New modules Gprofiler2/gconvert

modules/nf-core/gprofiler2/gconvert/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::r-gprofiler2=0.2.4

modules/nf-core/gprofiler2/gconvert/main.nf

@@ -0,0 +1,37 @@
+process GPROFILER2_GCONVERT {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'oras://community.wave.seqera.io/library/r-gprofiler2:0.2.4--ada5695b0be8ddbc':
+        'community.wave.seqera.io/library/r-gprofiler2:0.2.4--c87811ab729aa1b3' }"
+
+    input:
+    tuple val(meta), path(ids_tsv), val(target)
+
+    output:
+    tuple val(meta), path("*.gprofiler2.gconvert.tsv"), emit: converted_ids
+    tuple val(meta), path("*R_sessionInfo.log")        , emit: session_info
+    path "versions.yml"                                , emit: versions, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'gprofiler2_gconvert.R'
+
+    stub:
+    def prefix = task.ext.prefix ?: meta.id
+    """
+    touch ${prefix}.gprofiler2.gconvert.tsv
+    touch ${prefix}.R_sessionInfo.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        r-base: \$(Rscript -e "cat(strsplit(R.version[['version.string']], ' ')[[1]][3])")
+        r-gprofiler2: \$(Rscript -e "cat(as.character(packageVersion('gprofiler2')))")
+        gprofiler-data: \$(Rscript -e "cat(gprofiler2::get_version_info()[['gprofiler_version']])")
+    END_VERSIONS
+    """
+}

modules/nf-core/gprofiler2/gconvert/meta.yml

@@ -0,0 +1,73 @@
+name: "gprofiler2_gconvert"
+description: Convert gene and feature identifiers with gProfiler g:Convert
+keywords:
+  - gprofiler2
+  - gconvert
+  - identifier conversion
+  - gene ids
+tools:
+  - "gprofiler2":
+      description: "An R package for gene list functional enrichment analysis and namespace conversion with g:Profiler."
+      homepage: "https://biit.cs.ut.ee/gprofiler/page/r"
+      documentation: "https://cran.r-project.org/package=gprofiler2"
+      tool_dev_url: "https://github.com/gprofiler/gprofiler2"
+      doi: "10.1093/bioinformatics/btab213"
+      licence:
+        - "GPL-3.0-or-later"
+      identifier: biotools:gprofiler
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - ids_tsv:
+        type: file
+        description: TSV, TXT, or CSV table containing input IDs in the first column.
+        pattern: "*.{tsv,txt,csv}"
+        ontologies:
+          - edam: http://edamontology.org/format_3475 # TSV
+          - edam: http://edamontology.org/format_3752 # CSV
+    - target:
+        type: string
+        description: Target namespace to pass to gprofiler2::gconvert().
+output:
+  converted_ids:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*.gprofiler2.gconvert.tsv":
+          type: file
+          description: TSV table returned by gprofiler2::gconvert().
+          pattern: "*.gprofiler2.gconvert.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475 # TSV
+  session_info:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*R_sessionInfo.log":
+          type: file
+          description: R session information.
+          pattern: "*R_sessionInfo.log"
+          ontologies: []
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750 # YAML
+topics:
+  versions:
+    - versions.yml:
+        type: string
+        description: File containing software versions
+authors:
+  - "@Schansiate"
+maintainers:
+  - "@Schansiate"

