From 0d542db737f74391e6dc4ea346197d0cb8945718 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Wed, 23 Nov 2022 21:50:51 +0000 Subject: [PATCH 01/32] annot --- {cwl => descriptions/cwl}/ascat.cwl | 0 {cwl => descriptions/cwl}/workflow_ascat.cwl | 0 descriptions/driver_catalog.cwl | 57 ++++++ descriptions_temp/ascat.cwl | 95 +++++++++ descriptions_temp/workflow_ascat.cwl | 81 ++++++++ dockerfiles/genomic_ranges/Dockerfile | 44 +++++ .../genomic_ranges/scripts/driver_catalog.sh | 33 ++++ .../scripts/postprocess_ascat.R | 185 ++++++++++++++++++ portal_objects/file_reference.yaml | 39 ++++ portal_objects/metaworkflows/ascat.yaml | 140 +++++++++++++ portal_objects/software.yaml | 18 ++ portal_objects/workflows/ascat.yaml | 59 ++++++ portal_objects/workflows/driver_catalog.yaml | 38 ++++ 13 files changed, 789 insertions(+) rename {cwl => descriptions/cwl}/ascat.cwl (100%) rename {cwl => descriptions/cwl}/workflow_ascat.cwl (100%) create mode 100644 descriptions/driver_catalog.cwl create mode 100644 descriptions_temp/ascat.cwl create mode 100644 descriptions_temp/workflow_ascat.cwl create mode 100644 dockerfiles/genomic_ranges/Dockerfile create mode 100644 dockerfiles/genomic_ranges/scripts/driver_catalog.sh create mode 100644 dockerfiles/genomic_ranges/scripts/postprocess_ascat.R create mode 100644 portal_objects/file_reference.yaml create mode 100644 portal_objects/metaworkflows/ascat.yaml create mode 100644 portal_objects/software.yaml create mode 100644 portal_objects/workflows/ascat.yaml create mode 100644 portal_objects/workflows/driver_catalog.yaml diff --git a/cwl/ascat.cwl b/descriptions/cwl/ascat.cwl similarity index 100% rename from cwl/ascat.cwl rename to descriptions/cwl/ascat.cwl diff --git a/cwl/workflow_ascat.cwl b/descriptions/cwl/workflow_ascat.cwl similarity index 100% rename from cwl/workflow_ascat.cwl rename to descriptions/cwl/workflow_ascat.cwl diff --git a/descriptions/driver_catalog.cwl b/descriptions/driver_catalog.cwl new file mode 100644 index 0000000..80b7acc --- /dev/null +++ b/descriptions/driver_catalog.cwl @@ -0,0 +1,57 @@ +#!/usr/bin/env cwl-runner + +cwlVersion: v1.0 + +class: CommandLineTool + +requirements: + - class: InlineJavascriptRequirement + +hints: + - class: DockerRequirement + dockerPull: ACCOUNT/genomic_ranges:VERSION + +baseCommand: [driver_catalog.sh] + +inputs: + - id: ascat + type: File + inputBinding: + prefix: "--ascat" + doc: TODO + + - id: gene_panel + type: File + inputBinding: + prefix: "--gene_panel" + doc: TODO + - id: cgap_genes + type: File + inputBinding: + prefix: "--cgap_genes" + doc: TODO + + - id: ascat_objects + type: File + inputBinding: + prefix: "--ascat_objects" + doc: TODO + + - id: output + type: string + inputBinding: + prefix: "--output" + default: putative_drivers_CNV_ASCAT.tsv + doc: TODO + + + +outputs: + - id: putative_drivers + type: File + outputBinding: + glob: putative_drivers_CNV_ASCAT.tsv.gz + + +doc: | + run driver_catalog.sh \ No newline at end of file diff --git a/descriptions_temp/ascat.cwl b/descriptions_temp/ascat.cwl new file mode 100644 index 0000000..fdcfdcd --- /dev/null +++ b/descriptions_temp/ascat.cwl @@ -0,0 +1,95 @@ +#!/usr/bin/env cwl-runner + +cwlVersion: v1.0 + +class: CommandLineTool + +requirements: + - class: InlineJavascriptRequirement + +hints: + - class: DockerRequirement + dockerPull: ACCOUNT/ascat:VERSION + +baseCommand: [run_ascat.sh] + +inputs: + - id: tumor_file + type: File + inputBinding: + prefix: "--tumor_file" + secondaryFiles: + - .bai + doc: tumor sample BAM file + + - id: normal_file + type: File + inputBinding: + prefix: "--normal_file" + secondaryFiles: + - .bai + doc: normal sample BAM file + + - id: gender + type: string + inputBinding: + prefix: "--gender" + doc: gender + + - id: nthreads + type: int + default: 23 + inputBinding: + prefix: "--nthreads" + doc: number of threads used to run ascat + + - id: reference_data + type: File + inputBinding: + prefix: "--reference_data" + doc: tar file of loci, alleles and GC correction files + +outputs: + - id: BAF_LogR_tumor_germline + type: File + outputBinding: + glob: BAF_LogR_tumor_germline.tsv.gz + - id: after_correction_tumor_germline + type: File + outputBinding: + glob: After_correction_tumor.germline.png + - id: after_correction_tumor_tumour + type: File + outputBinding: + glob: After_correction_tumor.tumour.png + - id: before_correction_tumor_tumour + type: File + outputBinding: + glob: Before_correction_tumor.tumour.png + - id: tumor_ASCATprofile + type: File + outputBinding: + glob: tumor.ASCATprofile.png + - id: tumor_ASPCF + type: File + outputBinding: + glob: tumor.ASPCF.png + - id: tumor_rawprofile + type: File + outputBinding: + glob: tumor.rawprofile.png + - id: tumor_sunrise + type: File + outputBinding: + glob: tumor.sunrise.png + - id: cnv_ascat + type: File + outputBinding: + glob: cnv_ascat.tsv.gz + - id: ascat_objects + type: File + outputBinding: + glob: ascat_objects.Rdata + +doc: | + run run_ascat.sh diff --git a/descriptions_temp/workflow_ascat.cwl b/descriptions_temp/workflow_ascat.cwl new file mode 100644 index 0000000..e676033 --- /dev/null +++ b/descriptions_temp/workflow_ascat.cwl @@ -0,0 +1,81 @@ +cwlVersion: v1.0 + +class: Workflow + +requirements: + MultipleInputFeatureRequirement: {} + +inputs: + - id: tumor_file + type: File + secondaryFiles: + - .bai + doc: tumor sample BAM file + + - id: normal_file + type: File + secondaryFiles: + - .bai + doc: normal sample BAM file + + - id: gender + type: string + doc: gender + + - id: nthreads + type: int + doc: number of threads used to run ascat + + - id: reference_data + type: File + doc: tar file of loci, alleles and GC correction files + +outputs: + - id: BAF_LogR_tumor_germline + type: File + outputSource: ascat/BAF_LogR_tumor_germline + - id: cnv_ascat + type: File + outputSource: ascat/cnv_ascat + - id: after_correction_tumor_germline + type: File + outputSource: ascat/after_correction_tumor_germline + - id: after_correction_tumor_tumour + type: File + outputSource: ascat/after_correction_tumor_tumour + - id: before_correction_tumor_tumour + type: File + outputSource: ascat/before_correction_tumor_tumour + - id: tumor_ASCATprofile + type: File + outputSource: ascat/tumor_ASCATprofile + - id: tumor_ASPCF + type: File + outputSource: ascat/tumor_ASPCF + - id: tumor_rawprofile + type: File + outputSource: ascat/tumor_rawprofile + - id: tumor_sunrise + type: File + outputSource: ascat/tumor_sunrise + - id: ascat_objects + type: File + outputSource: ascat/ascat_objects + +steps: + ascat: + run: ascat.cwl + in: + tumor_file: + source: tumor_file + normal_file: + source: normal_file + gender: + source: gender + nthreads: + source: nthreads + reference_data: + source: reference_data + out: [BAF_LogR_tumor_germline, tumor_sunrise, tumor_rawprofile, cnv_ascat,tumor_ASPCF, before_correction_tumor_tumour, tumor_ASCATprofile, after_correction_tumor_germline, after_correction_tumor_tumour, ascat_objects] + +doc: run run_ascat.sh diff --git a/dockerfiles/genomic_ranges/Dockerfile b/dockerfiles/genomic_ranges/Dockerfile new file mode 100644 index 0000000..bc6f951 --- /dev/null +++ b/dockerfiles/genomic_ranges/Dockerfile @@ -0,0 +1,44 @@ +####################################################################### +# Basic image +####################################################################### +FROM cgap/cgap-ubuntu2004-py-38:0.0.1 +MAINTAINER Michele Berselli (berselli.michele@gmail.com), Dominika Maziec (dominika_maziec@hms.harvard.edu) + +####################################################################### +# General updates & installing necessary Linux components +# - tabix brings in bgzip and tabix +# - locales for UTF-8 +####################################################################### +####################################################################### +# Software +####################################################################### +#install R +RUN apt-get update && apt-get install -y \ + locales \ + tabix +RUN apt-get install -y --no-install-recommends r-base +RUN apt-get install -y --no-install-recommends r-cran-tidyverse r-cran-optparse r-cran-biocmanager + +#install GenomicRanges +RUN R -e "BiocManager::install('GenomicRanges')" + +####################################################################### +# Setting working env +####################################################################### +WORKDIR /usr/local/bin + +####################################################################### +# Scripts +####################################################################### +COPY scripts/driver_catalog.sh . +RUN chmod +x driver_catalog.sh +COPY scripts/postprocess_ascat.R . + +####################################################################### +# Setting env variables +####################################################################### +## Supporting UTF-8 +RUN locale-gen "en_US.UTF-8" && update-locale LC_ALL="en_US.UTF-8" +ENV LC_ALL=en_US.UTF-8 + +CMD ["bash"] diff --git a/dockerfiles/genomic_ranges/scripts/driver_catalog.sh b/dockerfiles/genomic_ranges/scripts/driver_catalog.sh new file mode 100644 index 0000000..ffb8019 --- /dev/null +++ b/dockerfiles/genomic_ranges/scripts/driver_catalog.sh @@ -0,0 +1,33 @@ +#!