Merge pull request nf-core#25 from caravagnalab/dev

Docker and script templates
caravagnalab · Jan 30, 2025 · 7a5b5df · 7a5b5df
2 parents b74cc13 + 21c6732
commit 7a5b5df
Show file tree

Hide file tree

Showing 34 changed files with 1,103 additions and 1,202 deletions.
diff --git a/.nf-core.yml b/.nf-core.yml
@@ -13,3 +13,7 @@ template:
   org: nf-core
   outdir: .
   version: 1.0dev
+lint:
+  modules_config: False
+  files_exist:
+    - conf/modules.config
diff --git a/conf/modules.config b/conf/modules.config
diff --git a/conf/test.config b/conf/test.config
@@ -43,10 +43,10 @@ params {
 
     sparsesignatures_K = "2:3"
     sparsesignatures_nmf_runs = "3"
-    sparsesignatures_iterations = "10"
+    sparsesignatures_iterations = "5"
     sparsesignatures_max_iterations_lasso = "80"
-    sparsesignatures_cross_validation_repetitions = "8"
-    sparsesignatures_cross_validation_iterations = "5"
+    sparsesignatures_cross_validation_repetitions = "5"
+    sparsesignatures_cross_validation_iterations = "3"
     sparsesignatures_lambda_values_alpha = "c(0.00, 0.01)"
     sparsesignatures_lambda_values_beta = "c(0.01, 0.05)"
 

diff --git a/modules.json b/modules.json
@@ -23,16 +23,6 @@
                         "installed_by": ["modules", "vcf_annotate_ensemblvep"],
                         "patch": "modules/nf-core/ensemblvep/vep/ensemblvep-vep.diff"
                     },
-                    "fastqc": {
-                        "branch": "master",
-                        "git_sha": "08108058ea36a63f141c25c4e75f9f872a5b2296",
-                        "installed_by": ["modules"]
-                    },
-                    "multiqc": {
-                        "branch": "master",
-                        "git_sha": "f0719ae309075ae4a291533883847c3f7c441dad",
-                        "installed_by": ["modules"]
-                    },
                     "tabix/tabix": {
                         "branch": "master",
                         "git_sha": "9502adb23c0b97ed8e616bbbdfa73b4585aec9a1",

diff --git a/modules/local/CNAqc/main.nf b/modules/local/CNAqc/main.nf
@@ -1,7 +1,9 @@
 process CNAQC {
     tag "$meta.id"
     label "process_low"
-    container = 'docker://lvaleriani/cnaqc:version1.0'
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://lvaleriani/cnaqc:version1.0' :
+        'docker.io/lvaleriani/cnaqc:version1.0' }"
 
     input:
     tuple val(meta), path(cna_rds), path(snv_rds)
@@ -13,7 +15,6 @@ process CNAQC {
     tuple val(meta), path("*_qc.pdf"),                                  emit: plot_pdf_qc
     path "versions.yml",                                                emit: versions
 
-
     script:
     def args                                = task.ext.args
     def prefix                              = task.ext.prefix                                       ?: "${meta.id}"

diff --git a/modules/local/CNAqc2tsv/main.nf b/modules/local/CNAqc2tsv/main.nf
@@ -1,11 +1,9 @@
-//
-// Mutations extraction from mCNAqc
-//
-
 process RDS_PROCESSING {
     tag "$meta.id"
     label "process_single"
-    container = 'docker://lvaleriani/cnaqc:version1.0'
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://lvaleriani/cnaqc:version1.0' :
+        'docker.io/lvaleriani/cnaqc:version1.0' }"
 
     input:
     tuple val(meta), path(rds_join), val(tumour_samples)
@@ -14,41 +12,6 @@ process RDS_PROCESSING {
     tuple val(meta), path("*_joint_table.tsv"), val(tumour_samples),    emit: tsv
     path "versions.yml",                                                emit: versions
 
