Added Annosine

.github/workflows/test.yml

@@ -209,6 +209,7 @@ jobs:
           NFT_DIFF: "pdiff"
           NFT_DIFF_ARGS: "--line-numbers --width 120 --expand-tabs=2"
         run: |
+          PROFILE=${{ matrix.profile }}
           NFT_WORKDIR=~ \
           nf-test test \
             --profile=$PROFILE \

cleanNXF.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+rm -rf .nextflow*
+echo "Cleaned .nextflow..."
+rm -rf .nextflow.pid
+echo "Cleaned .nextflow.pid..."
+for i in $(ls work | grep -v "conda");
+do
+    rm -rf "work/$i"
+done
+echo "Cleaned work..."
+
+rm -rf output
+echo "Cleaned output..."
+
+rm -rf .pytest_cache
+echo "Cleaned .pytest_cache..."
+
+rm -rf .nf-test
+echo "Cleaned .nf-test..."
+
+rm -rf ./.nf-test.log

modules/edta-components/annosine/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "annosine"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::annosine2=2.0.7"

modules/edta-components/annosine/main.nf

@@ -0,0 +1,58 @@
+process ANNOSINE {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/annosine2:2.0.7--pyh7cba7a3_0':
+        'biocontainers/annosine2:2.0.7--pyh7cba7a3_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    val mode
+
+    output:
+    tuple val(meta), path("*.fa")       , emit: fa          , optional: true
+    path "versions.yml"                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args ?: ''
+    def prefix  = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '2.0.7' // WARN: Manually update when changing Bioconda assets
+    if ( "$fasta" == "${prefix}.fa" ) error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    AnnoSINE_v2 \\
+        $args \\
+        --threads $task.cpus \\
+        $mode \\
+        $fasta \\
+        $prefix
+
+    mv \\
+        $prefix/Seed_SINE.fa \\
+        ${prefix}.fa \\
+        || echo 'AnnoSINE_v2 did not find SINE sequences. See log for details!'
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        annosine: $VERSION
+    END_VERSIONS
+    """
+
+    stub:
+    def args    = task.ext.args ?: ''
+    def prefix  = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '2.0.7' // WARN: Manually update when changing Bioconda assets
+    if ( "$fasta" == "${prefix}.fa" ) error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    touch ${prefix}.fa
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        annosine: $VERSION
+    END_VERSIONS
+    """
+}

modules/edta-components/annosine/meta.yml

@@ -0,0 +1,50 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "annosine"
+description: Accelerating de novo SINE annotation in plant and animal genomes
+keywords:
+  - genomics
+  - SINE
+  - annotation
+  - plant
+tools:
+  - "annosine":
+      description: "AnnoSINE_v2 - SINE Annotation Tool for Plant and Animal Genomes"
+      homepage: "https://github.com/liaoherui/AnnoSINE_v2"
+      documentation: "https://github.com/liaoherui/AnnoSINE_v2"
+      tool_dev_url: "https://github.com/liaoherui/AnnoSINE_v2"
+      doi: "10.1101/2024.03.01.582874"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1' ]`
+  - fasta:
+      type: file
+      description: Input genome assembly
+      pattern: "*.{fasta,fa,fsa}"
+  - mode:
+      type: integer
+      description: Run mode
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1' ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - fa:
+      type: file
+      description: Non-redundant SINE library with serial number
+      pattern: "*.fa"
+authors:
+  - "@GallVp"
+maintainers:
+  - "@GallVp"

modules/edta-components/annosine/tests/main.nf.test

@@ -0,0 +1,61 @@
+nextflow_process {
+
+    name "Test Process ANNOSINE"
+    script "../main.nf"
+    process "ANNOSINE"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "annosine"
+
+    test("actinidia_chinensis-genome_21_fasta_gz") {
+
+        config './nextflow.config'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.test_data['actinidia_chinensis']['genome']['genome_21_fasta_gz'], checkIfExists: true)
+                ]
+                input[1] = 3
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("actinidia_chinensis-genome_21_fasta_gz-stub") {
+
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.test_data['actinidia_chinensis']['genome']['genome_21_fasta_gz'], checkIfExists: true)
+                ]
+                input[1] = 3
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/edta-components/annosine/tests/nextflow.config

@@ -0,0 +1,5 @@
+process {
+    withName: ANNOSINE {
+        ext.args = '-a 2 -rpm 0 --copy_number 1 --shift 200'
+    }
+}

modules/edta-components/annosine/tests/tags.yml

@@ -0,0 +1,2 @@
+annosine:
+  - "modules/edta-components/annosine/**"

tests/config/test_data.config

@@ -46,7 +46,7 @@ params {
                 kofamscan_ko_list_gz                           = "${params.test_data_base}/data/genomics/sarscov2/genome/db/kofamscan/ko_list.gz"
 
                 metamaps_db                                    = "${params.test_data_base}/data/genomics/sarscov2/genome/db/metamaps_db.tar.gz"
-                
+
                 ncbi_taxmap_zip                                = "${params.test_data_base}/data/genomics/sarscov2/genome/db/maltextract/ncbi_taxmap.zip"
                 taxon_list_txt                                 = "${params.test_data_base}/data/genomics/sarscov2/genome/db/maltextract/taxon_list.txt"
 
@@ -655,7 +655,7 @@ params {
             'genome' {
                 samplesheet                     = "${params.test_data_base}/data/genomics/eukaryotes/saccharomyces_cerevisiae/samplesheet.csv"
                 genome_gfp_gtf                  = "${params.test_data_base}/data/genomics/eukaryotes/saccharomyces_cerevisiae/genome_gfp.gtf"
-		        kallisto_results                = "${params.test_data_base}/data/genomics/eukaryotes/saccharomyces_cerevisiae/kallisto_results.tar.gz"
+                kallisto_results                = "${params.test_data_base}/data/genomics/eukaryotes/saccharomyces_cerevisiae/kallisto_results.tar.gz"
                 salmon_results                  = "${params.test_data_base}/data/genomics/eukaryotes/saccharomyces_cerevisiae/salmon_results.tar.gz"
             }
         }