Merge branch 'master' into master

modules/nf-core/decoupler/decoupler/main.nf

@@ -0,0 +1,71 @@
+process DECOUPLER {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "conda-forge::decoupler-py=1.6.0"
+    container = "ghcr.io/saezlab/publish-packages/decoupler:sha-5838309"
+
+    input:
+    tuple val(meta), path(mat)
+    path(net)
+
+    output:
+    tuple val(meta), path("*estimate__decoupler.tsv"), emit: dc_estimate
+    tuple val(meta), path("*pvals__decoupler.tsv"), emit: dc_pvals
+    path("versions.yml"), emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: "{}"
+    """
+    #!/usr/bin/env python3
+    import os
+    import pandas as pd
+
+    os.environ["NUMBA_CACHE_DIR"] = "./tmp"
+
+    import decoupler as dc
+
+    methods = ['aucell', 'gsea', 'gsva', 'mdt', 'mlm', 'ora', 'udt',
+        'ulm', 'viper', 'wmean', 'wsum']
+
+    mat = pd.read_csv("${mat}", sep="\t", index_col=0)
+    net = pd.read_csv("${net}", sep="\t", index_col=0)
+
+    # Parsing arguments
+    args = ${args}
+    parsedargs = {'args': {}}
+
+    for k, v in args.items():
+        # Specific method argument
+        if k.split('_')[0] in methods:
+            meth = k.split('_')[0]
+            arg = '_'.join(k.split('_')[1:])
+
+            if meth not in args['args'].keys():
+                parsedargs['args'][meth] = {arg: v}
+            else:
+                parsedargs['args'][meth].update({arg: v})
+
+        # Generic argument
+        else:
+            parsedargs[k] = v
+
+
+    results = dc.decouple(
+        mat=mat,
+        net=net,
+        **parsedargs
+    )
+
+    for result in results:
+        results[result].to_csv(result + "__decoupler.tsv", sep="\t")
+
+    ## VERSIONS FILE
+    with open('versions.yml', 'a') as version_file:
+        version_file.write('"${task.process}":' + "\\n")
+        version_file.write("\tdecoupler-py: " + dc.__version__ + "\\n")
+    """
+}

modules/nf-core/decoupler/decoupler/meta.yml

@@ -0,0 +1,83 @@
+name: "decoupler"
+
+description: |
+  decoupler is a package containing different statistical methods
+  to extract biological activities from omics data within a unified framework.
+  It allows to flexibly test any enrichment method with any prior knowledge
+  resource and incorporates methods that take into account the sign and weight.
+  It can be used with any omic, as long as its features can be linked to a
+  biological process based on prior knowledge. For example, in transcriptomics
+  gene sets regulated by a transcription factor, or in phospho-proteomics
+  phosphosites that are targeted by a kinase.
+
+keywords:
+  - enrichment
+  - omics
+  - biological activity
+  - functional analysis
+  - prior knowledge
+
+tools:
+  - "decoupler":
+      description: "Ensemble of methods to infer biological activities from omics data"
+      homepage: "https://github.com/saezlab/decoupler-py"
+      documentation: "https://decoupler-py.readthedocs.io/en/latest/api.html"
+      tool_dev_url: "https://decoupler-py.readthedocs.io"
+      doi: "10.1093/bioadv/vbac016"
+      licence: ["GPL v3"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:‘test’, single_end ]
+  - mat:
+      type: file
+      description: |
+        Path to the matrix file (e.g. gene/protein expression, etc.).
+        Should be in in tab-separated format (`*.tab`)
+      pattern: "*.tsv"
+  - net:
+      type: file
+      description: |
+        The prior knowledge network linking the features of the
+        expression matrix to a process/component (e.g. gene set,
+        transcription factor, kinase, etc.)
+      pattern: "*.tsv"
+  - args:
+      type: string
+      description: |
+        Keyword arguments passed to `decoupler.decouple()` (see
+        documentation for more information here:
+        https://decoupler-py.readthedocs.io/en/latest/generated/decoupler.decouple.html#decoupler.decouple).
+        Arguments specific for a method must be specified with
+        the method name as a prefix e.g. `'gsea_batch_size'`
+      pattern: "{arg: val, ..., method_arg: val}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:‘test’, single_end ]
+  - dc_estimate:
+      type: file
+      description: |
+        The file containing the estimation results of the enrichment(s)
+      pattern: "*estimate__decoupler.tsv"
+  - dc_pvals:
+      type: file
+      description: |
+        The file containing the p-value associated to the estimation
+        results of the enrichment(s)
+      pattern: "*pvals__decoupler.tsv"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@gabora"
+  - "@vicpaton"
+  - "@Nic-Nic"

modules/nf-core/decoupler/decoupler/tests/main.nf.test

@@ -0,0 +1,38 @@
+nextflow_process {
+
+    name "Test Process DECOUPLER"
+    script "../main.nf"
+    config "./nextflow.config"
+    process "DECOUPLER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "decoupler"
+    tag "decoupler/decoupler"
+
+    test("decoupler_test") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id: 'test' ],
+                    file(params.test_data['generic']['tsv']['expression'], checkIfExists: true)
+                ]
+                input[1] = [
+                    file(params.test_data['generic']['tsv']['network'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/decoupler/decoupler/tests/nextflow.config

@@ -0,0 +1,6 @@
+process {
+    withName: "DECOUPLER" {
+        ext.prefix = 'test'
+        ext.args = "{'min_n': 1}"
+    }
+}

modules/nf-core/decoupler/decoupler/tests/tags.yml

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

modules/nf-core/deepvariant/tests/main.nf.test

@@ -0,0 +1,117 @@
+nextflow_process {
+
+    name "Test Process DEEPVARIANT"
+    script "../main.nf"
+    process "DEEPVARIANT"
+
+    tag "deepvariant"
+    tag "modules"
+    tag "modules_nfcore"
+
+    test("homo_sapiens - [bam, bai] - fasta - fai") {
+        when {
+            config "./nextflow.config"
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam.bai', checkIfExists: true),
+                      []
+                ]
+                input[1] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[2] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta.fai', checkIfExists: true)
+                ]
+                input[3] = [
+                    [],[]
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("homo_sapiens - [cram, crai, genome_bed] - fasta - fai") {
+        config "./nextflow-intervals.config"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram', checkIfExists: true),
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram.crai', checkIfExists: true),
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.bed', checkIfExists: true)
+                ]
+                input[1] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[2] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta.fai', checkIfExists: true)
+                ]
+                input[3] = [
+                    [],[]
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("homo_sapiens - [bam, bai] - fasta_gz - fasta_gz_fai") {
+        when {
+            config "./nextflow.config"
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam.bai', checkIfExists: true),
+                      []
+                ]
+                input[1] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta.gz', checkIfExists: true)
+                ]
+                input[2] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta.gz.fai', checkIfExists: true)
+                ]
+                input[3] = [
+                    [ id:'genome'],
+                      file(params.modules_testdata_base_path + '/genomics/homo_sapiens/genome/genome.fasta.gz.gzi', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+}