-
     script:
-    def args    = task.ext.args     ?:  ''
-    def prefix  = task.ext.prefix   ?:  "${meta.id}"
-
-    """
-    #!/usr/bin/env Rscript
-    library(dplyr)
-    library(CNAqc)
-
-    source("$moduleDir/utils.R")
-
-    multi_cnaqc = readRDS(file = "$rds_join")
-    mutations_multisample <- get_sample(m_cnaqc_obj = multi_cnaqc,sample = get_sample_name(multi_cnaqc),
-                                    which_obj = "original")
-    multisample_jointTable <- list()
-
-    for (s in get_sample_name(multi_cnaqc)){
-        purity <- mutations_multisample[[s]][["purity"]]
-        multisample_jointTable[[s]] <- mutations_multisample[[s]][["mutations"]] %>%
-            dplyr::mutate(purity=purity)
-    }
-
-    joint_table <- bind_rows(multisample_jointTable)
-
-    write.table(joint_table, file = paste0("$prefix","_joint_table.tsv"), append = F, quote = F, sep = "\t", row.names = FALSE)
-
-        # version export
-    f <- file("versions.yml","w")
-    dplyr_version <- sessionInfo()\$otherPkgs\$dplyr\$Version
-    cnaqc_version <- sessionInfo()\$otherPkgs\$CNAqc\$Version
-    writeLines(paste0('"', "$task.process", '"', ":"), f)
-    writeLines(paste("    dplyr:", dplyr_version), f)
-    writeLines(paste("    CNAqc:", cnaqc_version), f)
-    close(f)
-
-    """
+    template "main_script.R"
 }
diff --git a/modules/local/CNAqc2tsv/utils.R → ...s/local/CNAqc2tsv/templates/main_script.R b/modules/local/CNAqc2tsv/utils.R → ...s/local/CNAqc2tsv/templates/main_script.R
@@ -1,9 +1,12 @@
-## This source file is temporary, only needed in
-## absence of the updated CNAqc package
+#!/usr/bin/env Rscript
 
-get_sample <- function(m_cnaqc_obj,
-                    sample,
-                    which_obj) {
+opt = list(
+    prefix = ifelse('$task.ext.prefix' == 'null', '$meta.id', '$task.ext.prefix')
+)
+
+# Auxiliary functions #####
+
+get_sample = function(m_cnaqc_obj, sample, which_obj) {
     if (class(m_cnaqc_obj) != "m_cnaqc") {
         wrong_class_all = class(m_cnaqc_obj)
 
@@ -13,72 +16,79 @@ get_sample <- function(m_cnaqc_obj,
         )
     }
 
-    consented_obj <- c("shared", "original")
-
+    consented_obj = c("shared", "original")
     if ((which_obj %in% consented_obj) == FALSE) {
-
         cli::cli_abort("{.var which_obj} must be one of {.val shared} or {.val original}")
-
     }
 
     # define the element names
-
     if (which_obj == "original") {
-
         type = "original_cnaqc_objc"
-
         # check if the original cnaqc obj exist
-
         check_or = any(names(m_cnaqc_obj) == type)
-
         if (check_or == FALSE) {
             cli::cli_abort(c("mCNAqc object was build without keeping original CNAqc objects"),
                         "x" = "It is not possible to retrieve the required samples")
         } else {
-
             cli::cli_h1("Retrieving original {.cls CNAqc} objects")
             cnaqc_samples = m_cnaqc_obj[[type]][sample]
-
         }
 
     } else {
-
         type = "cnaqc_obj_new_segmentation"
-
         cli::cli_h1("Retrieving {.cls CNAqc} objects with the new segmentation")
-
         cnaqc_samples = m_cnaqc_obj[[type]][sample]
     }
-
     return(cnaqc_samples)
 }
 
