Merge branch 'nf-core:master' into merfin_hist_v2

modules/nf-core/xengsort/index/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "xengsort_index"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::xengsort=2.0.5"

modules/nf-core/xengsort/index/main.nf

@@ -0,0 +1,54 @@
+process XENGSORT_INDEX {
+    tag "$host_fasta"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/xengsort:2.0.5--pyhdfd78af_0':
+        'biocontainers/xengsort:2.0.5--pyhdfd78af_0' }"
+
+    input:
+    path(host_fasta, stageAs: "host/*")
+    path(graft_fasta, stageAs: "graft/*")
+    val index
+    val nobjects
+    val mask
+
+    output:
+    path "${index}.hash"          , emit: hash
+    path "${index}.info"          , emit: info
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    xengsort \\
+        index \\
+        $args \\
+        --index $index \\
+        --host $host_fasta \\
+        --graft $graft_fasta \\
+        --nobjects $nobjects \\
+        --mask '$mask' \\
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        xengsort: \$(xengsort --version)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    """
+    touch ${index}.info
+    touch ${index}.hash
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        xengsort: \$(xengsort --version)
+    END_VERSIONS
+    """
+}

modules/nf-core/xengsort/index/meta.yml

@@ -0,0 +1,61 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "xengsort_index"
+description: Fast lightweight accurate xenograft sorting
+keywords:
+  - index
+  - QC
+  - reference
+  - fasta
+  - xenograft
+  - sort
+  - k-mer
+tools:
+  - "xengsort":
+      description: "A fast xenograft read sorter based on space-efficient k-mer hashing"
+      homepage: "https://gitlab.com/genomeinformatics/xengsort"
+      documentation: "https://gitlab.com/genomeinformatics/xengsort"
+      tool_dev_url: "https://gitlab.com/genomeinformatics/xengsort"
+      doi: "10.4230/LIPIcs.WABI.2020.4"
+      licence: ["MIT"]
+
+input:
+  - host_fasta:
+      type: file
+      description: |
+        Reference genome fasta file from host, compressed or uncompressed.
+  - graft_fasta:
+      type: file
+      description: |
+        Reference genome fasta file from graft, compressed or uncompressed.
+  - index:
+      type: string
+      description: |
+        File name prefix to store index files.
+  - nobjects:
+      type: string
+      description: |
+        Number of k-mers that will be stored in the hash table. Underscore should be used, i.e for 1000000, it should be typed 1_000_000.
+  - mask:
+      type: string
+      description: |
+        Gapped k-mer mask (quoted string like '#__##_##__#').
+
+output:
+  - hash:
+      type: file
+      description: File with index hash file.
+      pattern: "*hash"
+  - info:
+      type: file
+      description: File with index info file.
+      pattern: "*info"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@diegomscoelho"
+maintainers:
+  - "@diegomscoelho"

modules/nf-core/xengsort/index/tests/main.nf.test

@@ -0,0 +1,37 @@
+nextflow_process {
+
+    name "Test Process XENGSORT_INDEX"
+    script "../main.nf"
+    process "XENGSORT_INDEX"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "xengsort"
+    tag "xengsort/index"
+
+    test("homo_sapiens - sarscov2 - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+                input[1] = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+                input[2] = 'index'
+                input[3] = '10_000_000'
+                input[4] = '###__#_##__#_#_###__#__###_#_#__##_#__###'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/xengsort/index/tests/tags.yml

@@ -0,0 +1,2 @@
+xengsort/index:
+  - "modules/nf-core/xengsort/index/**"