/bin/bash + +WORKDIR="/usr/local/bin" + +while [ "$1" != "" ]; do + case $1 in + --ascat) + shift + ascat=$1 + ;; + --gene_panel) + shift + gene_panel=$1 + ;; + --cgap_genes) + shift + cgap_genes=$1 + ;; + --ascat_objects) + shift + ascat_objects=$1 + ;; + --output) + shift + output=$1 + ;; + esac + shift +done + + +Rscript $WORKDIR/postprocess_ascat.R --ascat $ascat --ascat_objects $ascat_objects --gene_panel $gene_panel --cgap_genes $cgap_genes --output $output || exit 1 +gzip $output || exit 1 diff --git a/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R b/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R new file mode 100644 index 0000000..2087e17 --- /dev/null +++ b/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R @@ -0,0 +1,185 @@ +library(GenomicRanges) +library(dplyr) +library(tidyverse) +library(optparse) + +option_list <- list( + make_option( + c("--ascat"), + action = "store", + type = "character", + help = "" + ), + + make_option( + c("--gene_panel"), + action = "store", + type = "character", + help = "" + ), + + make_option( + c("--cgap_genes"), + type = "character", + action = "store", + help = "" + ), + make_option( + c("--output"), + type = "character", + action = "store", + help = "" + ), + make_option( + c("--ascat_objects"), + type = "character", + action = "store", + help = "" + ) +) + +opt = parse_args(OptionParser(option_list = option_list)) +# loading ascat results +ascat_table <- + read.table( + gzfile(opt$ascat), + header = TRUE, + sep = '\t' + ) + + +#loading gene panel from Hartwig +driver_gene_panel <- + read.table(gzfile(opt$gene_panel), + header = TRUE, + sep = '\t') + +# create cnvs genomic ranges obj +ascat.gr <- GRanges( + seqnames = Rle(paste0('chr', ascat_table$chr)), + ranges = IRanges(ascat_table$startpos, ascat_table$endpos), + strand = rep(c("*"), nrow(ascat_table)) +) + +ascat.gr$total.cn <- ascat_table$copyNumber +ascat.gr$minor.cn <- ascat_table$nMinor +ascat.gr$major.cn <- ascat_table$nMajor + + +#genes from CGAP +gene_table <- read.table(gzfile(opt$cgap_genes), + sep = '\t', + header = TRUE) + +# create genes genomic ranges obj +genes.gr <- GRanges( + seqnames = Rle(paste0('chr', gene_table$chr)), + ranges = IRanges(gene_table$start, gene_table$end), + strand = gene_table$strand +) + + +#finding overlaps +overlap.df <- as.data.frame(findOverlaps(genes.gr, ascat.gr)) + + +gene_table$ID_gene <- seq.int(nrow(gene_table)) +ascat_table$ID_cv <- seq.int(nrow(ascat_table)) + + +overlap.df <- overlap.df %>% + rename(ID_gene = queryHits, + ID_cv = subjectHits) + + + +# left join : overlaps with ascat table by ID_cv to to find copy numbers in each region +overlap.df <- + merge(x = overlap.df, + y = ascat_table, + by = "ID_cv", + all.x = TRUE) + + + +# group by ID_gene to check what is the minimum and maximum value of cnvs in each gene +grouped <- overlap.df %>% group_by(ID_gene) %>% + summarise(max_subjectHits = max(copyNumber), + min_subjectHits = min(copyNumber)) + + +#final <- merge(x=gene_table,y=grouped,by="ID_gene", all.x=TRUE) %>% +# replace(is.na(.), 2) # can I do this???? we have all the genes including those that do not contain CNVs + +# inner join with genes from CGAP to find names of the genes, ID gene stores only index +final <- + merge(x = gene_table, y = grouped, by = "ID_gene") # we have genes that we found some CNVs in + + + + +# merge with panel by gene symbol to query the decision tree +final <- + merge(x = final, y = driver_gene_panel, by = 'gene') #merges only common genes + +#loading ascat objects to check ploidy +load(opt$ascat_objects) +ploidy <- ascat.output$ploidy +check_ploidy <- 3 * ploidy + + +# for each gene we check if there is amplification and if we should report it +final$amplification <- + ifelse(( + final$min_subjectHits > check_ploidy & + final$reportAmplification == 'TRUE' + ), + TRUE, + FALSE + ) + + +final$partial_amplification <- + ifelse(( + final$max_subjectHits > check_ploidy & + final$reportAmplification == 'TRUE' + ), + TRUE, + FALSE + ) + +final$deletion <- + ifelse(final$min_subjectHits < 0.5 & + final$reportDeletion == 'TRUE', + TRUE, + FALSE) + + + + +#select only relevant fields +final <- + final %>% select( + gene, + chr, + start, + end, + #strand, + max_subjectHits, + min_subjectHits, + amplification, + partial_amplification, + deletion, + ) %>% filter(amplification==TRUE | partial_amplification==TRUE | deletion==TRUE) + +final$category[final$amplification == TRUE | final$partial_amplification == TRUE ] <- "amplification" +final$category[final$deletion==TRUE] <- "deletion" + +final <- final %>% select(gene, + chr, + start, + end, + category) + +write.table(final, file=opt$output, sep='\t',row.names = FALSE, quote=FALSE) + diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml new file mode 100644 index 0000000..b0558e2 --- /dev/null +++ b/portal_objects/file_reference.yaml @@ -0,0 +1,39 @@ +################################################################ +# Datasource for ASCAT +################################################################ +name: ascat_reference_loci_alleles_GC_G1000 +description: Datasource for loci, alleles and GC correction files from G1000/ASCAT. +format: tar_gz +version: hg38 +uuid: 7a33ce65-80f4-4c65-8229-8c2bbe0c1445 +accession: GAPFI6BNMYRO + +--- + +################################################################ +# Datasource for the driver catalog +################################################################ +name: cgap_genes +description: Datasource for genes supported by CGAP in a tabular format +format: tsv_gz +version: hg38 +uuid: 335f7c0f-640e-44b9-a0da-bbe2728f782c +accession: GAPFI6BQNY5O + +--- + +name: gene_panel_hartwig +description: Configuration file of which genes to add to the driver catalog +format: tsv_gz +version: hg38 +uuid: bd334693-b83e-4709-9d96-d8cc3f524848 +accession: GAPFI6BNWA1O + +--- + +name: somatic_hotspot_mutations +description: todo +format: vcf_gz +version: hg38 +uuid: 19f548db-5491-464c-babd-a9f4f0b2c8c4 +accession: GAPFI6BNWA90 \ No newline at end of file diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/ascat.yaml new file mode 100644 index 0000000..e94c23b --- /dev/null +++ b/portal_objects/metaworkflows/ascat.yaml @@ -0,0 +1,140 @@ +## Pipeline information ##################################### +# General information for the pipeline +############################################################# +name: WGS_CNV_somatic_ascat +description: Call CNV on tumor-normal samples with ASCAT | + Prioritize somatic mutations + +## General arguments ######################################## +# Pipeline input, reference files, and general arguments +# define all arguments for the pipeline here +############################################################# +input: + + tumor_file: + argument_type: file.bam + dimensionality: 1 + + normal_file: + argument_type: file.bam + dimensionality: 1 + + gender: + argument_type: parameter.string + + nthreads: + argument_type: parameter.integer + + reference_data: + argument_type: file.tar_gz + files: + - ascat_reference_loci_alleles_GC_G1000@hg38 + cgap_genes: + argument_type: file.tsv_gz + files: + - cgap_genes@hg38 + gene_panel: + argument_type: file.tsv_gz + files: + - gene_panel_hartwig@hg38 + + +## Workflows and dependencies ############################### +# Information for the workflows and their dependencies +############################################################# +workflows: + + ## Workflow definition ##################### + # cram2fastq + ############################################ + ascat: + + ## Workflow arguments ############## + #################################### + input: + + tumor_file: + argument_type: file.bam + input_dimension: 1 + + normal_file: + argument_type: file.bam + input_dimension: 1 + + gender: + argument_type: parameter.string + + nthreads: + argument_type: parameter.integer + value: "23" + + reference_data: + argument_type: file.tar_gz + + ## Output ########################## + #################################### + output: + + BAF_LogR_tumor_germline: + file_type: tsv + description: BAF and LogR for the germline sample + after_correction_tumor_germline: + file_type: png + description: correctected LogR of the tumor sample with genomic GC content + after_correction_tumor_tumour: + file_type: png + before_correction_tumor_tumour: + file_type: png + tumor_ASCATprofile: + file_type: png + tumor_ASPCF: + file_type: png + tumor_rawprofile: + file_type: png + tumor_sunrise: + file_type: png + cnv_ascat: + file_type: tsv_gz + ascat_objects: + file_type: Rdata + + + ## EC2 Configuration to use ######## + #################################### + config: + instance_type: + - c5.4xlarge + ebs_size: 1.5x + EBS_optimized: True + spot_instance: False + run_name: run_workflow_ascat + behavior_on_capacity_limit: wait_and_retry + driver_catalog: + input: + ascat: + argument_type: file.tsv_gz + source: ascat + source_argument_name: cnv_ascat + ascat_objects: + argument_type: file.Rdata + source: ascat + source_argument_name: ascat_objects + cgap_genes: + argument_type: file.tsv_gz + gene_panel: + argument_type: file.tsv_gz + + output: + putative_drivers: + file_type: tsv_gz + + config: + instance_type: + - t3.xlarge + ebs_size: 1.5x + EBS_optimized: True + spot_instance: False + run_name: run_driver_catalog + behavior_on_capacity_limit: wait_and_retry + + diff --git