Merge remote-tracking branch 'origin/purecn/run' into purecn/run

nf-core · Jul 6, 2023 · 7665ef3 · 7665ef3
2 parents 205abd4 + 08e7352
commit 7665ef3
Show file tree

Hide file tree

Showing 12 changed files with 251 additions and 6 deletions.
diff --git a/modules/nf-core/metaphlan/metaphlan/main.nf b/modules/nf-core/metaphlan/metaphlan/main.nf
@@ -23,12 +23,13 @@ process METAPHLAN_METAPHLAN {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input_type  = ("$input".endsWith(".fastq.gz") || "$input".endsWith(".fq.gz")) ? "--input_type fastq" :  ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam"
+    def input_type = "$input" =~ /.*\.(fastq|fq)/ ? "--input_type fastq" : "$input" =~ /.*\.(fasta|fna|fa)/ ? "--input_type fasta" : "$input".endsWith(".bowtie2out.txt") ? "--input_type bowtie2out" : "--input_type sam"
     def input_data  = ("$input_type".contains("fastq")) && !meta.single_end ? "${input[0]},${input[1]}" : "$input"
     def bowtie2_out = "$input_type" == "--input_type bowtie2out" || "$input_type" == "--input_type sam" ? '' : "--bowtie2out ${prefix}.bowtie2out.txt"
 
     """
     BT2_DB=`find -L "${metaphlan_db_latest}" -name "*rev.1.bt2l" -exec dirname {} \\;`
+    BT2_DB_INDEX=`find -L ${metaphlan_db_latest} -name "*.rev.1.bt2l" | sed 's/\\.rev.1.bt2l\$//' | sed 's/.*\\///'`
 
     metaphlan \\
         --nproc $task.cpus \\
@@ -37,6 +38,7 @@ process METAPHLAN_METAPHLAN {
         $args \\
         $bowtie2_out \\
         --bowtie2db \$BT2_DB \\
+        --index \$BT2_DB_INDEX \\
         --biom ${prefix}.biom \\
         --output_file ${prefix}_profile.txt
 

diff --git a/modules/nf-core/peka/main.nf b/modules/nf-core/peka/main.nf
@@ -0,0 +1,59 @@
+process PEKA {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "bioconda::peka=1.0.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/peka:1.0.0--pyhdfd78af_0':
+        'biocontainers/peka:1.0.0--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(peaks)
+    tuple val(meta), path(crosslinks)
+    path fasta
+    path fai
+    path gtf
+
+    output:
+    tuple val(meta), path("*mer_cluster_distribution*"), emit: cluster,      optional: true
+    tuple val(meta), path("*mer_distribution*")        , emit: distribution, optional: true
+    tuple val(meta), path("*.pdf")                     , emit: pdf,          optional: true
+    path "versions.yml"                                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args ?: ''
+    def VERSION = '1.0.0' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    # If the modification date and time of the fai is before the fasta then
+    # there will be an error. Touching the file first avoids that.
+    touch $fai
+    mkdir tmp
+    TMPDIR=\$(pwd)/tmp peka \
+        -i $peaks \
+        -x $crosslinks \
+        -g $fasta \
+        -gi $fai \
+        -r $gtf \
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        peka: $VERSION
+    END_VERSIONS
+    """
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.0.0' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    """
+    touch ${prefix}_4mer_cluster_distribution_genome.tsv
+    touch ${prefix}_4mer_distribution_genome.tsv
+    touch ${prefix}_4mer_genome.pdf
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        peka: $VERSION
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/peka/meta.yml b/modules/nf-core/peka/meta.yml
@@ -0,0 +1,68 @@
+---
+name: "peka"
+description: Runs PEKA CLIP peak k-mer analysis
+keywords:
+  - motif
+  - CLIP
+  - iCLIP
+  - genomics
+  - k-mer
+tools:
+  - "peka":
+      description: "Positionally-enriched k-mer analysis (PEKA) is a software package for identifying enriched protein-RNA binding motifs from CLIP datasets"
+      homepage: "https://github.com/ulelab/peka"
+      documentation: "https://github.com/ulelab/peka"
+      tool_dev_url: "https://github.com/ulelab/peka"
+      doi: "10.1186/s13059-022-02755-2"
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - peaks:
+      type: file
+      description: BED file of peak regions
+      pattern: "*.{bed,bed.gz}"
+  - crosslinks:
+      type: file
+      description: BED file of crosslinks
+      pattern: "*.{bed,bed.gz}"
+  - fasta:
+      type: file
+      description: Genome reference sequence used
+      pattern: "*.{fa,fasta}"
+  - fai:
+      type: file
+      description: FAI file corresponding to the reference sequence
+      pattern: "*.{fai}"
+  - gtf:
+      type: file
+      description: A segmented GTF used to annotate peaks
+      pattern: "*.{gtf}"
+
+output:
+  - cluster:
+      type: file
+      description: TSV file of summed occurrence distributions of k-mers within defined clusters
+      pattern: "*.tsv"
+  - distribution:
+      type: file
+      description: TSV file with calculated PEKA score and occurrence distribution for all possible k-mers
+      pattern: "*.tsv"
+  - pdf:
+      type: file
+      description: PDF file with graphs showing k-mer occurrence distributions around thresholded crosslink sites
+      pattern: "*.pdf"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@kkuret"
+  - "@codeprimate123"
+  - "@chris-cheshire"
+  - "@charlotteanne"
diff --git a/modules/nf-core/salmon/quant/main.nf b/modules/nf-core/salmon/quant/main.nf
@@ -28,7 +28,9 @@ process SALMON_QUANT {
     prefix   = task.ext.prefix ?: "${meta.id}"
 
