Change the workflow to take MAGeCK MLE as a default and add tests

.github/workflows/ci.yml

@@ -29,8 +29,10 @@ jobs:
         ANALYSIS:
           - "test_screening"
           - "test_screening_paired"
+          - "test_screening_rra"
           - "test_targeted"
           - "test_umis"
+
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v3

conf/modules.config

@@ -173,6 +173,14 @@ process {
         ]
     }
 
+    withName: MATRICESCREATION {
+        publishDir = [
+            path: { "${params.outdir}/design_matrix" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: MINIMAP2_ALIGN_UMI_1 {
         ext.args = '-x map-ont'
         ext.prefix = { "${reads.baseName}_cycle1" }

conf/test_screening.config

@@ -23,7 +23,6 @@ params {
     input             = 'https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/samplesheet_test.csv'
     analysis          = 'screening'
     crisprcleanr      = "Brunello_Library"
-    mle_design_matrix = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/design_matrix.txt"
     library           = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/brunello_target_sequence.txt"
-    rra_contrasts     = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/rra_contrasts.txt"
+    contrasts         = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/rra_contrasts.txt"
 }

conf/test_screening_rra.config

@@ -0,0 +1,29 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/crisprseq -profile test_screening_rra,<conda/docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test screening profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input             = 'https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/samplesheet_test.csv'
+    analysis          = 'screening'
+    crisprcleanr      = "Brunello_Library"
+    library           = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/brunello_target_sequence.txt"
+    contrasts         = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/rra_contrasts.txt"
+    rra               = true
+}

modules/local/matricescreation.nf

@@ -0,0 +1,53 @@
+process MATRICESCREATION {
+    label 'process_single'
+
+    conda 'r-ggplot2=3.4.3 bioconductor-shortread=1.58.0 r-ggpubr=0.6.0 r-ggmsa=1.0.2 r-seqmagick=0.1.6 r-tidyr=1.3.0 r-ggseqlogo=0.1 r-cowplot=1.1.1 r-seqinr=4.2_30 r-optparse=1.7.3 r-dplyr=1.1.2 r-plyr=1.8.8 r-stringr=1.5.0 r-plotly=4.10.2'
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-6de07928379e6eface08a0019c4a1d6b5192e805:0d77388f37ddd923a087f7792e30e83ab54c918c-0' :
+        'biocontainers/mulled-v2-6de07928379e6eface08a0019c4a1d6b5192e805:0d77388f37ddd923a087f7792e30e83ab54c918c-0' }"
+
+    input:
+    path(contrasts)
+
+    output:
+    path("*.txt"), emit: design_matrix
+   // path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+
+    """
+    #!/usr/bin/env Rscript
+    #### author: Laurence Kuhlburger
+    #### Released under the MIT license. See git repository (https://github.com/nf-core/crisprseq) for full license text.
+    ####
+    #### Orient a reference sequence according to reads orientation.
+
+    data <- read.table("$contrasts", header = TRUE, sep = ";", stringsAsFactors = FALSE)
+    print(data)
+    # Loop through each row in the data
+    for (i in 1:nrow(data)) {
+        # Extract control and treatment samples for the current row
+        control_samples <- unlist(strsplit(data\$reference[i], ","))
+        treatment_samples <- unlist(strsplit(data\$treatment[i], ","))
+
+        # Create a vector of all unique samples
+        all_samples <- unique(c(control_samples, treatment_samples))
+
+        # Initialize a matrix to store the design matrix
+        design_matrix <- data.frame(matrix(0, nrow = length(all_samples), ncol = 3,
+                        dimnames = list(all_samples, c("Samples", "baseline", paste0(gsub(',', '_', data\$treatment[i] ),"_vs_", data\$reference[i])))))
+
+        # Set baseline and treatment values in the design matrix
+        design_matrix[, "Samples"] <- rownames(design_matrix)
+        design_matrix\$baseline <- 1
+        design_matrix[treatment_samples, paste0(gsub(',', '_', data\$treatment[1] ),"_vs_",gsub(",","_",data\$reference[i]))] <- 1
+
+        # Print the design matrix to a file
+        output_file <- paste0(gsub(',', '_', data\$treatment[1] ),"_vs_",gsub(",","_",data\$reference[i]),".txt")
+        write.table(design_matrix, output_file, sep = "\t", quote = FALSE, row.names=FALSE)
+    }
+    """
+}