a/portal_objects/software.yaml b/portal_objects/software.yaml new file mode 100644 index 0000000..2ecee1a --- /dev/null +++ b/portal_objects/software.yaml @@ -0,0 +1,18 @@ + +################################################################ +# ASCAT, v3.0.0 +################################################################ +name: ascat +version: 3.0.0 +source_url: https://github.com/VanLoo-lab/ascat + +--- + +################################################################ +# cancerit-allelecount, v4.3.0 +################################################################ +name: cancerit-allelecount +version: 4.3.0 +source_url: https://anaconda.org/bioconda/cancerit-allelecount + + diff --git a/portal_objects/workflows/ascat.yaml b/portal_objects/workflows/ascat.yaml new file mode 100644 index 0000000..66eefcf --- /dev/null +++ b/portal_objects/workflows/ascat.yaml @@ -0,0 +1,59 @@ +## Workflow information ##################################### +# General information for the workflow +############################################################# +name: ascat +description: Run CNV analysis with ASCAT + +runner: + language: cwl + main: workflow_ascat.cwl + child: + - ascat.cwl + +software: + - ascat@3.0.0 + - cancerit-allelecount@4.3.0 + +## Input information ######################################## +# Input files and parameters +############################################################# +input: + + tumor_file: + argument_type: file.bam + + normal_file: + argument_type: file.bam + + gender: + argument_type: parameter.string + + nthreads: + argument_type: parameter.string + + +## Output information ####################################### +# Output files +############################################################# +output: + + BAF_LogR_tumor_germline: + argument_type: file.tsv_gz + after_correction_tumor_germline: + argument_type: file.png + after_correction_tumor_tumour: + argument_type: file.png + before_correction_tumor_tumour: + argument_type: file.png + tumor_ASCATprofile: + argument_type: file.png + tumor_ASPCF: + argument_type: file.png + tumor_rawprofile: + argument_type: file.png + tumor_sunrise: + argument_type: file.png + cnv_ascat: + argument_type: file.tsv_gz + ascat_objects: + argument_type: file.Rdata \ No newline at end of file diff --git a/portal_objects/workflows/driver_catalog.yaml b/portal_objects/workflows/driver_catalog.yaml new file mode 100644 index 0000000..d3d4b19 --- /dev/null +++ b/portal_objects/workflows/driver_catalog.yaml @@ -0,0 +1,38 @@ +# Workflow information ##################################### +# General information for the workflow +############################################################# +name: driver_catalog +description: Run CNV analysis with ASCAT + +runner: + language: cwl + main: driver_catalog.cwl + + + +## Input information ######################################## +# Input files and parameters +############################################################# +input: + + ascat: + argument_type: file.tsv_gz + + gene_panel: + argument_type: file.tsv_gz + + cgap_genes: + argument_type: file.tsv_gz + + ascat_objects: + argument_type: file.Rdata + + +## Output information ####################################### +# Output files +############################################################# +output: + + putative_drivers: + argument_type: file.tsv_gz + \ No newline at end of file From de0454ddf1c270824533a22c10bb0755a2c30147 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Tue, 29 Nov 2022 15:58:28 +0000 Subject: [PATCH 02/32] . --- descriptions/driver_catalog.cwl | 16 ++-- descriptions_temp/ascat.cwl | 95 ------------------- descriptions_temp/workflow_ascat.cwl | 81 ---------------- .../scripts/postprocess_ascat.R | 28 ++---- 4 files changed, 17 insertions(+), 203 deletions(-) delete mode 100644 descriptions_temp/ascat.cwl delete mode 100644 descriptions_temp/workflow_ascat.cwl diff --git a/descriptions/driver_catalog.cwl b/descriptions/driver_catalog.cwl index 80b7acc..53a3f8a 100644 --- a/descriptions/driver_catalog.cwl +++ b/descriptions/driver_catalog.cwl @@ -18,40 +18,38 @@ inputs: type: File inputBinding: prefix: "--ascat" - doc: TODO + doc: tsv file containing ASCAT CNVs - id: gene_panel type: File inputBinding: prefix: "--gene_panel" - doc: TODO + doc: tsv configuration file of which genes to add to the driver catalog from Hartwig Medical Foundation - id: cgap_genes type: File inputBinding: prefix: "--cgap_genes" - doc: TODO + doc: tsv file of genes available on CGAP - id: ascat_objects type: File inputBinding: prefix: "--ascat_objects" - doc: TODO - + doc: ascat objects from the CGAP SV somatic pipeline (ASCAT) + - id: output type: string inputBinding: prefix: "--output" default: putative_drivers_CNV_ASCAT.tsv - doc: TODO - - + doc: output file name outputs: - id: putative_drivers type: File outputBinding: glob: putative_drivers_CNV_ASCAT.tsv.gz - + doc: tsv file containing reported putative drivers doc: | run driver_catalog.sh \ No newline at end of file diff --git a/descriptions_temp/ascat.cwl b/descriptions_temp/ascat.cwl deleted file mode 100644 index fdcfdcd..0000000 --- a/descriptions_temp/ascat.cwl +++ /dev/null @@ -1,95 +0,0 @@ -#!/usr/bin/env cwl-runner - -cwlVersion: v1.0 - -class: CommandLineTool - -requirements: - - class: InlineJavascriptRequirement - -hints: - - class: DockerRequirement - dockerPull: ACCOUNT/ascat:VERSION - -baseCommand: [run_ascat.sh] - -inputs: - - id: tumor_file - type: File - inputBinding: - prefix: "--tumor_file" - secondaryFiles: - - .bai - doc: tumor sample BAM file - - - id: normal_file - type: File - inputBinding: - prefix: "--normal_file" - secondaryFiles: - - .bai - doc: normal sample BAM file - - - id: gender - type: string - inputBinding: - prefix: "--gender" - doc: gender - - - id: nthreads - type: int - default: 23 - inputBinding: - prefix: "--nthreads" - doc: number of threads used to run ascat - - - id: reference_data - type: File - inputBinding: - prefix: "--reference_data" - doc: tar file of loci, alleles and GC correction files - -outputs: - - id: BAF_LogR_tumor_germline - type: File - outputBinding: - glob: BAF_LogR_tumor_germline.tsv.gz - - id: after_correction_tumor_germline - type: File - outputBinding: - glob: After_correction_tumor.germline.png - - id: after_correction_tumor_tumour - type: File - outputBinding: - glob: After_correction_tumor.tumour.png - - id: before_correction_tumor_tumour - type: File - outputBinding: - glob: Before_correction_tumor.tumour.png - - id: tumor_ASCATprofile - type: File - outputBinding: - glob: tumor.ASCATprofile.png - - id: tumor_ASPCF - type: File - outputBinding: - glob: tumor.ASPCF.png - - id: tumor_rawprofile - type: File - outputBinding: - glob: tumor.rawprofile.png - - id: tumor_sunrise - type: File - outputBinding: - glob: tumor.sunrise.png - - id: cnv_ascat - type: File - outputBinding: - glob: cnv_ascat.tsv.gz - - id: ascat_objects - type: File - outputBinding: - glob: ascat_objects.Rdata - -doc: | - run run_ascat.sh diff --git a/descriptions_temp/workflow_ascat.cwl b/descriptions_temp/workflow_ascat.cwl deleted file mode 100644 index e676033..0000000 --- a/descriptions_temp/workflow_ascat.cwl +++ /dev/null @@ -1,81 +0,0 @@ -cwlVersion: v1.0 - -class: Workflow - -requirements: - MultipleInputFeatureRequirement: {} - -inputs: - - id: tumor_file - type: File - secondaryFiles: - - .bai - doc: tumor sample BAM file - - - id: normal_file - type: File - secondaryFiles: - - .bai - doc: normal sample BAM file - - - id: gender - type: string - doc: gender - - - id: nthreads - type: int - doc: number of threads used to run ascat - - - id: reference_data - type: File - doc: tar file of loci, alleles and GC correction files - -outputs: - - id: BAF_LogR_tumor_germline - type: File - outputSource: ascat/BAF_LogR_tumor_germline - - id: cnv_ascat - type: File - outputSource: ascat/cnv_ascat - - id: after_correction_tumor_germline - type: File - outputSource: ascat/after_correction_tumor_germline - - id: after_correction_tumor_tumour - type: File - outputSource: ascat/after_correction_tumor_tumour - - id: before_correction_tumor_tumour - type: File - outputSource: ascat/before_correction_tumor_tumour - - id: tumor_ASCATprofile - type: File - outputSource: ascat/tumor_ASCATprofile - - id: tumor_ASPCF - type: File - outputSource: ascat/tumor_ASPCF - - id: tumor_rawprofile - type: File - outputSource: ascat/tumor_rawprofile - - id: tumor_sunrise - type: File - outputSource: ascat/tumor_sunrise - - id: ascat_objects - type: File - outputSource: ascat/ascat_objects - -steps: - ascat: - run: ascat.cwl - in: - tumor_file: - source: tumor_file - normal_file: - source: normal_file - gender: - source: gender - nthreads: - source: nthreads - reference_data: - source: reference_data - out: [BAF_LogR_tumor_germline, tumor_sunrise, tumor_rawprofile, cnv_ascat,tumor_ASPCF, before_correction_tumor_tumour, tumor_ASCATprofile, after_correction_tumor_germline, after_correction_tumor_tumour, ascat_objects] - -doc: run run_ascat.sh diff --git a/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R b/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R index 2087e17..ca52c07 100644 --- a/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R +++ b/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R @@ -8,33 +8,35 @@ option_list <- list( c("--ascat"), action = "store", type = "character", - help = "" + help = "tsv file containing ASCAT CNVs" ), make_option( c("--gene_panel"), action = "store", type = "character", - help = "" + help = "tsv configuration file of which genes to add to the driver catalog from Hartwig Medical Foundation" ), make_option( c("--cgap_genes"), type = "character", action = "store", - help = "" + help = "tsv file containing genes supported by CGAP" ), + make_option( c("--output"), type = "character", action = "store", - help = "" + help = "tsv file containing reported putative drivers" ), - make_option( + + make_option( c("--ascat_objects"), type = "character", action = "store", - help = "" + help = "ascat objects from the CGAP SV somatic pipeline (ASCAT) (Rdata format)" ) ) @@ -65,7 +67,6 @@ ascat.gr$total.cn <- ascat_table$copyNumber ascat.gr$minor.cn <- ascat_table$nMinor ascat.gr$major.cn <- ascat_table$nMajor - #genes from CGAP gene_table <- read.table(gzfile(opt$cgap_genes), sep = '\t', @@ -92,7 +93,6 @@ overlap.df <- overlap.df %>% ID_cv = subjectHits) - # left join : overlaps with ascat table by ID_cv to to find copy numbers in each region overlap.df <- merge(x = overlap.df, @@ -108,20 +108,16 @@ grouped <- overlap.df %>% group_by(ID_gene) %>% min_subjectHits = min(copyNumber)) -#final <- merge(x=gene_table,y=grouped,by="ID_gene", all.x=TRUE) %>% -# replace(is.na(.), 2) # can I do this???? we have all the genes including those that do not contain CNVs - # inner join with genes from CGAP to find names of the genes, ID gene stores only index final <- merge(x = gene_table, y = grouped, by = "ID_gene") # we have genes that we found some CNVs in - - # merge with panel by gene symbol to query the decision tree final <- merge(x = final, y = driver_gene_panel, by = 'gene') #merges only common genes + #loading ascat objects to check ploidy load(opt$ascat_objects) ploidy <- ascat.output$ploidy @@ -155,8 +151,6 @@ final$deletion <- FALSE) - - #select only relevant fields final <- final %>% select( @@ -164,7 +158,6 @@ final <- chr, start, end, - #strand, max_subjectHits, min_subjectHits, amplification, @@ -181,5 +174,4 @@ final <- final %>% select(gene, end, category) -write.table(final, file=opt$output, sep='\t',row.names = FALSE, quote=FALSE) - +write.table(final, file=opt$output, sep='\t',row.names = FALSE, quote=FALSE) \ No newline at end of file From 56f7af294484a5aff68fbee1a557f0acf722f6d1 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Fri, 2 Dec 2022 15:06:18 +0000 Subject: [PATCH 03/32] . --- dockerfiles/genomic_ranges/scripts/postprocess_ascat.R | 2 +- portal_objects/file_reference.yaml | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R b/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R index ca52c07..c3d4b76 100644 --- a/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R +++ b/dockerfiles/genomic_ranges/scripts/postprocess_ascat.R @@ -172,6 +172,6 @@ final <- final %>% select(gene, chr, start, end, - category) + category) %>% rename(chrom = chr) #rename it for GosCan write.table(final, file=opt$output, sep='\t',row.names = FALSE, quote=FALSE) \ No newline at end of file diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml index b0558e2..122325d 100644 --- a/portal_objects/file_reference.yaml +++ b/portal_objects/file_reference.yaml @@ -14,7 +14,7 @@ accession: GAPFI6BNMYRO # Datasource for the driver catalog ################################################################ name: cgap_genes -description: Datasource for genes supported by CGAP in a tabular format +description: Datasource for genes supported by CGAP format: tsv_gz version: hg38 uuid: 335f7c0f-640e-44b9-a0da-bbe2728f782c @@ -32,7 +32,7 @@ accession: GAPFI6BNWA1O --- name: somatic_hotspot_mutations -description: todo +description: Datasource for somatic hotspot locations format: vcf_gz version: hg38 uuid: 19f548db-5491-464c-babd-a9f4f0b2c8c4 From 4bdd970f2b74ae79a005be2dc80955cc37a2a19e Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Fri, 9 Dec 2022 14:39:59 +0000 Subject: [PATCH 04/32] . --- descriptions/driver_catalog.cwl | 4 ++-- portal_objects/metaworkflows/ascat.yaml | 2 +- portal_objects/workflows/driver_catalog.yaml | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/descriptions/driver_catalog.cwl b/descriptions/driver_catalog.cwl index 53a3f8a..d3ce8a4 100644 --- a/descriptions/driver_catalog.cwl +++ b/descriptions/driver_catalog.cwl @@ -45,10 +45,10 @@ inputs: doc: output file name outputs: - - id: putative_drivers + - id: putative_drivers_tsv type: File outputBinding: - glob: putative_drivers_CNV_ASCAT.tsv.gz + glob: $(inputs.output) doc: tsv file containing reported putative drivers doc: | diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/ascat.yaml index e94c23b..1217c75 100644 --- a/portal_objects/metaworkflows/ascat.yaml +++ b/portal_objects/metaworkflows/ascat.yaml @@ -125,7 +125,7 @@ workflows: argument_type: file.tsv_gz output: - putative_drivers: + putative_drivers_tsv: file_type: tsv_gz config: diff --git a/portal_objects/workflows/driver_catalog.yaml b/portal_objects/workflows/driver_catalog.yaml index d3d4b19..d2ba6f0 100644 --- a/portal_objects/workflows/driver_catalog.yaml +++ b/portal_objects/workflows/driver_catalog.yaml @@ -33,6 +33,6 @@ input: ############################################################# output: - putative_drivers: + putative_drivers_tsv: argument_type: file.tsv_gz \ No newline at end of file From e6a357cf4793b6ff54633ee27a873af26b3e382a Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Fri, 9 Dec 2022 15:45:41 +0000 Subject: [PATCH 05/32] . --- portal_objects/metaworkflows/ascat.yaml | 2 +- portal_objects/workflows/driver_catalog.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/ascat.yaml index 1217c75..37ee195 100644 --- a/portal_objects/metaworkflows/ascat.yaml +++ b/portal_objects/metaworkflows/ascat.yaml @@ -109,7 +109,7 @@ workflows: spot_instance: False run_name: run_workflow_ascat behavior_on_capacity_limit: wait_and_retry - driver_catalog: + putative_drivers: input: ascat: argument_type: file.tsv_gz diff --git a/portal_objects/workflows/driver_catalog.yaml b/portal_objects/workflows/driver_catalog.yaml index d2ba6f0..12ad4f4 100644 --- a/portal_objects/workflows/driver_catalog.yaml +++ b/portal_objects/workflows/driver_catalog.yaml @@ -1,7 +1,7 @@ # Workflow information ##################################### # General information for the workflow ############################################################# -name: driver_catalog +name: putative_drivers description: Run CNV analysis with ASCAT runner: From bc3af60eab4914853faa3748d76049872ac6578f Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Fri, 9 Dec 2022 16:36:32 +0000 Subject: [PATCH 06/32] . --- .../{driver_catalog.yaml => putative_drivers_cnv.yaml} | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) rename portal_objects/workflows/{driver_catalog.yaml => putative_drivers_cnv.yaml} (90%) diff --git a/portal_objects/workflows/driver_catalog.yaml b/portal_objects/workflows/putative_drivers_cnv.yaml similarity index 90% rename from portal_objects/workflows/driver_catalog.yaml rename to portal_objects/workflows/putative_drivers_cnv.yaml index 12ad4f4..10025c0 100644 --- a/portal_objects/workflows/driver_catalog.yaml +++ b/portal_objects/workflows/putative_drivers_cnv.yaml @@ -1,8 +1,8 @@ # Workflow information ##################################### # General information for the workflow ############################################################# -name: putative_drivers -description: Run CNV analysis with ASCAT +name: putative_drivers_cnv +description: Find putative driver mutations from CNVs runner: language: cwl From 9d07c98b366e524895446358e65b752ce54a72f2 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Fri, 9 Dec 2022 17:52:34 +0000 Subject: [PATCH 07/32] . --- portal_objects/metaworkflows/ascat.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/ascat.yaml index 37ee195..df1e594 100644 --- a/portal_objects/metaworkflows/ascat.yaml +++ b/portal_objects/metaworkflows/ascat.yaml @@ -109,7 +109,7 @@ workflows: spot_instance: False run_name: run_workflow_ascat behavior_on_capacity_limit: wait_and_retry - putative_drivers: + putative_drivers_cnv: input: ascat: argument_type: file.tsv_gz From aa3aed921898215d58a4de9facc3b293962e46c0 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Fri, 9 Dec 2022 19:56:55 +0000 Subject: [PATCH 08/32] . --- descriptions/{cwl => }/ascat.cwl | 0 descriptions/cwl/workflow_ascat.cwl | 81 ----- descriptions/driver_catalog.cwl | 2 +- portal_objects/file_reference.json | 15 - portal_objects/metaworkflows/ascat.json | 86 ----- portal_objects/software.json | 26 -- portal_objects/workflows/ascat.yaml | 4 +- portal_objects/workflows/workflow_ascat.json | 322 ------------------- 8 files changed, 2 insertions(+), 534 deletions(-) rename descriptions/{cwl => }/ascat.cwl (100%) delete mode 100644 descriptions/cwl/workflow_ascat.cwl delete mode 100644 portal_objects/file_reference.json delete mode 100644 portal_objects/metaworkflows/ascat.json delete mode 100644 portal_objects/software.json delete mode 100644 portal_objects/workflows/workflow_ascat.json diff --git a/descriptions/cwl/ascat.cwl b/descriptions/ascat.cwl similarity index 100% rename from descriptions/cwl/ascat.cwl rename to