Added 2FAST2Q module (#7318)

* Added 2FAST2Q module * added tests to 2fast2q * added tests to 2fast2q * added tests to 2fast2q * fixed tests to 2fast2q * fixed tests to 2fast2q * Update modules/nf-core/fast2q/tests/main.nf.test Co-authored-by: Simon Pearce <[email protected]> * Update modules/nf-core/fast2q/tests/main.nf.test Co-authored-by: Simon Pearce <[email protected]> * added optional input - hope it is being parsed correctly * fix * fix lack of optional input on tests * fixing in progree * fixing in progress * fixing in progress * fixing in progress * I changed the test data to 2FAST2Q repo data, NOT NF-CORE test data, just as a way to check if it is working. The test data I was using from NF-core has the wrong input file format. * I changed the test data to 2FAST2Q repo data, NOT NF-CORE test data, just as a way to check if it is working. The test data I was using from NF-core has the wrong input file format. * I changed the test data to 2FAST2Q repo data, NOT NF-CORE test data, just as a way to check if it is working. The test data I was using from NF-core has the wrong input file format. * I changed the test data to 2FAST2Q repo data, NOT NF-CORE test data, just as a way to check if it is working. The test data I was using from NF-core has the wrong input file format. * testing if it works with just fastq * Update modules/nf-core/fast2q/main.nf Co-authored-by: Simon Pearce <[email protected]> * added test data and fixed several output issues * fixed the nf.test * fixed the nf.test * fixed the module * moved test data up * direct link to a test data * changed paths to tests * Update modules/nf-core/fast2q/tests/nextflow.config Co-authored-by: Simon Pearce <[email protected]> * Update modules/nf-core/fast2q/tests/main.nf.test Co-authored-by: Simon Pearce <[email protected]> * Update modules/nf-core/fast2q/tests/main.nf.test Co-authored-by: Simon Pearce <[email protected]> * Update modules/nf-core/fast2q/tests/main.nf.test Co-authored-by: Simon Pearce <[email protected]> * changed assertions in test * removed indentation on main 2fast2q cmd as it was not being recognized * everything working locally * everything working locally * everything working locally * everything working locally * everything working locally * everything working locally * enhanced descriptions * updated singularity container * adding a file deleted by accident * Update module * Fix linting * Update meta.yml Updated meta descriptions * Update meta.yml * Update meta.yml * Fix broken test * Update main.nf.test.snap * Update main.nf.test --------- Co-authored-by: Simon Pearce <[email protected]>
nf-core · Jan 30, 2025 · 92aad63 · 92aad63
1 parent 62c2b3e
commit 92aad63
Show file tree