nextflow.config

@@ -16,11 +16,12 @@ params {
     protospacer                = null
     library                    = null
     crisprcleanr               = null
-    rra_contrasts              = null
+    contrasts                  = null
     mle_design_matrix          = null
     count_table                = null
     min_reads                  = 30
     min_targeted_genes         = 3
+    rra                        = false
     bagel_reference_essentials =    'https://raw.githubusercontent.com/hart-lab/bagel/master/CEGv2.txt'
     bagel_reference_nonessentials = 'https://raw.githubusercontent.com/hart-lab/bagel/master/NEGv1.txt'
 
@@ -199,6 +200,7 @@ profiles {
     test_screening_full   { includeConfig 'conf/test_screening_full.config' }
     test_screening        { includeConfig 'conf/test_screening.config' }
     test_screening_paired { includeConfig 'conf/test_screening_paired.config' }
+    test_screening_rra    { includeConfig 'conf/test_screening_rra.config' }
 }
 
 // Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile

nextflow_schema.json

@@ -156,12 +156,16 @@
                     "exists": true,
                     "description": "Design matrix used for MAGeCK MLE to call essential genes under multiple conditions while considering sgRNA knockout efficiency"
                 },
-                "rra_contrasts": {
+                "contrasts": {
                     "type": "string",
                     "format": "file-path",
                     "exists": true,
                     "description": "Comma-separated file with the conditions to be compared. The first one will be the reference (control)"
                 },
+                "rra": {
+                    "type": "boolean",
+                    "description": "Parameter in case MAGeCK RRA should be ran instead of MAGeCK MLE."
+                },
                 "count_table": {
                     "type": "string",
                     "format": "file-path",

workflows/crisprseq_screening.nf

@@ -24,6 +24,14 @@ if(params.mle_design_matrix) {
         .set { ch_design }
 }
 
+if(params.rra && params.mle_design_matrix) {
+    warning "mle_design_matrix will only be used for the MAGeCK MLE computations"
+    }
+
+if(params.rra && !params.contrasts) {
+    error "Please also provide the contrasts table to compare the samples for MAGeCK RRA"
+    }
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     CONFIG FILES
@@ -66,6 +74,7 @@ include { BAGEL2_FC                   } from '../modules/local/bagel2/fc'
 include { BAGEL2_BF                   } from '../modules/local/bagel2/bf'
 include { BAGEL2_PR                   } from '../modules/local/bagel2/pr'
 include { BAGEL2_GRAPH                } from '../modules/local/bagel2/graph'
+include { MATRICESCREATION            } from '../modules/local/matricescreation'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -157,8 +166,8 @@ workflow CRISPRSEQ_SCREENING {
         }.set { ch_counts }
     }
 
-    if(params.rra_contrasts) {
-        Channel.fromPath(params.rra_contrasts)
+    if(params.rra) {
+        Channel.fromPath(params.contrasts)
             .splitCsv(header:true, sep:';' )
             .set { ch_contrasts }
         counts = ch_contrasts.combine(ch_counts)
@@ -175,8 +184,8 @@ workflow CRISPRSEQ_SCREENING {
         ch_versions = ch_versions.mix(MAGECK_GRAPHRRA.out.versions)
     }
 
-    if(params.rra_contrasts) {
-        Channel.fromPath(params.rra_contrasts)
+    if(params.contrasts && params.rra) {
+        Channel.fromPath(params.contrasts)
             .splitCsv(header:true, sep:';' )
             .set { ch_bagel }
     counts = ch_bagel.combine(ch_counts)
@@ -216,8 +225,14 @@ workflow CRISPRSEQ_SCREENING {
 
     }
 
-    if(params.mle_design_matrix) {
-        ch_mle = ch_counts.combine(ch_design)
+    if((params.mle_design_matrix) || (params.contrasts && !rra)) {
+        if(params.mle_design_matrix) {
+            ch_mle = ch_counts.combine(ch_design)
+            }
+        if(params.contrasts) {
+            MATRICESCREATION(params.contrasts)
+            ch_mle = ch_counts.combine(MATRICESCREATION.out.design_matrix)
+        }
         ch_mle.map {
             it -> [[id: it[1].getBaseName()], it[0], it[1]]
         }.set { ch_designed_mle }