descriptions/ascat.cwl diff --git a/descriptions/cwl/workflow_ascat.cwl b/descriptions/cwl/workflow_ascat.cwl deleted file mode 100644 index e676033..0000000 --- a/descriptions/cwl/workflow_ascat.cwl +++ /dev/null @@ -1,81 +0,0 @@ -cwlVersion: v1.0 - -class: Workflow - -requirements: - MultipleInputFeatureRequirement: {} - -inputs: - - id: tumor_file - type: File - secondaryFiles: - - .bai - doc: tumor sample BAM file - - - id: normal_file - type: File - secondaryFiles: - - .bai - doc: normal sample BAM file - - - id: gender - type: string - doc: gender - - - id: nthreads - type: int - doc: number of threads used to run ascat - - - id: reference_data - type: File - doc: tar file of loci, alleles and GC correction files - -outputs: - - id: BAF_LogR_tumor_germline - type: File - outputSource: ascat/BAF_LogR_tumor_germline - - id: cnv_ascat - type: File - outputSource: ascat/cnv_ascat - - id: after_correction_tumor_germline - type: File - outputSource: ascat/after_correction_tumor_germline - - id: after_correction_tumor_tumour - type: File - outputSource: ascat/after_correction_tumor_tumour - - id: before_correction_tumor_tumour - type: File - outputSource: ascat/before_correction_tumor_tumour - - id: tumor_ASCATprofile - type: File - outputSource: ascat/tumor_ASCATprofile - - id: tumor_ASPCF - type: File - outputSource: ascat/tumor_ASPCF - - id: tumor_rawprofile - type: File - outputSource: ascat/tumor_rawprofile - - id: tumor_sunrise - type: File - outputSource: ascat/tumor_sunrise - - id: ascat_objects - type: File - outputSource: ascat/ascat_objects - -steps: - ascat: - run: ascat.cwl - in: - tumor_file: - source: tumor_file - normal_file: - source: normal_file - gender: - source: gender - nthreads: - source: nthreads - reference_data: - source: reference_data - out: [BAF_LogR_tumor_germline, tumor_sunrise, tumor_rawprofile, cnv_ascat,tumor_ASPCF, before_correction_tumor_tumour, tumor_ASCATprofile, after_correction_tumor_germline, after_correction_tumor_tumour, ascat_objects] - -doc: run run_ascat.sh diff --git a/descriptions/driver_catalog.cwl b/descriptions/driver_catalog.cwl index d3ce8a4..5b8e479 100644 --- a/descriptions/driver_catalog.cwl +++ b/descriptions/driver_catalog.cwl @@ -48,7 +48,7 @@ outputs: - id: putative_drivers_tsv type: File outputBinding: - glob: $(inputs.output) + glob: $(inputs.output).gz doc: tsv file containing reported putative drivers doc: | diff --git a/portal_objects/file_reference.json b/portal_objects/file_reference.json deleted file mode 100644 index 27fcb64..0000000 --- a/portal_objects/file_reference.json +++ /dev/null @@ -1,15 +0,0 @@ -[ - { - "uuid": "7a33ce65-80f4-4c65-8229-8c2bbe0c1445", - "institution": "INSTITUTION_UUID", - "project": "PROJECT_UUID", - "file_format": "tar_gz", - "description": "datasource for loci, alleles and GC correction files from G1000/Ascat", - "aliases": [ - "cgap:ascat_reference_loci_alleles_GC_G1000" - ], - "status": "uploading", - "accession": "GAPFI6BNMYRO", - "file_version": "hg38" - } -] \ No newline at end of file diff --git a/portal_objects/metaworkflows/ascat.json b/portal_objects/metaworkflows/ascat.json deleted file mode 100644 index d3d0d88..0000000 --- a/portal_objects/metaworkflows/ascat.json +++ /dev/null @@ -1,86 +0,0 @@ -{ - "name": "WGS_CNV_somatic_ascat", - "title": "WGS CNV Somatic ASCAT VERSION ", - "version": "VERSION", - "accession": "GAPMWFOOL21M", - "description": "Call CNV on tumor-normal samples with ASCAT", - "uuid": "46b32ec8-ef0e-430e-bc38-ed357656b728", - "project": "PROJECT_UUID", - "institution": "INSTITUTION_UUID", - "input": [ - { - "argument_name": "tumor_file", - "argument_type": "file", - "dimensionality": 1 - }, - { - "argument_name": "normal_file", - "argument_type": "file", - "dimensionality": 1 - }, - { - "argument_name": "gender", - "argument_type": "parameter", - "value_type": "string" - }, - { - "argument_name": "nthreads", - "argument_type": "parameter", - "value_type": "integer" - }, - { - "argument_name": "reference_data", - "argument_type": "file", - "files": [ - { - "file": "7a33ce65-80f4-4c65-8229-8c2bbe0c1445" - } - ] - } - ], - "workflows": [ - { - "name": "workflow_ascat", - "workflow": "6ab682c4-7e40-4cce-9d81-5db3538d89cb", - "config": { - "instance_type": "m5.4xlarge", - "ebs_size": "1.5x", - "EBS_optimized": true, - "spot_instance": false, - "run_name": "run_workflow_ascat", - "behavior_on_capacity_limit": "wait_and_retry" - }, - "custom_pf_fields": {}, - "input": [ - { - "argument_name": "tumor_file", - "argument_type": "file", - "source_argument_name": "tumor_file", - "input_dimension": 1 - }, - { - "argument_name": "normal_file", - "argument_type": "file", - "source_argument_name": "normal_file", - "input_dimension": 1 - }, - { - "argument_name": "gender", - "argument_type": "parameter", - "source_argument_name": "gender" - }, - { - "argument_name": "reference_data", - "argument_type": "file", - "source_argument_name": "reference_data" - }, - { - "argument_name": "nthreads", - "argument_type": "parameter", - "value": "23", - "value_type": "integer" - } - ] - } - ] -} diff --git a/portal_objects/software.json b/portal_objects/software.json deleted file mode 100644 index 663bcbc..0000000 --- a/portal_objects/software.json +++ /dev/null @@ -1,26 +0,0 @@ -[ - { - "project": "PROJECT_UUID", - "institution": "INSTITUTION_UUID", - "name": "ascat", - "software_type": [ - "variant caller" - ], - "source_url": "https://github.com/VanLoo-lab/ascat", - "title": "ascat_3.0.0", - "uuid": "c91ebae7-03c3-4d93-8e28-03ce87d63c62", - "version": "3.0.0" - }, - { - "project": "PROJECT_UUID", - "institution": "INSTITUTION_UUID", - "name": "cancerit-allelecount", - "software_type": [ - "other" - ], - "source_url": "https://anaconda.org/bioconda/cancerit-allelecount", - "title": " cancerit-allelecount_4.3.0", - "uuid": "34914c29-7a44-45ec-a5f9-b8d33d069b87", - "version": "4.3.0" - } -] \ No newline at end of file diff --git a/portal_objects/workflows/ascat.yaml b/portal_objects/workflows/ascat.yaml index 66eefcf..41a3665 100644 --- a/portal_objects/workflows/ascat.yaml +++ b/portal_objects/workflows/ascat.yaml @@ -6,9 +6,7 @@ description: Run CNV analysis with ASCAT runner: language: cwl - main: workflow_ascat.cwl - child: - - ascat.cwl + main: ascat.cwl software: - ascat@3.0.0 diff --git a/portal_objects/workflows/workflow_ascat.json b/portal_objects/workflows/workflow_ascat.json deleted file mode 100644 index dba7d59..0000000 --- a/portal_objects/workflows/workflow_ascat.json +++ /dev/null @@ -1,322 +0,0 @@ -{ - "accession": "GAPWFJL4GOP", - "app_name": "workflow_ascat", - "app_version": "VERSION", - "arguments": [ - { - "argument_format": "bam", - "argument_type": "Input file", - "workflow_argument_name": "tumor_file" - }, - { - "argument_format": "bam", - "argument_type": "Input file", - "workflow_argument_name": "normal_file" - }, - { - "argument_format": "tar_gz", - "argument_type": "Input file", - "workflow_argument_name": "reference_data" - }, - { - "argument_type": "parameter", - "workflow_argument_name": "gender" - }, - { - "argument_type": "parameter", - "workflow_argument_name": "nthreads" - }, - { - "argument_format": "tsv_gz", - "argument_type": "Output processed file", - "workflow_argument_name": "BAF_LogR_tumor_germline" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "after_correction_tumor_germline" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "after_correction_tumor_tumour" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "before_correction_tumor_tumour" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "tumor_ASCATprofile" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "tumor_ASPCF" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "tumor_rawprofile" - }, - { - "argument_format": "png", - "argument_type": "Output processed file", - "workflow_argument_name": "tumor_sunrise" - }, - { - "argument_format": "tsv_gz", - "argument_type": "Output processed file", - "workflow_argument_name": "cnv_ascat" - }, - { - "argument_format": "Rdata", - "argument_type": "Output processed file", - "workflow_argument_name": "ascat_objects" - } - - ], - "project": "PROJECT_UUID", - "category": ["processing"], - "cwl_child_filenames": ["ascat.cwl"], - "cwl_directory_url_v1": "s3://CWLBUCKET/PIPELINE/VERSION", - "cwl_main_filename": "workflow_ascat.cwl", - "cwl_pointer": "", - "description": "Run ASCAT to call allele-specific copy number variants in tumor-normal sample", - "institution": "INSTITUTION_UUID", - "name": "workflow_ascat_VERSION", - "aliases": ["cgap:workflow_ascat_VERSION"], - "steps": [ - { - "inputs": [ - { - "meta": { - "cardinality": "single", - "file_format": "bam", - "global": true, - "type": "data file" - }, - "name": "tumor_file", - "source": [ - { - "name": "tumor_file" - } - ] - }, - { - "meta": { - "cardinality": "single", - "file_format": "bam", - "global": true, - "type": "data file" - }, - "name": "normal_file", - "source": [ - { - "name": "normal_file" - } - ] - }, - { - "meta": { - "cardinality": "single", - "file_format": "tar_gz", - "global": true, - "type": "data file" - }, - "name": "reference_data", - "source": [ - { - "name": "reference_data" - } - ] - }, - { - "meta": { - "cardinality": "single", - "global": true, - "type": "parameter" - }, - "name": "nthreads", - "source": [ - { - "name": "nthreads" - } - ] - }, - { - "meta": { - "cardinality": "single", - "global": true, - "type": "parameter" - }, - "name": "gender", - "source": [ - { - "name": "gender" - } - ] - } - ], - "meta": { - "analysis_step_types": [ - "Run ASCAT to call CNV in tumor-normal sample" - ], - "software_used": [ - "/softwares/c91ebae7-03c3-4d93-8e28-03ce87d63c62", - "/softwares/34914c29-7a44-45ec-a5f9-b8d33d069b87" - ] - }, - "name": "run ASCAT", - "outputs": [ - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "after_correction_tumor_germline", - "target": [ - { - "name": "after_correction_tumor_germline" - } - ] - }, - - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "after_correction_tumor_tumour", - "target": [ - { - "name": "after_correction_tumor_tumour" - } - ] - }, - - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "before_correction_tumor_tumour" - }, - - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "tumor_ASCATprofile", - "target": [ - { - "name": "tumor_ASCATprofile" - } - ] - }, - - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "tumor_ASPCF", - "target": [ - { - "name": "tumor_ASPCF" - } - ] - - }, - - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "tumor_rawprofile", - "target": [ - { - "name": "tumor_rawprofile" - } - ] - }, - - { - "meta": { - "cardinality": "single", - "file_format": "png", - "global": true, - "type": "data file" - }, - "name": "tumor_sunrise", - "target": [ - { - "name": "tumor_sunrise" - } - ] - }, - { - "meta": { - "cardinality": "single", - "file_format": "tsv_gz", - "global": true, - "type": "data file" - }, - "name": "cnv_ascat", - "target": [ - { - "name": "cnv_ascat" - } - ] - }, - { - "meta": { - "cardinality": "single", - "file_format": "Rdata", - "global": true, - "type": "data file" - }, - "name": "ascat_objects", - "target": [ - { - "name": "ascat_objects" - } - ] - }, - { - "meta": { - "cardinality": "single", - "file_format": "tsv_gz", - "global": true, - "type": "data file" - }, - "name": "BAF_LogR_tumor_germline" - , - "target": [ - { - "name": "BAF_LogR_tumor_germline" - } - ] - } - ] - } - ], - "title": "Run CNV analysis with ASCAT", - "uuid": "6ab682c4-7e40-4cce-9d81-5db3538d89cb" -} From 4fc8989dd31041ae56f5b73215b1f6b290c583ee Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 14:34:22 +0000 Subject: [PATCH 09/32] . --- portal_objects/workflows/ascat.yaml | 2 +- portal_objects/workflows/putative_drivers_cnv.yaml | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/portal_objects/workflows/ascat.yaml b/portal_objects/workflows/ascat.yaml index 41a3665..eb7f990 100644 --- a/portal_objects/workflows/ascat.yaml +++ b/portal_objects/workflows/ascat.yaml @@ -2,7 +2,7 @@ # General information for the workflow ############################################################# name: ascat -description: Run CNV analysis with ASCAT +description: Run CNV analysis with ASCAT. runner: language: cwl diff --git a/portal_objects/workflows/putative_drivers_cnv.yaml b/portal_objects/workflows/putative_drivers_cnv.yaml index 10025c0..45e5e04 100644 --- a/portal_objects/workflows/putative_drivers_cnv.yaml +++ b/portal_objects/workflows/putative_drivers_cnv.yaml @@ -2,7 +2,8 @@ # General information for the workflow ############################################################# name: putative_drivers_cnv -description: Find putative driver mutations from CNVs +description: Identify putative cancer drivers from CNV calls. + runner: language: cwl From 0a535e7ecf2a63d7621be7255a1208aecedc4922 Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 12:28:39 -0500 Subject: [PATCH 10/32] Update file_reference.yaml --- portal_objects/file_reference.yaml | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml index 122325d..f30da31 100644 --- a/portal_objects/file_reference.yaml +++ b/portal_objects/file_reference.yaml @@ -2,9 +2,10 @@ # Datasource for ASCAT ################################################################ name: ascat_reference_loci_alleles_GC_G1000 -description: Datasource for loci, alleles and GC correction files from G1000/ASCAT. +description: Datasource for loci, alleles and GC correction files from G1000/ASCAT. | + Build hg38/GRCh38. format: tar_gz -version: hg38 +version: 09132022 uuid: 7a33ce65-80f4-4c65-8229-8c2bbe0c1445 accession: GAPFI6BNMYRO @@ -14,26 +15,29 @@ accession: GAPFI6BNMYRO # Datasource for the driver catalog ################################################################ name: cgap_genes -description: Datasource for genes supported by CGAP +description: Datasource for genes supported by CGAP. | + Build hg38/GRCh38. format: tsv_gz -version: hg38 +version: 09132022 uuid: 335f7c0f-640e-44b9-a0da-bbe2728f782c accession: GAPFI6BQNY5O --- name: gene_panel_hartwig -description: Configuration file of which genes to add to the driver catalog +description: Configuration file of which genes to add to the driver catalog. | + Build hg38/GRCh38. format: tsv_gz -version: hg38 +version: 09132022 uuid: bd334693-b83e-4709-9d96-d8cc3f524848 accession: GAPFI6BNWA1O --- name: somatic_hotspot_mutations -description: Datasource for somatic hotspot locations +description: Datasource for somatic hotspot locations. | + Build hg38/GRCh38. format: vcf_gz -version: hg38 +version: 09132022 uuid: 19f548db-5491-464c-babd-a9f4f0b2c8c4 -accession: GAPFI6BNWA90 \ No newline at end of file +accession: GAPFI6BNWA90 From fd542c3e67fbc199d20da2c73a12ef986dd23930 Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 12:29:29 -0500 Subject: [PATCH 11/32] Update file_reference.yaml --- portal_objects/file_reference.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml index f30da31..500afc2 100644 --- a/portal_objects/file_reference.yaml +++ b/portal_objects/file_reference.yaml @@ -5,7 +5,7 @@ name: ascat_reference_loci_alleles_GC_G1000 description: Datasource for loci, alleles and GC correction files from G1000/ASCAT. | Build hg38/GRCh38. format: tar_gz -version: 09132022 +version: v09132022 uuid: 7a33ce65-80f4-4c65-8229-8c2bbe0c1445 accession: GAPFI6BNMYRO @@ -18,7 +18,7 @@ name: cgap_genes description: Datasource for genes supported by CGAP. | Build hg38/GRCh38. format: tsv_gz -version: 09132022 +version: v09132022 uuid: 335f7c0f-640e-44b9-a0da-bbe2728f782c accession: GAPFI6BQNY5O @@ -28,7 +28,7 @@ name: gene_panel_hartwig description: Configuration file of which genes to add to the driver catalog. | Build hg38/GRCh38. format: tsv_gz -version: 09132022 +version: v09132022 uuid: bd334693-b83e-4709-9d96-d8cc3f524848 accession: GAPFI6BNWA1O @@ -38,6 +38,6 @@ name: somatic_hotspot_mutations description: Datasource for somatic hotspot locations. | Build hg38/GRCh38. format: vcf_gz -version: 09132022 +version: v09132022 uuid: 19f548db-5491-464c-babd-a9f4f0b2c8c4 accession: GAPFI6BNWA90 From 8988942e8968a238d3ea27cd595e780c8fb3926c Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 12:30:54 -0500 Subject: [PATCH 12/32] Update file_reference.yaml --- portal_objects/file_reference.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml index 500afc2..f88aca3 100644 --- a/portal_objects/file_reference.yaml +++ b/portal_objects/file_reference.yaml @@ -5,7 +5,7 @@ name: ascat_reference_loci_alleles_GC_G1000 description: Datasource for loci, alleles and GC correction files from G1000/ASCAT. | Build hg38/GRCh38. format: tar_gz -version: v09132022 +version: hg38 uuid: 7a33ce65-80f4-4c65-8229-8c2bbe0c1445 accession: GAPFI6BNMYRO From 243f900efe142855f2b10149d9eb77d936bc7b7b Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 12:50:51 -0500 Subject: [PATCH 13/32] Update file_reference.yaml --- portal_objects/file_reference.yaml | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml index f88aca3..2503d78 100644 --- a/portal_objects/file_reference.yaml +++ b/portal_objects/file_reference.yaml @@ -2,7 +2,8 @@ # Datasource for ASCAT ################################################################ name: ascat_reference_loci_alleles_GC_G1000 -description: Datasource for loci, alleles and GC correction files from G1000/ASCAT. | +description: Loci, alleles and GC correction files from 1000 Genomes. | + From ASCAT repository. | Build hg38/GRCh38. format: tar_gz version: hg38 @@ -15,17 +16,18 @@ accession: GAPFI6BNMYRO # Datasource for the driver catalog ################################################################ name: cgap_genes -description: Datasource for genes supported by CGAP. | +description: Genes supported by CGAP. | Build hg38/GRCh38. format: tsv_gz -version: v09132022 +version: v0.4.6 uuid: 335f7c0f-640e-44b9-a0da-bbe2728f782c accession: GAPFI6BQNY5O --- name: gene_panel_hartwig -description: Configuration file of which genes to add to the driver catalog. | +description: Genes to add to the driver catalog. | + From Hartwig Medical Foundation. | Build hg38/GRCh38. format: tsv_gz version: v09132022 @@ -35,7 +37,8 @@ accession: GAPFI6BNWA1O --- name: somatic_hotspot_mutations -description: Datasource for somatic hotspot locations. | +description: Somatic hotspot locations. | + From Hartwig Medical Foundation. | Build hg38/GRCh38. format: vcf_gz version: v09132022 From e19b4e91a629684d61f27e8657ebc46d40cb763f Mon Sep 17 00:00:00 2001 From: Michele Berselli Date: Mon, 12 Dec 2022 13:37:16 -0500 Subject: [PATCH 14/32] . --- portal_objects/metaworkflows/ascat.yaml | 135 +++++++++++++++--------- 1 file