVs')
+$output_process(concat_vcfs, 'BCFtools concat', 'Output: Single VCF with all SNVs %newline()found by 2 or more algorithms')
+$output_process(vcf2maf, 'vcf2maf', 'Output: Single MAF with all SNVs %newline()found by 2 or more algorithms: %newline()//SNV-concat.maf.gz//')
+
+num_algos -d-> input_vcfs: true
+num_algos -d-> done: false
+input_vcfs -d-> intersect_vcfs_2
+input_vcfs -d-> intersect_vcfs_1
+intersect_vcfs_1 -d-> plot_venn
+intersect_vcfs_2 -d-> concat_vcfs: // SNV-concensus-variants.vcf.gz //
+concat_vcfs -d-> vcf2maf: // SNV-concat.vcf.gz //
+
+$add_legend("right")
+
+@enduml

docs/muse_flowchart.puml

@@ -15,13 +15,13 @@ $input_process(tumor_bam, 'Tumor BAM', 'Input: tumor BAM file')
 $intermediate_process(muse_call_run, "MuSE call", "Output: position-specific %newline()summary statistics")
 $input_process(dbsnp_file, 'dbSNP', 'Input: dbSNP VCF')
 $intermediate_process(muse_sump_run, "MuSE sump", "Output: VCF with tier-based %newline()quality cutoffs")
-$output_process(filter_vcf, 'Filter VCF', 'Output: VCF with top tier %newline()somatic variants')
+$output_process(filter_vcf, 'Filter VCF', 'Output: VCF with top tier %newline()somatic variants: %newline()//SNV.vcf.gz//')
 
 tumor_bam -d-> muse_call_run
 normal_bam -d-> muse_call_run
-muse_call_run -d-> muse_sump_run
+muse_call_run -d-> muse_sump_run: // MuSE.txt //
 dbsnp_file -d-> muse_sump_run
-muse_sump_run -d-> filter_vcf
+muse_sump_run -d-> filter_vcf: // raw.vcf //
 
 $add_legend("left")
 

docs/mutect2_flowchart.puml

@@ -21,8 +21,8 @@ $intermediate_process(gatk_mergeVcfs, 'GATK MergeVcfs', 'Output: unfiltered VCF'
 $intermediate_process(mutect2_mergeStats, 'GATK MergeMutectStats', 'Output: Mutect2 stats')
 $intermediate_process(gatk_learnReadOrientation, 'GATK LearnReadOrientationModel', 'Output: orientation bias artifacts table')
 $intermediate_process(mutect2_filterCalls, 'GATK FilterMutectCalls', 'Output: VCF with non-PASSing variants tagged %newline()Optional output: filtering stats')
-$output_process(bcftools_filterVCF, 'remove non-PASS variants', 'Output: VCF including only variants that passed above filters')
-$output_process(bcftools_splitVCF, 'split by variant type', 'Output: %newline()pass-snvs.vcf.gz %newline()pass-mnvs.vcf.gz %newline()pass-indels.vcf.gz')
+$intermediate_process(bcftools_filterVCF, 'remove non-PASS variants', 'Output: VCF including only variants that passed above filters')
+$output_process(bcftools_splitVCF, 'split by variant type', 'Output: %newline()//SNV.vcf.gz // %newline()//MNV.vcf.gz // %newline()//Indel.vcf.gz //')
 $qc_process(gatk_filteringStats, 'Optional', 'Output: filteringStats.tsv')
 
 reference_genome -d-> gatk_splitIntervals
@@ -40,14 +40,14 @@ mutect2_call_sSNV -d-> mutect2_mergeStats
 mutect2_call_sSNV -d-> gatk_learnReadOrientation
 mutect2_call_sSNV -d-> mutect2_mergeStats
 
-gatk_mergeVcfs -d-> mutect2_filterCalls : // unfiltered.vcf.gz //
+gatk_mergeVcfs -d-> mutect2_filterCalls : //unfiltered.vcf.gz//
 gatk_learnReadOrientation -d-> mutect2_filterCalls : // f1r2.tar.gz //
 mutect2_mergeStats -d-> mutect2_filterCalls : // unfiltered.vcf.stats.gz //
 reference_genome -d-> mutect2_filterCalls
 contamination_table -d-> mutect2_filterCalls
 mutect2_filterCalls -d-> gatk_filteringStats
 mutect2_filterCalls -d-> bcftools_filterVCF : // filtered.vcf.gz //
-bcftools_filterVCF -d-> bcftools_splitVCF : // pass.vcf.gz //
+bcftools_filterVCF -d-> bcftools_splitVCF : // all-pass.vcf.gz //
 