modules/nf-core/gprofiler2/gconvert/templates/gprofiler2_gconvert.R

@@ -0,0 +1,209 @@
+#!/usr/bin/env Rscript
+
+#written by Mo Tan (https://github.com/Schansiate) modified from original script by Oliver Wacker (https://github.com/WackerO)
+
+# MIT License
+
+# Copyright (c) QBiC
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+################################################
+################################################
+## Functions                                  ##
+################################################
+################################################
+
+#' Parse out options from a string without recourse to optparse
+#'
+#' @param x Long-form argument list like --opt1 val1 --opt2 val2
+#'
+#' @return named list of options and values similar to optparse
+
+parse_args <- function(x) {
+    args_list <- unlist(strsplit(x, ' ?--')[[1]])[-1]
+    args_vals <- lapply(args_list, function(x) scan(text=x, what='character', quiet = TRUE))
+
+    # Ensure the option vectors are length 2 (key/ value) to catch empty ones
+    args_vals <- lapply(args_vals, function(z) { length(z) <- 2; z})
+
+    parsed_args <- structure(lapply(args_vals, function(x) x[2]), names = lapply(args_vals, function(x) x[1]))
+    parsed_args[! is.na(parsed_args)]
+}
+
+#' Flexibly read CSV or TSV files
+#'
+#' @param file Input file
+#' @param header Passed to read.delim()
+#' @param row.names Passed to read.delim()
+#'
+#' @return output Data frame
+
+read_delim_flexible <- function(file, header = TRUE, row.names = NULL, check.names = FALSE) {
+
+    ext <- tolower(tail(strsplit(basename(file), split = "\\\\.")[[1]], 1))
+
+    if (ext == "tsv" || ext == "txt") {
+        separator <- "\\t"
+    } else if (ext == "csv") {
+        separator <- ","
+    } else {
+        stop(paste("Unknown separator for", ext))
+    }
+
+    read.delim(
+        file,
+        sep = separator,
+        header = header,
+        row.names = row.names,
+        check.names = check.names
+    )
+}
+
+################################################
+################################################
+## PARSE PARAMETERS FROM NEXTFLOW             ##
+################################################
+################################################
+
+opt <- list(
+    ids_tsv = '$ids_tsv',
+    target = '$target',
+    organism = 'hsapiens',
+    numeric_ns = '',
+    mthreshold = Inf,
+    filter_na = TRUE,
+    output_prefix = ifelse('$task.ext.prefix' == 'null', '$meta.id', '$task.ext.prefix')
+)
+
+opt_types <- lapply(opt, class)
+
+args_opt <- parse_args('$task.ext.args')
+allowed_args <- c('organism', 'numeric_ns', 'mthreshold', 'filter_na')
+for (ao in names(args_opt)) {
+    if (! ao %in% allowed_args) {
+        stop(paste("Invalid option:", ao))
+    } else {
+        if (! is.null(opt[[ao]])) {
+            args_opt[[ao]] <- as(args_opt[[ao]], opt_types[[ao]])
+        }
+        opt[[ao]] <- args_opt[[ao]]
+    }
+}
+
+required_opts <- c('ids_tsv', 'target', 'output_prefix')
+missing <- required_opts[unlist(lapply(opt[required_opts], is.null)) | ! required_opts %in% names(opt)]
+
+if (length(missing) > 0) {
+    stop(paste("Missing required options:", paste(missing, collapse=', ')))
+}
+
+if (opt\$target == "") {
+    stop("Please provide target.")
+}
+
+if (! file.exists(opt\$ids_tsv)) {
+    stop(paste0('Value of ids_tsv: ', opt\$ids_tsv, ' is not a valid file'))
+}
+
+################################################
+################################################
+## Finish loading libraries                   ##
+################################################
+################################################
+
+library(gprofiler2)
+
+################################################
+################################################
+## READ IDS AND RUN GCONVERT                  ##
+################################################
+################################################
+
+ids_table <- read_delim_flexible(
+    file = opt\$ids_tsv
+)
+
+if (ncol(ids_table) < 1) {
+    stop("The input ID table must contain at least one column.")
+}
+
+output_prefix <- paste0(opt\$output_prefix, ".gprofiler2")
+output_file <- paste(output_prefix, 'gconvert', 'tsv', sep = '.')
+
+query <- as.character(ids_table[[1]])
+query <- query[!is.na(query) & query != ""]
+
+if (length(query) > 0) {
+    gconvert_results <- gconvert(
+        query = query,
+        organism = opt\$organism,
+        target = opt\$target,
+        numeric_ns = opt\$numeric_ns,
+        mthreshold = opt\$mthreshold,
+        filter_na = opt\$filter_na
+    )
+
+    write.table(
+        gconvert_results,
+        file = output_file,
+        col.names = TRUE,
+        row.names = FALSE,
+        sep = '\t',
+        quote = FALSE
+    )
+} else {
+    print("No input IDs found, gProfiler2 g:Convert will be skipped.")
+    file.create(output_file)
+}
+
+################################################
+################################################
+## R SESSION INFO                             ##
+################################################
+################################################
+
+sink("R_sessionInfo.log")
+print(sessionInfo())
+sink()
+
+################################################
+################################################
+## VERSIONS FILE                              ##
+################################################
+################################################
+
+r.version <- strsplit(version[['version.string']], ' ')[[1]][3]
+gprofiler2.version <- as.character(packageVersion('gprofiler2'))
+gprofiler_data.version <- gprofiler2::get_version_info(opt[["organism"]])[["gprofiler_version"]]
+
+writeLines(
+    c(
+        '"$task.process":',
+        paste0('    r-base: ', r.version),
+        paste0('    r-gprofiler2: ', gprofiler2.version),
+        paste0('    gprofiler-data: ', gprofiler_data.version)
+    ),
+    con = 'versions.yml'
+)
+
+################################################
+################################################
+################################################
+################################################

modules/nf-core/gprofiler2/gconvert/tests/input_ids.tsv

@@ -0,0 +1,5 @@
+id
+Klf4
+Pax5
+Sox2
+Nanog