changed, 84 insertions(+), 51 deletions(-) diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/ascat.yaml index df1e594..8aaff42 100644 --- a/portal_objects/metaworkflows/ascat.yaml +++ b/portal_objects/metaworkflows/ascat.yaml @@ -2,8 +2,8 @@ # General information for the pipeline ############################################################# name: WGS_CNV_somatic_ascat -description: Call CNV on tumor-normal samples with ASCAT | - Prioritize somatic mutations +description: Call CNVs on tumor-normal samples with ASCAT. | + Prioritize putative driver mutations. ## General arguments ######################################## # Pipeline input, reference files, and general arguments @@ -21,22 +21,24 @@ input: gender: argument_type: parameter.string - + nthreads: argument_type: parameter.integer - + reference_data: argument_type: file.tar_gz files: - ascat_reference_loci_alleles_GC_G1000@hg38 + cgap_genes: argument_type: file.tsv_gz files: - - cgap_genes@hg38 + - cgap_genes@0.4.6 + gene_panel: argument_type: file.tsv_gz files: - - gene_panel_hartwig@hg38 + - gene_panel_hartwig@v09132022 ## Workflows and dependencies ############################### @@ -45,7 +47,7 @@ input: workflows: ## Workflow definition ##################### - # cram2fastq + # ascat ############################################ ascat: @@ -63,41 +65,57 @@ workflows: gender: argument_type: parameter.string - + nthreads: argument_type: parameter.integer value: "23" - + reference_data: argument_type: file.tar_gz - + ## Output ########################## #################################### output: BAF_LogR_tumor_germline: - file_type: tsv - description: BAF and LogR for the germline sample + file_type: BAF and LogR TSV + description: BAF and LogR for the germline sample from ASCAT in TSV format + after_correction_tumor_germline: - file_type: png - description: correctected LogR of the tumor sample with genomic GC content + file_type: LogR PNG + description: correctected LogR of the tumor sample with genomic GC content from ASCAT in PNG format + after_correction_tumor_tumour: - file_type: png + file_type: ASCAT PNG + description: supplementary output from ASCAT in PNG format + before_correction_tumor_tumour: - file_type: png + file_type: ASCAT PNG + description: supplementary output from ASCAT in PNG format + tumor_ASCATprofile: - file_type: png + file_type: ASCAT PNG + description: supplementary output from ASCAT in PNG format + tumor_ASPCF: - file_type: png + file_type: ASCAT PNG + description: supplementary output from ASCAT in PNG format + tumor_rawprofile: - file_type: png + file_type: ASCAT PNG + description: supplementary output from ASCAT in PNG format + tumor_sunrise: - file_type: png + file_type: ASCAT PNG + description: supplementary output from ASCAT in PNG format + cnv_ascat: - file_type: tsv_gz + file_type: ASCAT TSV + description: output from ASCAT in TSV format + ascat_objects: - file_type: Rdata - + file_type: Rdata objects + description: objects from ASCAT run in Rdata format ## EC2 Configuration to use ######## #################################### @@ -106,35 +124,50 @@ workflows: - c5.4xlarge ebs_size: 1.5x EBS_optimized: True - spot_instance: False - run_name: run_workflow_ascat + spot_instance: True + run_name: run_ascat behavior_on_capacity_limit: wait_and_retry + + ## Workflow definition ##################### + # putative_drivers_cnv + ############################################ putative_drivers_cnv: - input: - ascat: - argument_type: file.tsv_gz - source: ascat - source_argument_name: cnv_ascat - ascat_objects: - argument_type: file.Rdata - source: ascat - source_argument_name: ascat_objects - cgap_genes: - argument_type: file.tsv_gz - gene_panel: - argument_type: file.tsv_gz - - output: - putative_drivers_tsv: - file_type: tsv_gz - - config: - instance_type: - - t3.xlarge - ebs_size: 1.5x - EBS_optimized: True - spot_instance: False - run_name: run_driver_catalog - behavior_on_capacity_limit: wait_and_retry + ## Workflow arguments ############## + #################################### + input: + + ascat: + argument_type: file.tsv_gz + source: ascat + source_argument_name: cnv_ascat + + ascat_objects: + argument_type: file.Rdata + source: ascat + source_argument_name: ascat_objects + + cgap_genes: + argument_type: file.tsv_gz + gene_panel: + argument_type: file.tsv_gz + + ## Output ########################## + #################################### + output: + + putative_drivers_tsv: + file_type: drivers TSV + description: output from drivers prioritization step in TSV format + + ## EC2 Configuration to use ######## + #################################### + config: + instance_type: + - t3.xlarge + ebs_size: 1.5x + EBS_optimized: True + spot_instance: True + run_name: run_putative_drivers_cnv + behavior_on_capacity_limit: wait_and_retry From b8fdafe1f9c17e6f3f1795d396da43d3ae23242f Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:19:55 -0500 Subject: [PATCH 15/32] Update descriptions/driver_catalog.cwl Co-authored-by: Michele --- descriptions/driver_catalog.cwl | 1 + 1 file changed, 1 insertion(+) diff --git a/descriptions/driver_catalog.cwl b/descriptions/driver_catalog.cwl index 5b8e479..baa4201 100644 --- a/descriptions/driver_catalog.cwl +++ b/descriptions/driver_catalog.cwl @@ -25,6 +25,7 @@ inputs: inputBinding: prefix: "--gene_panel" doc: tsv configuration file of which genes to add to the driver catalog from Hartwig Medical Foundation + - id: cgap_genes type: File inputBinding: From 67637526323fd5c9026fbe0afae6bd7e4caec73b Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:20:05 -0500 Subject: [PATCH 16/32] Update dockerfiles/genomic_ranges/Dockerfile Co-authored-by: Michele --- dockerfiles/genomic_ranges/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dockerfiles/genomic_ranges/Dockerfile b/dockerfiles/genomic_ranges/Dockerfile index bc6f951..08ee547 100644 --- a/dockerfiles/genomic_ranges/Dockerfile +++ b/dockerfiles/genomic_ranges/Dockerfile @@ -12,7 +12,7 @@ MAINTAINER Michele Berselli (berselli.michele@gmail.com), Dominika Maziec (domin ####################################################################### # Software ####################################################################### -#install R +## Install R RUN apt-get update && apt-get install -y \ locales \ tabix From 7ea7c2420f98ebfb5efaa09e4e8be3eba6b13794 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:20:13 -0500 Subject: [PATCH 17/32] Update dockerfiles/genomic_ranges/Dockerfile Co-authored-by: Michele --- dockerfiles/genomic_ranges/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dockerfiles/genomic_ranges/Dockerfile b/dockerfiles/genomic_ranges/Dockerfile index 08ee547..ea19572 100644 --- a/dockerfiles/genomic_ranges/Dockerfile +++ b/dockerfiles/genomic_ranges/Dockerfile @@ -19,7 +19,7 @@ RUN apt-get update && apt-get install -y \ RUN apt-get install -y --no-install-recommends r-base RUN apt-get install -y --no-install-recommends r-cran-tidyverse r-cran-optparse r-cran-biocmanager -#install GenomicRanges +## Install GenomicRanges RUN R -e "BiocManager::install('GenomicRanges')" ####################################################################### From f893d305509678f30a7a7dee8fe14b0fa5469c1f Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:20:42 -0500 Subject: [PATCH 18/32] Update portal_objects/workflows/putative_drivers_cnv.yaml Co-authored-by: Michele --- portal_objects/workflows/putative_drivers_cnv.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/portal_objects/workflows/putative_drivers_cnv.yaml b/portal_objects/workflows/putative_drivers_cnv.yaml index 45e5e04..cde94b3 100644 --- a/portal_objects/workflows/putative_drivers_cnv.yaml +++ b/portal_objects/workflows/putative_drivers_cnv.yaml @@ -10,7 +10,6 @@ runner: main: driver_catalog.cwl - ## Input information ######################################## # Input files and parameters ############################################################# From 570ff6be1df23cbbcb3e0fd08121ecee1e890dce Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:20:49 -0500 Subject: [PATCH 19/32] Update portal_objects/workflows/putative_drivers_cnv.yaml Co-authored-by: Michele --- portal_objects/workflows/putative_drivers_cnv.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/portal_objects/workflows/putative_drivers_cnv.yaml b/portal_objects/workflows/putative_drivers_cnv.yaml index cde94b3..83d48b0 100644 --- a/portal_objects/workflows/putative_drivers_cnv.yaml +++ b/portal_objects/workflows/putative_drivers_cnv.yaml @@ -27,7 +27,6 @@ input: ascat_objects: argument_type: file.Rdata - ## Output information ####################################### # Output files ############################################################# From f370c22d1fa888f17b17ad8f120de3f4d5c32d56 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:20:59 -0500 Subject: [PATCH 20/32] Update portal_objects/software.yaml Co-authored-by: Michele --- portal_objects/software.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/portal_objects/software.yaml b/portal_objects/software.yaml index 2ecee1a..1793a1f 100644 --- a/portal_objects/software.yaml +++ b/portal_objects/software.yaml @@ -9,7 +9,7 @@ source_url: https://github.com/VanLoo-lab/ascat --- ################################################################ -# cancerit-allelecount, v4.3.0 +# cancerit-allelecount, 4.3.0 ################################################################ name: cancerit-allelecount version: 4.3.0 From a5b08fc9fcb13227ab71e07583fb69ca78e196d1 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:21:09 -0500 Subject: [PATCH 21/32] Update portal_objects/metaworkflows/ascat.yaml Co-authored-by: Michele --- portal_objects/metaworkflows/ascat.