Merge branch 'master' into seqkit-2.9.0-part-2

modules/nf-core/immunedeconv/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::r-immunedeconv=2.1.2

modules/nf-core/immunedeconv/main.nf

@@ -0,0 +1,37 @@
+process IMMUNEDECONV {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/22/22cb85f1b69ceff45b83e0fdb7b96d9ae29c8aafeaa0707d64cc4628982977ab/data' :
+    'community.wave.seqera.io/library/r-immunedeconv:2.1.2--e1bb1ea1cf505cb3' }"
+
+    input:
+    tuple val(meta), path(input_file), val(method), val(function)
+    val gene_symbol_col
+
+    output:
+    tuple val(meta), path("*.deconvolution_results.tsv"), emit: deconv_table
+    tuple val(meta), path("*.png"),                       emit: deconv_plots, optional: true
+    path "versions.yml",                                  emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'immunedeconv.R'
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.deconvolution_results.tsv
+    touch ${prefix}.plot1_stacked_bar_chart.png
+    touch ${prefix}.plot2_points_with_facets.png
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        r-immunedeconv: \$(Rscript -e "cat(as.character(packageVersion('immunedeconv')))")
+    END_VERSIONS
+    """
+}

modules/nf-core/immunedeconv/meta.yml

@@ -0,0 +1,67 @@
+name: immunedeconv
+description: Perform immune cell deconvolution using RNA-seq data and various computational methods.
+keywords:
+  - Immune Deconvolution
+  - RNA-seq
+  - Bioinformatics Tools
+  - Computational Immunology
+tools:
+  - immunedeconv:
+      description: |
+        The immunedeconv R package provides functions for immune cell deconvolution
+        from RNA-seq data. It supports multiple deconvolution methods and generates
+        results as well as visualizations.
+      homepage: https://github.com/icbi-lab/immunedeconv
+      documentation: https://icbi-lab.github.io/immunedeconv/
+      licence: ["GPL-2"]
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - input_file:
+        type: file
+        description: Input matrix with genes in rows and samples in columns.
+        pattern: "*.tsv"
+    - method:
+        type: string
+        description: The deconvolution method to use (e.g., 'CIBERSORT', 'EPIC', 'xCell').
+    - function:
+        type: string
+        description: The specific function from immunedeconv to execute for analysis.
+  - - gene_symbol_col:
+        type: string
+        description: Column name for gene symbols in the matrix input file.
+output:
+  - deconv_table:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.deconvolution_results.tsv":
+          type: file
+          description: Results table containing deconvolution data.
+          pattern: "*.deconvolution_results.tsv"
+  - deconv_plots:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.png":
+          type: file
+          description: Visualization plots generated during deconvolution.
+          pattern: "*.png"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@grst"
+  - "@nschcolnicov"
+maintainers:
+  - "@grst"
+  - "@nschcolnicov"

