Bbmap filterbyname (#2206)

* Added bbmap/filterbyname module

* updated tests/config/pytest_modules.yml

* Formatting

* [automated] Fix linting with Prettier

* removed white spaces

* 1) Added an option for interleaved output into args
2) Output extension is now also controlled by args

* Removed TO-DO strings + reverted gitignore file

* output now depends on "output_extension"

* 1) Added more tests
2) Removed "names" entirely (should be passed inside `args` if needed
)

* Update modules/nf-core/bbmap/filterbyname/main.nf

Co-authored-by: FriederikeHanssen <[email protected]>

* FIxed typo (me5sum -> md5sum)

* [automated] Fix linting with Prettier

* 1) Changed container
2) Fixed tests

* [automated] Fix linting with Prettier

* Update main.nf

Try grepping to remove the odd extra text on the singularity test

* Updated version with nf-test

* Update meta

* Address review comments

---------

Co-authored-by: nf-core-bot <[email protected]>
Co-authored-by: FriederikeHanssen <[email protected]>
Co-authored-by: Simon Pearce <[email protected]>
Co-authored-by: Fabian Egli <[email protected]>
Co-authored-by: Matthias De Smet <[email protected]>

.gitignore

@@ -15,4 +15,3 @@ test_output/
 tests/data/
 work/
 .github/CODEOWNERS-tmp
-

modules/nf-core/bbmap/filterbyname/environment.yml

@@ -0,0 +1,7 @@
+name: bbmap_filterbyname
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::bbmap=39.01

modules/nf-core/bbmap/filterbyname/main.nf

@@ -0,0 +1,71 @@
+process BBMAP_FILTERBYNAME {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bbmap:39.01--h5c4e2a8_0':
+        'biocontainers/bbmap:39.01--h5c4e2a8_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    val(names_to_filter)
+    val(output_format)
+    val(interleaved_output)
+
+    output:
+    tuple val(meta), path("*.${output_format}"), emit: reads
+    tuple val(meta), path('*.log')             , emit: log
+    path "versions.yml"                        , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input  = meta.single_end ? "in=${reads}" : "in=${reads[0]} in2=${reads[1]}"
+    def output = (meta.single_end || interleaved_output) ?
+        "out=${prefix}.${output_format}" :
+        "out1=${prefix}_1.${output_format} out2=${prefix}_2.${output_format}"
+    def names_command = names_to_filter ? "names=${names_to_filter}": ""
+
+    def avail_mem = 3
+    if (!task.memory) {
+        log.info '[filterbyname] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
+    } else {
+        avail_mem = task.memory.giga
+    }
+
+    """
+    filterbyname.sh \\
+        -Xmx${avail_mem}g \\
+        $input \\
+        $output \\
+        $names_command \\
+        $args \\
+        | tee ${prefix}.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bbmap: \$(bbversion.sh | grep -v "Duplicate cpuset")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def filtered = (meta.single_end || interleaved_output) ?
+        "echo '' | gzip > ${prefix}.${output_format}" :
+        "echo '' | gzip >${prefix}_1.${output_format} ; echo '' | gzip >${prefix}_2.${output_format}"
+
+    """
+    $filtered
+    touch ${prefix}.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bbmap: \$(bbversion.sh | grep -v "Duplicate cpuset")
+    END_VERSIONS
+    """
+
+}

modules/nf-core/bbmap/filterbyname/meta.yml

@@ -0,0 +1,62 @@
+name: bbmap_filterbyname
+description: Filter out sequences by sequence header name(s)
+keywords:
+  - fastq
+  - fasta
+  - filter
+tools:
+  - bbmap:
+      description: BBMap is a short read aligner, as well as various other bioinformatic tools.
+      homepage: https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/clumpify-guide/
+      documentation: https://www.biostars.org/p/225338/
+      licence: ["UC-LBL license (see package)"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and
+        paired-end data, respectively.
+  - names_to_filter:
+      type: string
+      description: |
+        String containing names of reads to filter out of the fastq files.
+  - output_format:
+      type: string
+      description: |
+        String with the format of the output file, e.g. fastq.gz, fasta, fasta.bz2
+  - interleaved_output:
+      type: boolean
+      description: |
+        Whether to produce an interleaved fastq output file
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: The trimmed/modified fastq reads
+      pattern: "*${output_format}"
+  - log:
+      type: file
+      description: filterbyname.sh log file
+      pattern: "*.filterbyname.log"
+
+authors:
+  - "@tokarevvasily"
+  - "@sppearce"
+
+maintainers:
+  - "@sppearce"

modules/nf-core/bbmap/filterbyname/tests/main.nf.test

@@ -0,0 +1,218 @@
+nextflow_process {
+
+    name "Test Process BBMAP_FILTERBYNAME"
+    script "../main.nf"
+    process "BBMAP_FILTERBYNAME"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "bbmap"
+    tag "bbmap/filterbyname"
+
+    test("paired end fastq.bz2") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                    file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = ""
+                input[2] = "fastq.bz2"
+                input[3] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("paired end fastq.bz2 - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                    file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = ""
+                input[2] = "fastq.bz2"
+                input[3] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("single end fasta") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = ""
+                input[2] = "fasta"
+                input[3] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("single end fasta - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = ""
+                input[2] = "fasta"
+                input[3] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("single end fastq.gz filter") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = "ERR5069949.2151832,ERR5069949.576388,ERR5069949.501486"
+                input[2] = "fasta"
+                input[3] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("single end fastq.gz - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = "ERR5069949.2151832,ERR5069949.576388,ERR5069949.501486"
+                input[2] = "fastq.gz"
+                input[3] = false
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("paired end fastq.gz filter interleaved") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                    file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = "ERR5069949.2151832,ERR5069949.576388,ERR5069949.501486"
+                input[2] = "fastq.gz"
+                input[3] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("paired end fastq.gz filter interleaved - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ],
+                    file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                    file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
+                 ]
+                input[1] = "ERR5069949.2151832,ERR5069949.576388,ERR5069949.501486"
+                input[2] = "fastq.gz"
+                input[3] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+}