 $add_legend('left')
 

docs/pipeline_elements.iuml

@@ -44,6 +44,13 @@ $description"
 !endprocedure
 @enduml
 
+@startuml(id=test_rect)
+!unquoted procedure $test_process($alias, $title $description)
+rectangle $alias #Orange as "
+$description"
+!endprocedure
+@enduml
+
 @startuml(id=process_legend)
 !unquoted procedure $add_legend($pos="bottom right")
 legend $pos

metadata.yaml

@@ -5,4 +5,4 @@ Maintainers: ['[email protected]']
 Contributors: ['Mao Tian', 'Bugh Caden', 'Helena Winata', 'Yash Patel', 'Sorel Fitz-Gibbon']
 Languages: ['Docker', 'Nextflow']
 Dependencies: ['Docker', 'Nextflow']
-Tools: ['GATK 4.4.0.0', 'SomaticSniper v1.0.5.0', 'SAMtools v1.16.1', 'Strelka2 v2.9.10', 'Manta v1.6.0', 'MuSE v2.0.2', BCFtools v1.17]
+Tools: ['GATK 4.4.0.0', 'SomaticSniper v1.0.5.0', 'SAMtools v1.16.1', 'Strelka2 v2.9.10', 'Manta v1.6.0', 'MuSE v2.0.2', 'BCFtools v1.17', 'R v4.3.1', 'VennDiagram v1.7.3', 'vcf2maf v1.6.18']

module/intersect-processes.nf

@@ -32,8 +32,8 @@ process intersect_VCFs_BCFtools {
     path intersect_regions_index
 
     output:
-    path "*.vcf.gz", emit: consensus_vcf
-    path "*.vcf.gz.tbi", emit: consensus_idx
+    path "*.vcf.gz", emit: intersect_vcf
+    path "*.vcf.gz.tbi", emit: intersect_idx
     path ".command.*"
     path "isec-2-or-more/*.txt"
     path "isec-1-or-more/*.txt", emit: isec
@@ -51,7 +51,7 @@ process intersect_VCFs_BCFtools {
         ${regions_command} \
         ${vcf_list}
     awk '/Using the following file names:/{x=1;next} x' isec-2-or-more/README.txt  \
-        | sed 's/.vcf.gz\$/-consensus-variants.vcf.gz/' \
+        | sed 's/.vcf.gz\$/-intersect.vcf.gz/' \
         | while read a b c d; do
             mv \$a \$d
             mv \$a.tbi \$d.tbi

module/intersect.nf

@@ -36,11 +36,11 @@ workflow intersect {
             script_dir_ch,
             intersect_VCFs_BCFtools.out.isec,
             )
-        consensus_vcfs_ch = intersect_VCFs_BCFtools.out.consensus_vcf
+        intersect_vcfs_ch = intersect_VCFs_BCFtools.out.intersect_vcf
             .map { sortVcfs(it) }
         concat_VCFs_BCFtools(
-            consensus_vcfs_ch,
-            intersect_VCFs_BCFtools.out.consensus_idx
+            intersect_vcfs_ch,
+            intersect_VCFs_BCFtools.out.intersect_idx
             )
         convert_VCF_vcf2maf(
             concat_VCFs_BCFtools.out.concat_vcf,
@@ -52,10 +52,10 @@ workflow intersect {
             .map{ it -> ['SNV', it]}
             )
         compress_MAF_vcf2maf(convert_VCF_vcf2maf.out.concat_maf)
-        file_for_sha512 = intersect_VCFs_BCFtools.out.consensus_vcf
+        file_for_sha512 = intersect_VCFs_BCFtools.out.intersect_vcf
             .flatten()
             .map{ it -> ["${file(it).getName().split('_')[0]}-SNV-vcf", it]}
-            .mix(intersect_VCFs_BCFtools.out.consensus_idx
+            .mix(intersect_VCFs_BCFtools.out.intersect_idx
                 .flatten()
                 .map{ it -> ["${file(it).getName().split('_')[0]}-SNV-idx", it]}
                 )