modules/nf-core/immunedeconv/templates/immunedeconv.R

@@ -0,0 +1,89 @@
+#!/usr/bin/env Rscript
+
+library(dplyr)
+library(ggplot2)
+library(tidyr)
+library(immunedeconv)
+library(tibble)
+library(readr)
+
+#Load prefix
+prefix = ifelse('$task.ext.prefix' == 'null', '$meta.id', '$task.ext.prefix')
+
+# Load the TSV file and keep only $gene_symbol_col column + counts
+gene_expression_matrix <- readr::read_tsv('$input_file') %>%
+    as.data.frame() %>%
+    dplyr::select(
+        dplyr::all_of('$gene_symbol_col'), # Keep the '$gene_symbol_col' column
+        where(~ !is.character(.))    # Include all non-string columns
+    ) %>%
+    tibble::column_to_rownames('$gene_symbol_col')
+
+# Check if the data is log-transformed or TPM-transformed
+# Check range of values
+min_value <- min(gene_expression_matrix, na.rm = TRUE)
+max_value <- max(gene_expression_matrix, na.rm = TRUE)
+
+# Detect log-transformed data (values typically within a compressed range)
+if (max_value < 100 && min_value >= 0) {
+    warning("The data appears to be log-transformed. Please provide TPM-transformed data.")
+}
+
+# Detect TPM-transformed data (column sums should be close to 1,000,000)
+column_sums <- colSums(gene_expression_matrix, na.rm = TRUE)
+if (!all(abs(column_sums - 1e6) < 1e4)) {
+    warning("The data does not appear to be properly TPM-transformed. Ensure the data is normalized.")
+}
+
+# Generate results
+result <- immunedeconv::${function}(gene_expression_matrix, method = '$method')
+
+# Save the result to a CSV file
+readr::write_tsv(result, paste0(prefix,'.deconvolution_results.tsv'))
+
+# Plot and save results
+# Plot 1: Stacked bar chart
+plot1 <- result %>%
+    gather(sample, fraction, -cell_type) %>%
+    ggplot(aes(x = sample, y = fraction, fill = cell_type)) +
+    geom_bar(stat = 'identity') +
+    coord_flip() +
+    scale_fill_brewer(palette = 'Paired') +
+    scale_x_discrete(limits = rev(levels(result)))
+
+# Save Plot 1
+ggsave(paste0(prefix,'.plot1_stacked_bar_chart.png'), plot = plot1, dpi = 300, width = 10, height = 8)
+
+# Plot 2: Points with facets
+plot2 <- result %>%
+    gather(sample, score, -cell_type) %>%
+    ggplot(aes(x = sample, y = score, color = cell_type)) +
+    geom_point(size = 4) +
+    facet_wrap(~cell_type, scales = 'free_x', ncol = 3) +
+    scale_color_brewer(palette = 'Paired', guide = FALSE) +
+    coord_flip() +
+    theme_bw() +
+    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1))
+
+# Save Plot 2
+ggsave(paste0(prefix,'.plot2_points_with_facets.png'), plot = plot2, dpi = 300, width = 12, height = 10)
+
+################################################
+################################################
+## VERSIONS FILE                              ##
+################################################
+################################################
+
+immunedeconv_version <- as.character(packageVersion('immunedeconv'))
+
+writeLines(
+    c(
+        '"${task.process}":',
+        paste('    r-immunedeconv:', immunedeconv_version)
+    ),
+'versions.yml')
+
+################################################
+################################################
+################################################
+################################################

modules/nf-core/immunedeconv/tests/main.nf.test

@@ -0,0 +1,107 @@
+nextflow_process {
+
+    name "Test Process IMMUNEDECONV"
+    script "../main.nf"
+    process "IMMUNEDECONV"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "immunedeconv"
+
+    test("test_immunedeconv_bulkmat") {
+
+        when {
+            process {
+                """
+                input[0] = [ [id:"immunedeconv"], file(params.modules_testdata_base_path + 'genomics/mus_musculus/rnaseq_expression/bulk_mat.tsv', checkIfExists: true), "quantiseq", "deconvolute" ]
+                input[1] = "gene_symbol"
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                    process.out.deconv_table,
+                    process.out.deconv_plots[0][1].collect{ file(it).name }, //assert unstable file
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("test_immunedeconv_custom_data_mouse") {
+
+        when {
+            process {
+                """
+                input[0] = [ [id:"immunedeconv"], file(params.modules_testdata_base_path + 'genomics/mus_musculus/rnaseq_expression/bulk_mat_mouse.tsv', checkIfExists: true), "mmcp_counter", "deconvolute_mouse" ]
+                input[1] = "gene_symbol"
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                    process.out.deconv_table,
+                    process.out.deconv_plots[0][1].collect{ file(it).name }, //assert unstable file
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("test_immunedeconv_bulkmat_mouse") {
+
+        when {
+            process {
+                """
+                input[0] = [ [id:"immunedeconv"], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/mus_musculus/rnaseq_expression/SRP254919.salmon.merged.gene_counts.top1000cov.tsv', checkIfExists: true), "mmcp_counter", "deconvolute_mouse" ]
+                input[1] = "gene_name"
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                    process.out.deconv_table,
+                    process.out.deconv_plots[0][1].collect{ file(it).name }, //assert unstable file
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("test_immunedeconv - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [ [id:"immunedeconv"], file(params.modules_testdata_base_path + 'genomics/mus_musculus/rnaseq_expression/bulk_mat.tsv', checkIfExists: true), "quantiseq", "deconvolute" ]
+                input[1] = "gene_symbol"
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                    process.out.deconv_table,
+                    process.out.deconv_plots[0][1].collect{ file(it).name }, //assert unstable file
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+}