Tcoffee tcs

modules/nf-core/tcoffee/tcs/environment.yml

@@ -0,0 +1,10 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "tcoffee_tcs"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::t-coffee=13.46.0.919e8c6b"
+  - conda-forge::pigz=2.8

modules/nf-core/tcoffee/tcs/main.nf

@@ -0,0 +1,75 @@
+process TCOFFEE_TCS {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-a76a981c07359a31ff55b9dc13bd3da5ce1909c1:84c8f17f1259b49e2f7783b95b7a89c6f2cb199e-0':
+        'biocontainers/mulled-v2-a76a981c07359a31ff55b9dc13bd3da5ce1909c1:84c8f17f1259b49e2f7783b95b7a89c6f2cb199e-0' }"
+
+    input:
+    tuple val(meta), path(msa)
+    tuple val(meta2), path(lib)
+
+    output:
+    tuple val(meta), path("*.tcs")   , emit: tcs
+    tuple val(meta), path("*.scores"), emit: scores
+    path "versions.yml"              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args          = task.ext.args ?: ''
+    def prefix        = task.ext.prefix ?: "${meta.id}"
+    def lib_arg       = lib ? "-lib ${lib}" : ""
+    def header        = meta.keySet().join(",")
+    def values        = meta.values().join(",")
+    def unzipped_name = msa.toString() - '.gz'
+    """
+    export TEMP='./'
+    filename=${msa}
+    if [[ \$(basename $msa) == *.gz ]] ; then
+        unpigz -f $msa
+        filename=${unzipped_name}
+    fi
+
+    # Bad hack to circumvent t_coffee bug
+    # Issue described already in: https://github.com/cbcrg/tcoffee/issues/3
+    # Add an A in front of filename if the file begins with A
+    first_letter_filename=\${filename:0:1}
+    if [ "\$first_letter_filename" == "A" ]; then input="A"\$filename; else input=\$filename;  fi
+
+    t_coffee -infile \$input \
+        -evaluate -output=score_ascii \
+        ${lib_arg} \
+        -outfile ${prefix}.tcs
+
+    # Add metadata info to output file
+    echo "${header},TCS" > "${prefix}.scores"
+
+    # Add values
+    scores=\$(grep 'SCORE=' ${prefix}.tcs | cut -d '=' -f 2 )
+    echo "${values},\$scores" >> "${prefix}.scores"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        tcoffee: \$( t_coffee -version | awk '{gsub("Version_", ""); print \$3}')
+        pigz: \$(echo \$(pigz --version 2>&1) | sed 's/^.*pigz\\w*//' ))
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.tcs
+    touch ${prefix}.scores
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        tcoffee: \$( t_coffee -version | awk '{gsub("Version_", ""); print \$3}')
+        pigz: \$(echo \$(pigz --version 2>&1) | sed 's/^.*pigz\\w*//' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/tcoffee/tcs/main.nf.test

@@ -0,0 +1,29 @@
+nextflow_process {
+
+    name "Test Process TCOFFEE_TCS"
+    script "modules/nf-core/tcoffee/tcs/main.nf"
+    process "TCOFFEE_TCS"
+
+    test("Should run without failures") {
+
+        when {
+            params {
+                // define parameters here. Example:
+                // outdir = "tests/results"
+            }
+            process {
+                """
+                // define inputs of the process here. Example:
+                // input[0] = file("test-file.txt")
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assert snapshot(process.out).match()
+        }
+
+    }
+
+}

modules/nf-core/tcoffee/tcs/meta.yml

@@ -0,0 +1,57 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "tcoffee_tcs"
+description: Compute the TCS score for a MSA or for a MSA plus a library file. Outputs the tcs as it is and a csv with just the total TCS score.
+keywords:
+  - alignment
+  - MSA
+  - evaluation
+tools:
+  - "tcoffee":
+      description: "A collection of tools for Multiple Alignments of DNA, RNA, Protein Sequence"
+      homepage: "http://www.tcoffee.org/Projects/tcoffee/"
+      documentation: "https://tcoffee.readthedocs.io/en/latest/tcoffee_main_documentation.html"
+      tool_dev_url: "https://github.com/cbcrg/tcoffee"
+      doi: "10.1006/jmbi.2000.4042"
+      licence: ["GPL v3"]
+  - "pigz":
+      description: "Parallel implementation of the gzip algorithm."
+      homepage: "https://zlib.net/pigz/"
+      documentation: "https://zlib.net/pigz/pigz.pdf"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', ... ]
+  - msa:
+      type: file
+      description: fasta file containing the alignment to be evaluated. May be gzipped or uncompressed.
+      pattern: "*.{aln,fa,fasta,fas}{.gz,}"
+  - lib:
+      type: file
+      description: lib file containing the alignment library of the given msa.
+      pattern: "*{.tc_lib,*_lib}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - tcs:
+      type: file
+      description: The msa represented in tcs format, prepended with TCS scores
+      pattern: "*.tcs"
+  - scores:
+      type: file
+      description: a file containing the score of the alignment in csv format
+      pattern: "*.scores"
+
+authors:
+  - "@alessiovignoli"

modules/nf-core/tcoffee/tcs/tests/lib.config

@@ -0,0 +1,5 @@
+process {
+    withName: "TCOFFEE_ALIGN"{
+        ext.args = { "-output fasta_aln -out_lib=sample_lib1.tc_lib" }
+    }
+}

modules/nf-core/tcoffee/tcs/tests/main.nf.test

@@ -0,0 +1,114 @@
+nextflow_process {
+
+    name "Test Process TCOFFEE_TCS"
+    script "../main.nf"
+    process "TCOFFEE_TCS"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "tcoffee"
+    tag "tcoffee/tcs"
+    tag "pigz/compress"
+    tag "tcoffee/align"
+
+    test("tcs - msa") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], 
+                    file("https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/setoxin.ref", checkIfExists: true)
+                    ]
+                input[1] = [
+                    [ id:'test'],
+                    []
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("tcs - msa - compressed") {
+
+        setup {
+            run("PIGZ_COMPRESS") {
+                script "../../../pigz/compress/main.nf"
+                process {
+                    """
+                    input[0] = [ [ id:'test' ],
+                                file("https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/setoxin.ref", checkIfExists: true)
+                               ]
+
+                    """
+                }
+            }        
+        }
+
+        when {
+            process {
+                """
+                input[0] = PIGZ_COMPRESS.out.archive.map { it -> [[ id:'test'], it[1]] }
+                input[1] = [
+                    [ id:'test'],
+                    []
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("tcs - msa - lib") {
+
+        config "./lib.config"
+
+        setup {
+            run("TCOFFEE_ALIGN") {
+                script "../../align/main.nf"
+                process {
+                    """
+                    input[0] = [ [ id:'test' ],
+                             file("https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/setoxin-ref.fa", checkIfExists: true)
+                           ]
+                    input[1] = [[:],[]]
+                    input[2] = [[:],[],[]]
+                    input[3] = true
+                    """
+                }
+            }        
+        }
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], 
+                    file("https://raw.githubusercontent.com/nf-core/test-datasets/multiplesequencealign/testdata/setoxin.ref", checkIfExists: true)
+                    ]
+                input[1] = TCOFFEE_ALIGN.out.lib.map { it -> [[  id:'test' ], it[1]] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}