-get_sample_name <- function(x) {
-
+get_sample_name = function(x) {
     if (class(x) == "m_cnaqc") {
-
-        lapply(x$cnaqc_obj_new_segmentation, function(y) {
-
-            y$sample
-
+        lapply(x[["cnaqc_obj_new_segmentation"]], function(y) {
+            y[["sample"]]
         }) %>% unlist() %>% unname()
-
     } else if (class(x) == "cnaqc") {
-
-        x$sample
-
+        x[["sample"]]
     } else {
-
         wrong_class_all = class(x)
-
         cli::cli_abort(
             c("must provide a {.field m_cnaqc} object",
             "x" = "{.var x} is a {.cls {class(x)}}")
         )
     }
 }
 
-get_mCNAqc_stats <- function(m_cnaqc_obj){
+get_mCNAqc_stats = function(m_cnaqc_obj){
     stats = m_cnaqc_obj[["m_cnaqc_stats"]]
     return(stats)
 }
+
+# Script ####
+
+library(dplyr)
+library(CNAqc)
+
+multi_cnaqc = readRDS(file = "$rds_join")
+mutations_multisample = get_sample(m_cnaqc_obj = multi_cnaqc,sample = get_sample_name(multi_cnaqc),
+                                which_obj = "original")
+multisample_jointTable = list()
+
+for (s in get_sample_name(multi_cnaqc)){
+    purity = mutations_multisample[[s]][["purity"]]
+    multisample_jointTable[[s]] = mutations_multisample[[s]][["mutations"]] %>%
+        dplyr::mutate(purity=purity)
+}
+
+joint_table = bind_rows(multisample_jointTable)
+
+write.table(joint_table, file = paste0(opt[["prefix"]], "_joint_table.tsv"), append = F, quote = F, sep = "\t", row.names = FALSE)
+
+# version export
+f = file("versions.yml","w")
+dplyr_version = sessionInfo()\$otherPkgs\$dplyr\$Version
+cnaqc_version = sessionInfo()\$otherPkgs\$CNAqc\$Version
+writeLines(paste0('"', "$task.process", '"', ":"), f)
+writeLines(paste("    dplyr:", dplyr_version), f)
+writeLines(paste("    CNAqc:", cnaqc_version), f)
+close(f)
+
diff --git a/modules/local/SigProfiler/SigProfiler/main.nf b/modules/local/SigProfiler/SigProfiler/main.nf
@@ -1,7 +1,9 @@
 process SIGPROFILER {
     tag "$meta.id"
     label "process_high"
-    container = 'docker://katiad/sigprofiler:version1.0'
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://katiad/sigprofiler:version1.0' :
+        'docker.io/katiad/sigprofiler:version1.0' }"
 
     input:
         tuple val(meta), path(tsv_list, stageAs: '*.tsv')
@@ -61,7 +63,6 @@ process SIGPROFILER {
     from SigProfilerExtractor import sigpro as sig
     from SigProfilerMatrixGenerator.scripts import SigProfilerMatrixGeneratorFunc as matGen
 
-
     if __name__ == '__main__':
 
         dataset_id = "$meta.dataset"
@@ -72,9 +73,7 @@ process SIGPROFILER {
 
         output_path = os.path.join("output", "SBS", f"{dataset_id}.SBS96.all")
 
-
         # input data preprocessing
-
         def process_tsv_join(tsv_list):
             patients_tsv = tsv_list.split()
             # Read each file into a pandas DataFrame and ensure all columns are of type 'string'

diff --git a/modules/local/SigProfiler/download/main.nf b/modules/local/SigProfiler/download/main.nf
@@ -1,6 +1,8 @@
 process DOWNLOAD_GENOME_SIGPROFILER {
     label "process_single"
-    container = 'docker://katiad/sigprofiler:version1.0'
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://katiad/sigprofiler:version1.0' :
+        'docker.io/katiad/sigprofiler:version1.0' }"
 
     input:
         val(reference_genome) // reference_genome : genome -> for example: GRCh37
@@ -9,7 +11,6 @@ process DOWNLOAD_GENOME_SIGPROFILER {
         path("*"), emit: genome_sigprofiler
         path "versions.yml", emit: versions
 
-
     script:
     """
     SigProfilerMatrixGenerator install $reference_genome -v .