Adding nf-core sparsesignatures module

.github/skip_nf_test.json

@@ -101,7 +101,10 @@
         "subworkflows/nf-core/fastq_align_bamcmp_bwa",
         "subworkflows/nf-core/fastq_align_bwa"
     ],
-    "docker": ["modules/nf-core/parabricks", "subworkflows/nf-core/deepvariant/tests/equality"],
+    "docker": ["modules/nf-core/parabricks", 
+               "modules/nf-core/sparsesignatures",
+               "subworkflows/nf-core/deepvariant/tests/equality"
+    ],
     "singularity": [
         "modules/nf-core/bases2fastq",
         "modules/nf-core/deepvariant/rundeepvariant",

modules/nf-core/sparsesignatures/environment.yml

@@ -0,0 +1,11 @@
+channels:
+  - conda-forge
+  - bioconda
+
+dependencies:
+  - bioconda::bioconductor-bsgenome.hsapiens.1000genomes.hs37d5=0.99.1
+  - bioconda::bioconductor-bsgenome.hsapiens.ucsc.hg38=1.4.5
+  - bioconda::bioconductor-sparsesignatures=2.16.0
+  - conda-forge::r-dplyr=1.1.4
+  - conda-forge::r-patchwork=1.3.0
+  - conda-forge::r-tidyr=1.3.1

modules/nf-core/sparsesignatures/main.nf

@@ -0,0 +1,46 @@
+process SPARSE_SIGNATURES {
+    tag "$meta.id"
+    label "process_low_long"
+    label "error_retry"
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-d410175e2fbd9c47aa685bb5dfb87cfad76d408b:a995bb98b7122825523ffed7ae131cb006e56cbe-0':
+        'biocontainers/mulled-v2-d410175e2fbd9c47aa685bb5dfb87cfad76d408b:a995bb98b7122825523ffed7ae131cb006e56cbe-0' }"
+
+    input:
+    tuple val(meta), path(tsv_join,  stageAs: '*.tsv')
+
+    output:
+    tuple val(meta), path("*_mut_counts.rds"),            emit: signatures_mutCounts_rds
+    tuple val(meta), path("*_cv_means_mse.rds"),          emit: signatures_cv_rds
+    tuple val(meta), path("*_best_params_config.rds"),    emit: signatures_bestConf_rds
+    tuple val(meta), path("*_nmf_Lasso_out.rds"),         emit: signatures_nmfOut_rds
+    tuple val(meta), path("*_plot_all.rds"),              emit: signatures_plot_rds
+    tuple val(meta), path("*_plot_all.pdf"),              emit: signatures_plot_pdf
+    path "versions.yml",                                  emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template "main_script.R"
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_mut_counts.rds
+    touch ${prefix}_cv_means_mse.rds
+    touch ${prefix}_best_params_config.rds
+    touch ${prefix}_nmf_Lasso_out.rds
+    touch ${prefix}_plot_all.rds
+    touch ${prefix}_plot_all.pdf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bioconductor-sparsesignatures: \$(Rscript -e "library(SparseSignatures); cat(as.character(packageVersion('SparseSignatures')))")
+        bioconductor-bsgenome.hsapiens.1000genomes.hs37d5: \$(Rscript -e "library(BSgenome.Hsapiens.1000genomes.hs37d5); cat(as.character(packageVersion('BSgenome.Hsapiens.1000genomes.hs37d5')))")
+        bioconductor-bsgenome.hsapiens.ucsc.hg38: \$(Rscript -e "library(BSgenome.Hsapiens.UCSC.hg38); cat(as.character(packageVersion('BSgenome.Hsapiens.UCSC.hg38')))")
+    END_VERSIONS
+    """
+}

modules/nf-core/sparsesignatures/meta.yml

@@ -0,0 +1,111 @@
+name: sparse_signatures
+description: mutational signature deconvolution of cancer cells
+keywords:
+  - mutational signatures
+  - SBS
+  - bs genome reference
+tools:
+  - sparsesignatures:
+      description: SparseSignatures is an R-based computational framework which performs
+        de novo extraction, inference, interpretation, or deconvolution of mutational
+        counts of a large number of patients.
+      documentation: https://www.bioconductor.org/packages/release/bioc/html/SparseSignatures.html
+      tool_dev_url: https://github.com/danro9685/SparseSignatures/tree/master?tab=readme-ov-file
+      doi: "10.1371/journal.pcbi.1009119"
+      licence: ["Apache-2.0"]
+      identifier: biotools:sparsesignatures
+  - bsgenome.hsapiens.1000genomes.hs37d5:
+      description: Reference Genome Sequence (hs37d5), based on NCBI GRCh37
+      documentation: https://bioconductor.org/packages/3.8/data/annotation/html/BSgenome.Hsapiens.1000genomes.hs37d5.html
+      doi: "10.1038/s41467-022-29271-y"
+      licence: ["Artistic-2.0"]
+      identifier: biotools:bsgenome.hsapiens.1000genomes.hs37d5
+  - bsgenome.hsapiens.ucsc.hg38:
+      description: Full genomic sequences for Homo sapiens (UCSC genome hg38)
+      documentation: https://bioconductor.org/packages/3.16/data/annotation/html/BSgenome.Hsapiens.UCSC.hg38.html
+      doi: "10.18129/B9.bioc.BSgenome.Hsapiens.UCSC.hg38"
+      licence: ["Artistic-2.0"]
+      identifier: biotools:bsgenome.hsapiens.ucsc.hg38
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'sample1' ]
+    - tsv_join:
+        type: file
+        description: joint tsv file with validated mutations by CNAqc
+        pattern: "*.{tsv}"
+output:
+  - signatures_mutCounts_rds:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*_mut_counts.rds":
+          type: file
+          description: File containing mutational counts across samples/patients
+          pattern: "*{_mut_counts.rds}"
+  - signatures_cv_rds:
+      - meta: 
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*_cv_means_mse.rds": 
+          type: file
+          description: File containing cross-validation results
+          pattern: "*{_cv_means_mse.rds}"
+  - signatures_bestConf_rds:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*_best_params_config.rds": 
+          type: file
+          description: File containing best parameters configuration (numer of signatures (K) and lambda)
+          pattern: "*{_best_params_config.rds}"
+  - signatures_nmfOut_rds:
+      - meta: 
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*_nmf_Lasso_out.rds":
+          type: file
+          description: File containing the results of nmf LASSO fit (signatures and exposures)
+          pattern: "*{_nmf_Lasso_out.rds}"
+  - signatures_plot_rds:
+      - meta: 
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*_plot_all.rds":
+          type: file
+          description: File containig the data to generate plots
+          pattern: "*{_plot_all.rds}"
+  - signatures_plot_pdf:
+      - meta: 
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*_plot_all.pdf":
+          type: file
+          description: File containing the generated plots
+          pattern: "*{_plot_all.pdf}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@Katerina10-cloud"
+  - "@elena-buscaroli"
+maintainers:
+  - "@Katerina10-cloud"
+  - "@elena-buscaroli"
+