     def reference   = "--index $index"
-    def input_reads = meta.single_end ? "-r $reads" : "-1 ${reads[0]} -2 ${reads[1]}"
+    def reads1 = [], reads2 = []
+    meta.single_end ? [reads].flatten().each{reads1 << it} : reads.eachWithIndex{ v, ix -> ( ix & 1 ? reads2 : reads1) << v }
+    def input_reads = meta.single_end ? "-r ${reads1.join(" ")}" : "-1 ${reads1.join(" ")} -2 ${reads2.join(" ")}"
     if (alignment_mode) {
         reference   = "-t $transcript_fasta"
         input_reads = "-a $reads"

diff --git a/modules/nf-core/salmon/quant/meta.yml b/modules/nf-core/salmon/quant/meta.yml
@@ -22,8 +22,9 @@ input:
   - reads:
       type: file
       description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
-        respectively.
+        List of input FastQ files for single-end or paired-end data.
+        Multiple single-end fastqs or pairs of paired-end fastqs are
+        handled.
   - index:
       type: directory
       description: Folder containing the star index files

diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
@@ -2651,6 +2651,10 @@ peddy:
   - modules/nf-core/peddy/**
   - tests/modules/nf-core/peddy/**
 
+peka:
+  - modules/nf-core/peka/**
+  - tests/modules/nf-core/peka/**
+
 phantompeakqualtools:
   - modules/nf-core/phantompeakqualtools/**
   - tests/modules/nf-core/phantompeakqualtools/**

diff --git a/tests/modules/nf-core/metaphlan/metaphlan/main.nf b/tests/modules/nf-core/metaphlan/metaphlan/main.nf
@@ -53,7 +53,7 @@ workflow test_metaphlan_sam {
     db    = [ [], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan4_database.tar.gz', checkIfExists: true) ]
 
     UNTAR ( db )
-    SAMTOOLS_VIEW ( input, [] ,[])
+    SAMTOOLS_VIEW ( input, [[],[]], [])
     METAPHLAN_METAPHLAN ( SAMTOOLS_VIEW.out.sam, UNTAR.out.untar.map{ it[1] } )
 }
 
diff --git a/tests/modules/nf-core/peka/main.nf b/tests/modules/nf-core/peka/main.nf
@@ -0,0 +1,22 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PEKA               } from '../../../../modules/nf-core/peka/main.nf'
+
+workflow test_peka {
+
+    bed_crosslinks = [ [ id:'test' ], file("https://raw.githubusercontent.com/nf-core/test-datasets/clipseq/peka/chr21_HepG2-PCBP1-merged.xl.bed", checkIfExists: true) ]
+    bed_peaks      = [ [ id:'test' ], file("https://raw.githubusercontent.com/nf-core/test-datasets/clipseq/peka/chr21_HepG2-PCBP1-merged.xl10_200_density2_peaks.bed", checkIfExists: true) ]
+    regions        = file("https://raw.githubusercontent.com/nf-core/test-datasets/clipseq/peka/chr21_gencode_regions.gtf", checkIfExists: true)
+    fasta          = file("https://raw.githubusercontent.com/nf-core/test-datasets/clipseq/peka/chr21.GRCh38.p12.genome.masked.fa", checkIfExists: true)
+    fai            = file("https://raw.githubusercontent.com/nf-core/test-datasets/clipseq/peka/chr21.GRCh38.p12.genome.masked.fa.fai", checkIfExists: true)
+
+    PEKA(
+        bed_peaks,
+        bed_crosslinks,
+        fasta,
+        fai,
+        regions
+    )
+}
diff --git a/tests/modules/nf-core/peka/nextflow.config b/tests/modules/nf-core/peka/nextflow.config
@@ -0,0 +1,6 @@
+process {
+    withName: 'PEKA' {
+        ext.args = { "-sr 'genome' -re 'unmasked' -k 4 -p 0" }
+    }
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+}
diff --git a/tests/modules/nf-core/peka/test.yml b/tests/modules/nf-core/peka/test.yml
@@ -0,0 +1,9 @@
+- name: peka test_peka
+  command: nextflow run ./tests/modules/nf-core/peka -entry test_peka -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/peka/nextflow.config
+  tags:
+    - peka
+  files:
+    - path: output/peka/chr21_HepG2-PCBP1-merged_4mer_cluster_distribution_genome.tsv
+    - path: output/peka/chr21_HepG2-PCBP1-merged_4mer_distribution_genome.tsv
+    - path: output/peka/chr21_HepG2-PCBP1-merged_4mer_genome.pdf
+    - path: output/peka/versions.yml
diff --git a/tests/modules/nf-core/salmon/quant/main.nf b/tests/modules/nf-core/salmon/quant/main.nf
@@ -57,3 +57,22 @@ workflow test_salmon_quant_single_end_lib_type_A {
 