Hide file tree

Showing 8 changed files with 533 additions and 0 deletions.
diff --git a/modules/nf-core/fast2q/environment.yml b/modules/nf-core/fast2q/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::fast2q=2.7.2
diff --git a/modules/nf-core/fast2q/main.nf b/modules/nf-core/fast2q/main.nf
@@ -0,0 +1,67 @@
+process FAST2Q {
+
+    tag "2FAST2Q"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fast2q:2.7.2--pyh7e72e81_0' :
+        'biocontainers/fast2q:2.7.2--pyh7e72e81_0' }"
+
+    input:
+    tuple val(meta), path(fastq)
+    tuple val(meta2), path(library)
+
+    output:
+    tuple val(meta), path("${prefix}.csv")                      , emit: count_matrix
+    tuple val(meta), path("${prefix}_stats.csv")                , emit: stats
+    tuple val(meta), path("${prefix}_distribution_plot.png")    , emit: distribution_plot
+    tuple val(meta), path("${prefix}_reads_plot.png")           , emit: reads_plot
+    tuple val(meta), path("${prefix}_reads_plot_percentage.png"), emit: reads_plot_percentage
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args            = task.ext.args ?: ''
+    prefix              = task.ext.prefix ?: "${meta.id}"
+    def input_file      = (fastq instanceof Path && fastq.exists()) ? "--s ${fastq}" : ''
+    def library_file    = (library instanceof Path && library.exists()) ? "--g ${library}" : ''
+
+    """
+    export MPLCONFIGDIR=\$PWD
+    2fast2q \\
+        -c \\
+        --o ./ \\
+        --fn ${prefix} \\
+        --cp ${task.cpus} \\
+        $input_file \\
+        $library_file \\
+        $args
+
+    mv **/${prefix}* .
+
+    cat <<-END_VERSIONS > versions.yml
+    ${task.process}:
+        2FAST2Q version: \$(2fast2q -v | grep 'Version:' | sed 's/Version: //g')
+    END_VERSIONS
+    """
+
+    stub:
+    prefix              = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch ${prefix}.csv
+    touch ${prefix}_stats.csv
+    touch ${prefix}_distribution_plot.png
+    touch ${prefix}_reads_plot.png
+    touch ${prefix}_reads_plot_percentage.png
+
+    cat <<-END_VERSIONS > versions.yml
+    ${task.process}:
+        2FAST2Q version: \$(2fast2q -v | grep 'Version:' | sed 's/Version: //g')
+    END_VERSIONS
+    """
+
+}
diff --git a/modules/nf-core/fast2q/meta.yml b/modules/nf-core/fast2q/meta.yml
@@ -0,0 +1,98 @@
+name: fast2q
+description: A program that counts sequence occurrences in FASTQ files.
+keywords:
+  - CRISPRi
+  - FASTQ
+  - genomics
+tools:
+  - 2FAST2Q:
+      description: |
+        2FAST2Q is ideal for CRISPRi-Seq, and for extracting and counting any kind of information from reads in the fastq format, such as barcodes in Bar-seq experiments.
+        2FAST2Q can work with sequence mismatches, Phred-score, and be used to find and extract unknown sequences delimited by known sequences.
+        2FAST2Q can extract multiple features per read using either fixed positions or delimiting search sequences.
+      homepage: https://github.com/afombravo/2FAST2Q
+      doi: 10.7717/peerj.14041
+      licence: ["GPL-3.0-or-later"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing output name.
+          e.g. [ id:'test']
+    - fastq:
+        type: directory
+        description: Folder with FASTQ file(s). 2FAST2Q automatically picks up all the FASTQ files inside the provided folder.
+        pattern: "*.{fastq,gz}"
+
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'library_name', multiple_features_per_read:false ]
+    - library:
+        type: file
+        description: .csv library file following the ´Feature_name,sequence´ or ´Feature_name,sequence1:sequence2´ format. See 2FAST2Q instructions for more information.
+        pattern: "*.csv"
+
+output:
+  - count_matrix:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing output name.
+            e.g. [ id:'test' ]
+      - ${prefix}.csv:
+          type: file
+          description: |
+            Count matrix csv file
+  - stats:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing output name.
+            e.g. [ id:'test' ]
+      - ${prefix}_stats.csv:
+          type: file
+          description: |
+            File containing all the relevant statistics such as quality passing reads, aligned reads, total reads, and sample run times.
+  - distribution_plot:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing output name.
+            e.g. [ id:'test' ]
+      - ${prefix}_distribution_plot.png:
+          type: file
+          description: |
+            Violin plot of the distribution of reads per feature across all samples.
+  - reads_plot:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing output name.
+            e.g. [ id:'test' ]
+      - ${prefix}_reads_plot.png:
+          type: file
+          description: |
+            Bar plot with the distribution of reads, in absolute numbers, binned to the different quality metrics indicated in the statistics.csv
+  - reads_plot_percentage:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing output name.
+            e.g. [ id:'test' ]
+      - ${prefix}_reads_plot_percentage.png:
+          type: file
+          description: |
+            Bar plot with the distribution of reads, in percentage, binned to the different quality metrics indicated in the statistics.csv
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@afombravo"
+maintainers:
+  - "@afombravo"
diff --git a/modules/nf-core/fast2q/tests/main.nf.test b/modules/nf-core/fast2q/tests/main.nf.test
@@ -0,0 +1,165 @@
+nextflow_process {
+
+    name "Test Process 2FAST2Q"
+    script "../main.nf"
+    process "FAST2Q"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "fast2q"
+
+    config './nextflow.config'
+
+    test("2FAST2Q self-test") {
+
+        when {
+
+            params {
+                    module_args = '-t'
+                }
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test1' ], // meta map
+                    []
+                ]
+                input[1] = [
+                    [ id:'library_name', multiple_features_per_read:false ], // meta map for second input
+                    []
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                        process.out.count_matrix,
+                        file(process.out.stats[0][1]).name,
+                        file(process.out.distribution_plot[0][1]).name,
+                        file(process.out.reads_plot[0][1]).name,
+                        file(process.out.reads_plot_percentage[0][1]).name,
+                        process.out.versions,                       // versions file
+                        path(process.out.versions[0]).yaml          // Validate against the versions snapshot
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("Extracting and counting all features at position=0 with default length of 20bp from a FASTQ file (without optional library.csv)") {
+
+        when {
+
+            params {
+                module_args = '--mo EC'
+            }
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test1' ], // meta map
+                    file(params.test_data_base + '/data/genomics/mus_musculus/mageck/ERR376998.small.fastq.gz', checkIfExists: true) // FASTQ file
+                ]
+                input[1] = [
+                    [ id:'library_name', multiple_features_per_read:false ], // meta map for second input
+                    []
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success }, // Ensure process ran successfully
+                { assert snapshot(
+                        process.out.count_matrix,
+                        file(process.out.stats[0][1]).name,
+                        file(process.out.distribution_plot[0][1]).name,
+                        file(process.out.reads_plot[0][1]).name,
+                        file(process.out.reads_plot_percentage[0][1]).name,
+                        process.out.versions,                       // versions file
+                        path(process.out.versions[0]).yaml          // Validate against the versions snapshot
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("Extracting all features at position=0 with default length of 20bp from a FASTQ file, and respective alignment to a file with DNA features (library.csv)") {
+
+        when {
+
+            params {
+                module_args = ''
+            }
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test1' ], // meta map
+                    file(params.test_data_base + '/data/genomics/mus_musculus/mageck/ERR376998.small.fastq.gz', checkIfExists: true) // FASTQ file
+                ]
+                input[1] = [
+                    [ id:'library_name', multiple_features_per_read:false ], // meta map for second input
+                    file(params.test_data_base + '/data/genomics/mus_musculus/mageck/yusa_library.csv', checkIfExists: true) // library file
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success }, // Ensure process ran successfully
+                { assert snapshot(
+                        process.out.count_matrix,
+                        file(process.out.stats[0][1]).name,
+                        file(process.out.distribution_plot[0][1]).name,
+                        file(process.out.reads_plot[0][1]).name,
+                        file(process.out.reads_plot_percentage[0][1]).name,
+                        process.out.versions,                       // versions file
+                        path(process.out.versions[0]).yaml          // Validate against the versions snapshot
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("2FAST2Q self-test - stub") {
+        options "-stub"
+        when {
+
+            params {
+            module_args = '-t'
+                }
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test1' ], // meta map
+                    []
+                ]
+                input[1] = [
+                    [ id:'library_name', multiple_features_per_read:false ], // meta map for second input
+                    []
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                        process.out,
+                        path(process.out.versions[0]).yaml // Validate against the versions snapshot
+                    ).match()
+                }
+            )
+        }
+    }
+
+
+}