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/ascat.yaml index 8aaff42..3af99e5 100644 --- a/portal_objects/metaworkflows/ascat.yaml +++ b/portal_objects/metaworkflows/ascat.yaml @@ -40,7 +40,6 @@ input: files: - gene_panel_hartwig@v09132022 - ## Workflows and dependencies ############################### # Information for the workflows and their dependencies ############################################################# From dd7c17ca66febd59768e35e3e47b41df44566a13 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:21:19 -0500 Subject: [PATCH 22/32] Update dockerfiles/genomic_ranges/Dockerfile Co-authored-by: Michele --- dockerfiles/genomic_ranges/Dockerfile | 1 + 1 file changed, 1 insertion(+) diff --git a/dockerfiles/genomic_ranges/Dockerfile b/dockerfiles/genomic_ranges/Dockerfile index ea19572..05f9367 100644 --- a/dockerfiles/genomic_ranges/Dockerfile +++ b/dockerfiles/genomic_ranges/Dockerfile @@ -32,6 +32,7 @@ WORKDIR /usr/local/bin ####################################################################### COPY scripts/driver_catalog.sh . RUN chmod +x driver_catalog.sh + COPY scripts/postprocess_ascat.R . ####################################################################### From cb8e0dfbcd96401f60308032656621a1599757ba Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 15:21:53 -0500 Subject: [PATCH 23/32] Update portal_objects/software.yaml Co-authored-by: Michele --- portal_objects/software.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/portal_objects/software.yaml b/portal_objects/software.yaml index 1793a1f..8474a20 100644 --- a/portal_objects/software.yaml +++ b/portal_objects/software.yaml @@ -1,6 +1,6 @@ ################################################################ -# ASCAT, v3.0.0 +# ASCAT, 3.0.0 ################################################################ name: ascat version: 3.0.0 From f2dda4e499a75712709b962805b5014586b30f99 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 20:29:24 +0000 Subject: [PATCH 24/32] . --- dockerfiles/genomic_ranges/Dockerfile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/dockerfiles/genomic_ranges/Dockerfile b/dockerfiles/genomic_ranges/Dockerfile index 05f9367..3b147e5 100644 --- a/dockerfiles/genomic_ranges/Dockerfile +++ b/dockerfiles/genomic_ranges/Dockerfile @@ -9,13 +9,13 @@ MAINTAINER Michele Berselli (berselli.michele@gmail.com), Dominika Maziec (domin # - tabix brings in bgzip and tabix # - locales for UTF-8 ####################################################################### +RUN apt-get update && apt-get install -y \ + locales \ + tabix ####################################################################### # Software ####################################################################### ## Install R -RUN apt-get update && apt-get install -y \ - locales \ - tabix RUN apt-get install -y --no-install-recommends r-base RUN apt-get install -y --no-install-recommends r-cran-tidyverse r-cran-optparse r-cran-biocmanager From 4bbcc0dae10d0e39a02023addd05bdf0ec77f851 Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 15:35:56 -0500 Subject: [PATCH 25/32] Update Dockerfile --- dockerfiles/genomic_ranges/Dockerfile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/dockerfiles/genomic_ranges/Dockerfile b/dockerfiles/genomic_ranges/Dockerfile index 3b147e5..f5559a2 100644 --- a/dockerfiles/genomic_ranges/Dockerfile +++ b/dockerfiles/genomic_ranges/Dockerfile @@ -12,6 +12,7 @@ MAINTAINER Michele Berselli (berselli.michele@gmail.com), Dominika Maziec (domin RUN apt-get update && apt-get install -y \ locales \ tabix + ####################################################################### # Software ####################################################################### @@ -30,9 +31,11 @@ WORKDIR /usr/local/bin ####################################################################### # Scripts ####################################################################### +## driver_catalog.sh COPY scripts/driver_catalog.sh . RUN chmod +x driver_catalog.sh +## postprocess_ascat.R COPY scripts/postprocess_ascat.R . ####################################################################### From 77c86a2b4526d4459bd97613e256ff17c42b0da0 Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 15:39:48 -0500 Subject: [PATCH 26/32] Update portal_objects/workflows/putative_drivers_cnv.yaml --- portal_objects/workflows/putative_drivers_cnv.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/portal_objects/workflows/putative_drivers_cnv.yaml b/portal_objects/workflows/putative_drivers_cnv.yaml index 83d48b0..11e1aff 100644 --- a/portal_objects/workflows/putative_drivers_cnv.yaml +++ b/portal_objects/workflows/putative_drivers_cnv.yaml @@ -9,7 +9,6 @@ runner: language: cwl main: driver_catalog.cwl - ## Input information ######################################## # Input files and parameters ############################################################# From cd44cc7057e9f60b3a031ded8ce59376dc19e9c3 Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 15:39:57 -0500 Subject: [PATCH 27/32] Update portal_objects/workflows/putative_drivers_cnv.yaml --- portal_objects/workflows/putative_drivers_cnv.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/portal_objects/workflows/putative_drivers_cnv.yaml b/portal_objects/workflows/putative_drivers_cnv.yaml index 11e1aff..6f3b663 100644 --- a/portal_objects/workflows/putative_drivers_cnv.yaml +++ b/portal_objects/workflows/putative_drivers_cnv.yaml @@ -4,7 +4,6 @@ name: putative_drivers_cnv description: Identify putative cancer drivers from CNV calls. - runner: language: cwl main: driver_catalog.cwl From 648a617dee4809b211134e8e74879888ec86ae1d Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 15:40:39 -0500 Subject: [PATCH 28/32] Update portal_objects/workflows/ascat.yaml --- portal_objects/workflows/ascat.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/portal_objects/workflows/ascat.yaml b/portal_objects/workflows/ascat.yaml index eb7f990..7f29f43 100644 --- a/portal_objects/workflows/ascat.yaml +++ b/portal_objects/workflows/ascat.yaml @@ -29,7 +29,6 @@ input: nthreads: argument_type: parameter.string - ## Output information ####################################### # Output files ############################################################# From dc2f01bf9d5777e8213cc44c65abdad89d10d5c3 Mon Sep 17 00:00:00 2001 From: Michele Date: Mon, 12 Dec 2022 15:45:33 -0500 Subject: [PATCH 29/32] Update portal_objects/file_reference.yaml --- portal_objects/file_reference.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/portal_objects/file_reference.yaml b/portal_objects/file_reference.yaml index 2503d78..1a6a036 100644 --- a/portal_objects/file_reference.yaml +++ b/portal_objects/file_reference.yaml @@ -19,7 +19,7 @@ name: cgap_genes description: Genes supported by CGAP. | Build hg38/GRCh38. format: tsv_gz -version: v0.4.6 +version: 0.4.6 uuid: 335f7c0f-640e-44b9-a0da-bbe2728f782c accession: GAPFI6BQNY5O From 9a5ebc0f6e512fd19da1978589d2d4b310a9f613 Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Mon, 12 Dec 2022 20:54:10 +0000 Subject: [PATCH 30/32] ascat.yaml -> WGS_CNV_somatic_ascat.yaml --- .../metaworkflows/{ascat.yaml => WGS_CNV_somatic_ascat.yaml} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename portal_objects/metaworkflows/{ascat.yaml => WGS_CNV_somatic_ascat.yaml} (100%) diff --git a/portal_objects/metaworkflows/ascat.yaml b/portal_objects/metaworkflows/WGS_CNV_somatic_ascat.yaml similarity index 100% rename from portal_objects/metaworkflows/ascat.yaml rename to portal_objects/metaworkflows/WGS_CNV_somatic_ascat.yaml From 084dbaca078f3112ab7a7e2e7c59a0e20850df6e Mon Sep 17 00:00:00 2001 From: Dominika Maziec Date: Tue, 3 Jan 2023 17:23:53 +0000 Subject: [PATCH 31/32] ascat.yaml reformat --- portal_objects/workflows/ascat.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/portal_objects/workflows/ascat.yaml b/portal_objects/workflows/ascat.yaml index 7f29f43..0fe7154 100644 --- a/portal_objects/workflows/ascat.yaml +++ b/portal_objects/workflows/ascat.yaml @@ -36,21 +36,30 @@ output: BAF_LogR_tumor_germline: argument_type: file.tsv_gz + after_correction_tumor_germline: argument_type: file.png + after_correction_tumor_tumour: argument_type: file.png + before_correction_tumor_tumour: argument_type: file.png + tumor_ASCATprofile: argument_type: file.png + tumor_ASPCF: argument_type: file.png + tumor_rawprofile: argument_type: file.png + tumor_sunrise: argument_type: file.png + cnv_ascat: argument_type: file.tsv_gz + ascat_objects: argument_type: file.Rdata \ No newline at end of file From 2c55c1ce3624434b281406355b5ec50cbc55df94 Mon Sep 17 00:00:00 2001 From: Michele Date: Tue, 10 Jan 2023 15:46:47 -0500 Subject: [PATCH 32/32] Update VERSION --- VERSION | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/VERSION b/VERSION index 60453e6..795460f 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -v1.0.0 \ No newline at end of file +v1.1.0