 }
 
+workflow test_salmon_quant_paired_end_multiple {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [
+            file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test2_1_fastq_gz'], checkIfExists: true),
+            file(params.test_data['sarscov2']['illumina']['test2_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+    genome_fasta     = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    transcript_fasta = file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true)
+    gtf              = file(params.test_data['sarscov2']['genome']['genome_gtf'], checkIfExists: true)
+
+    SALMON_INDEX ( genome_fasta, transcript_fasta )
+    SALMON_QUANT ( input, SALMON_INDEX.out.index, gtf, transcript_fasta, false, '' )
+
+}
diff --git a/tests/modules/nf-core/salmon/quant/test.yml b/tests/modules/nf-core/salmon/quant/test.yml
@@ -95,7 +95,6 @@
       md5sum: 8d1970505b2b08ca0eb5ff7722b48cde
     - path: ./output/salmon/salmon/ctg_offsets.bin
       md5sum: 27a76542337df436436e66017f66dd25
-
     - path: ./output/salmon/salmon/rank.bin
       md5sum: 3f34dca1ec26cdf89a6d19b1d1c07e71
     - path: ./output/salmon/salmon/pos.bin
@@ -149,3 +148,57 @@
       md5sum: 3f34dca1ec26cdf89a6d19b1d1c07e71
     - path: ./output/salmon/salmon/pos.bin
     - path: ./output/salmon/salmon/seq.bin
+
+- name: salmon quant test_salmon_quant_paired_end_multiple
+  command: nextflow run ./tests/modules/nf-core/salmon/quant -entry test_salmon_quant_paired_end_multiple -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/salmon/quant/nextflow.config
+  tags:
+    - salmon/quant
+    - salmon
+  files:
+    - path: output/salmon/salmon/complete_ref_lens.bin
+      md5sum: f57562f1fca3ae7b133f895ae13c3d08
+    - path: output/salmon/salmon/ctable.bin
+    - path: output/salmon/salmon/ctg_offsets.bin
+      md5sum: 27a76542337df436436e66017f66dd25
+    - path: output/salmon/salmon/duplicate_clusters.tsv
+      md5sum: 51b5292e3a874119c0e1aa566e95d70c
+    - path: output/salmon/salmon/info.json
+      md5sum: 61ff4d3471134c280668355ddd39e99f
+    - path: output/salmon/salmon/mphf.bin
+      md5sum: 53669a47610e33e031faafd32703b714
+    - path: output/salmon/salmon/pos.bin
+    - path: output/salmon/salmon/pre_indexing.log
+    - path: output/salmon/salmon/rank.bin
+      md5sum: 3f34dca1ec26cdf89a6d19b1d1c07e71
+    - path: output/salmon/salmon/refAccumLengths.bin
+      md5sum: 8d1970505b2b08ca0eb5ff7722b48cde
+    - path: output/salmon/salmon/ref_indexing.log
+    - path: output/salmon/salmon/reflengths.bin
+      md5sum: f57562f1fca3ae7b133f895ae13c3d08
+    - path: output/salmon/salmon/refseq.bin
+      md5sum: 79c4ddf34be3a98d5a7b9d153629a6f7
+    - path: output/salmon/salmon/seq.bin
+    - path: output/salmon/salmon/versionInfo.json
+      md5sum: 8126856d616d41d63aebd11a440b5b5b
+    - path: output/salmon/test/aux_info/ambig_info.tsv
+      md5sum: 1067793c186f56621165add136987d7f
+    - path: output/salmon/test/aux_info/expected_bias.gz
+      md5sum: 24ee10af39b41ecf4f4e08faaaf537ee
+    - path: output/salmon/test/aux_info/fld.gz
+    - path: output/salmon/test/aux_info/meta_info.json
+    - path: output/salmon/test/aux_info/observed_bias.gz
+      md5sum: ef13c06a538e9c34ca9f84212c82f44e
+    - path: output/salmon/test/aux_info/observed_bias_3p.gz
+      md5sum: ef13c06a538e9c34ca9f84212c82f44e
+    - path: output/salmon/test/cmd_info.json
+      md5sum: 3284f2f259dad6c271d0e0e047854c4f
+    - path: output/salmon/test/libParams/flenDist.txt
+      md5sum: 62ced80c88aa784e3019a8ba7ca20236
+    - path: output/salmon/test/lib_format_counts.json
+      md5sum: 20bffb7bef3ffbae97968b85abf8bc14
+    - path: output/salmon/test/logs/salmon_quant.log
+    - path: output/salmon/test/quant.genes.sf
+      md5sum: 506c564cadf9c6572eb46c92c1d2a075
+    - path: output/salmon/test/quant.sf
+      md5sum: 37ebc8512a158ecdbf996e324eee226d
+    - path: output/salmon/versions.yml