module/strelka2-processes.nf

@@ -77,7 +77,7 @@ process call_sSNV_Strelka2 {
 
     output:
     tuple val("SNV"), path("StrelkaSomaticWorkflow/results/variants/somatic.snvs.vcf.gz"), emit: snvs_vcf
-    tuple val("INDEL"), path("StrelkaSomaticWorkflow/results/variants/somatic.indels.vcf.gz"), emit: indels_vcf
+    tuple val("Indel"), path("StrelkaSomaticWorkflow/results/variants/somatic.indels.vcf.gz"), emit: indels_vcf
     path "StrelkaSomaticWorkflow"
     path ".command.*"
 

test/config/a_mini-all-tools.config

@@ -17,7 +17,7 @@ params {
     dataset_id = 'TWGSAMIN'
      // setting params.exome to TRUE will add the '--exome' option when running manta and strelka2 and the -E option when running MuSE
     exome = false
-    save_intermediate_files = false
+    save_intermediate_files = true
 
     // module options
     bgzip_extra_args = ''

test/config/a_mini-muse.config

@@ -24,8 +24,21 @@ params {
     bgzip_extra_args = ''
     tabix_extra_args = ''
 
+    // mutect2 options
+    split_intervals_extra_args = ''
+    mutect2_extra_args = ''
+    filter_mutect_calls_extra_args = ''
+    gatk_command_mem_diff = 500.MB
+    scatter_count = 12
+    germline_resource_gnomad_vcf = '/hot/ref/tool-specific-input/GATK/GRCh38/af-only-gnomad.hg38.vcf.gz'
+
     // MuSE options
     dbSNP = '/hot/ref/database/dbSNP-155/original/GRCh38/GCF_000001405.39.gz'
+
+    // Intersect options
+    ncbi_build = 'GRCh38'
+    vcf2maf_extra_args = ''
+
 }
 
 methods.setup()

test/config/a_mini-mutect2.config

@@ -29,8 +29,15 @@ params {
     mutect2_extra_args = ''
     filter_mutect_calls_extra_args = ''
     gatk_command_mem_diff = 500.MB
-    scatter_count = 4
+    scatter_count = 12
     germline_resource_gnomad_vcf = '/hot/ref/tool-specific-input/GATK/GRCh38/af-only-gnomad.hg38.vcf.gz'
+
+    // MuSE options
+    dbSNP = '/hot/ref/database/dbSNP-155/original/GRCh38/GCF_000001405.39.gz'
+
+    // Intersect options
+    ncbi_build = 'GRCh38'
+    vcf2maf_extra_args = ''
 }
 
 methods.setup()

test/config/a_mini-somaticsniper.config

@@ -23,6 +23,21 @@ params {
     // module options
     bgzip_extra_args = ''
     tabix_extra_args = ''
+
+    // mutect2 options
+    split_intervals_extra_args = ''
+    mutect2_extra_args = ''
+    filter_mutect_calls_extra_args = ''
+    gatk_command_mem_diff = 500.MB
+    scatter_count = 12
+    germline_resource_gnomad_vcf = '/hot/ref/tool-specific-input/GATK/GRCh38/af-only-gnomad.hg38.vcf.gz'
+
+    // MuSE options
+    dbSNP = '/hot/ref/database/dbSNP-155/original/GRCh38/GCF_000001405.39.gz'
+
+    // Intersect options
+    ncbi_build = 'GRCh38'
+    vcf2maf_extra_args = ''
 }
 
 methods.setup()

test/config/a_mini-strelka2.config

@@ -23,6 +23,21 @@ params {
     // module options
     bgzip_extra_args = ''
     tabix_extra_args = ''
+
+    // mutect2 options
+    split_intervals_extra_args = ''
+    mutect2_extra_args = ''
+    filter_mutect_calls_extra_args = ''
+    gatk_command_mem_diff = 500.MB
+    scatter_count = 12
+    germline_resource_gnomad_vcf = '/hot/ref/tool-specific-input/GATK/GRCh38/af-only-gnomad.hg38.vcf.gz'
+
+    // MuSE options
+    dbSNP = '/hot/ref/database/dbSNP-155/original/GRCh38/GCF_000001405.39.gz'
+
+    // Intersect options
+    ncbi_build = 'GRCh38'
+    vcf2maf_extra_args = ''
 }
 
 methods.setup()