New modules: ultra/index and ultra/align (#1830)

* Add ultra/index and ultra/align modules

* Correct tag and prefix

* Fix typos

* Remove SAMTOOLS SORT from test

* Update: Convert sam to bam

* Add tag to docker image

* Fix typo

* Add args2 for samtools

modules/ultra/align/main.nf

@@ -0,0 +1,53 @@
+process ULTRA_ALIGN {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda (params.enable_conda ? "bioconda::ultra_bioinformatics=0.0.4 bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-4b749ef583d6de806ddbf51c2d235ac8c14763c6:f63170074b42f54276c1f9b334e732a0f3bf28bd-0':
+        'quay.io/biocontainers/mulled-v2-4b749ef583d6de806ddbf51c2d235ac8c14763c6:f63170074b42f54276c1f9b334e732a0f3bf28bd-0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path genome
+    tuple path(pickle), path(db)
+
+    output:
+    tuple val(meta), path("*.bam"), emit: bam
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    uLTRA \\
+        align \\
+        --t $task.cpus \\
+        --prefix $prefix \\
+        --index ./ \\
+        $args \\
+        $genome \\
+        $reads \\
+        ./
+
+    samtools \\
+        sort \\
+        --threads $task.cpus \\
+        -o ${prefix}.bam \\
+        -O BAM \\
+        $args2 \\
+        ${prefix}.sam
+
+    rm ${prefix}.sam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ultra: \$( uLTRA --version|sed 's/uLTRA //g' )
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/ultra/align/meta.yml

@@ -0,0 +1,58 @@
+name: "ultra_align"
+description: uLTRA aligner - A wrapper around minimap2 to improve small exon detection - Map reads on genome
+keywords:
+  - uLTRA
+  - align
+  - minimap2
+  - long_read
+  - isoseq
+  - ont
+tools:
+  - "ultra":
+      description: "Splice aligner of long transcriptomic reads to genome."
+      homepage: "https://github.com/ksahlin/uLTRA"
+      documentation: "https://github.com/ksahlin/uLTRA"
+      tool_dev_url: "https://github.com/ksahlin/uLTRA"
+      doi: "10.1093/bioinformatics/btab540"
+      licence: "['GNU GPLV3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: A fasta or fastq file of reads to align
+      pattern: "*.{fa,fasta,fastq}"
+  - genome:
+      type: file
+      description: A fasta file of reference genome
+      pattern: "*.{fa,fasta}"
+  - pickle:
+      type: file
+      description: Pickle files generated by uLTRA index
+      pattern: "*.pickle"
+  - db:
+      type: file
+      description: Database generated by uLTRA index
+      pattern: "*.db"
+
+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"
+  - bam:
+      type: file
+      description: The aligned reads in bam format
+      pattern: "*.bam"
+
+authors:
+  - "@sguizard"

modules/ultra/index/main.nf

@@ -0,0 +1,37 @@
+process ULTRA_INDEX {
+    tag "$gtf"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::ultra_bioinformatics=0.0.4" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ultra_bioinformatics:0.0.4.1--pyh5e36f6f_0':
+        'quay.io/biocontainers/ultra_bioinformatics:0.0.4.1--pyh5e36f6f_0' }"
+
+    input:
+    path fasta
+    path gtf
+
+    output:
+    tuple path("*.pickle"), path("*.db"), emit: index
+    path "versions.yml"                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${gtf.baseName}"
+    """
+    uLTRA \\
+        index \\
+        $args \\
+        $fasta \\
+        $gtf \\
+        ./
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ultra: \$( uLTRA --version|sed 's/uLTRA //g' )
+    END_VERSIONS
+    """
+}

modules/ultra/index/meta.yml

@@ -0,0 +1,44 @@
+name: "ultra_index"
+description: uLTRA aligner - A wrapper around minimap2 to improve small exon detection - Index gtf file for reads alignment
+keywords:
+  - uLTRA
+  - index
+  - minimap2
+  - long_read
+  - isoseq
+  - ont
+tools:
+  - "ultra":
+      description: "Splice aligner of long transcriptomic reads to genome."
+      homepage: "https://github.com/ksahlin/uLTRA"
+      documentation: "https://github.com/ksahlin/uLTRA"
+      tool_dev_url: "https://github.com/ksahlin/uLTRA"
+      doi: "10.1093/bioinformatics/btab540"
+      licence: "['GNU GPLV3']"
+
+input:
+  - fasta:
+      type: file
+      description: A fasta file of the genome to use as reference for mapping
+      pattern: "*.{fasta, fa}"
+  - gtf:
+      type: file
+      description: An annotation file of the reference genome in GTF format
+      pattern: "*.gtf"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - pickle:
+      type: file
+      description: Index files generated by uLTRA index
+      pattern: "*.pickle"
+  - pickle:
+      type: file
+      description: database file generated by uLTRA index
+      pattern: "*.db"
+
+authors:
+  - "@sguizard"

tests/config/pytest_modules.yml

@@ -2159,6 +2159,14 @@ ucsc/wigtobigwig:
   - modules/ucsc/wigtobigwig/**
   - tests/modules/ucsc/wigtobigwig/**
 
+ultra/align:
+  - modules/ultra/align/**
+  - tests/modules/ultra/align/**
+
+ultra/index:
+  - modules/ultra/index/**
+  - tests/modules/ultra/index/**
+
 ultra/pipeline:
   - modules/ultra/pipeline/**
   - tests/modules/ultra/pipeline/**

tests/modules/ultra/align/main.nf

@@ -0,0 +1,24 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GUNZIP        } from '../../../../modules/gunzip/main.nf'
+include { GFFREAD       } from '../../../../modules/gffread/main.nf'
+include { ULTRA_INDEX   } from '../../../../modules/ultra/index/main.nf'
+include { ULTRA_ALIGN   } from '../../../../modules/ultra/align/main.nf'
+
+workflow test_ultra_align {
+
+    input = [
+        [ id:'test', single_end:false ],
+        file(params.test_data['homo_sapiens']['pacbio']['hifi'], checkIfExists: true)
+    ]
+
+    genome = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    gtf    = file(params.test_data['homo_sapiens']['genome']['genome_gtf']  , checkIfExists: true)
+
+    GUNZIP ( input )
+    GFFREAD ( gtf )
+    ULTRA_INDEX ( genome, GFFREAD.out.gtf )
+    ULTRA_ALIGN ( GUNZIP.out.gunzip, genome, ULTRA_INDEX.out.index )
+}

tests/modules/ultra/align/nextflow.config

@@ -0,0 +1,14 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: GFFREAD {
+        ext.args = '--sort-alpha --keep-genes -T'
+        ext.prefix = { "${gff.baseName}_sorted" }
+    }
+
+    withName: ULTRA_INDEX {
+        ext.args = '--disable_infer'
+    }
+
+}

tests/modules/ultra/align/test.yml

@@ -0,0 +1,33 @@
+- name: ultra align test_ultra_align
+  command: nextflow run ./tests/modules/ultra/align -entry test_ultra_align -c ./tests/config/nextflow.config  -c ./tests/modules/ultra/align/nextflow.config
+  tags:
+    - ultra/align
+    - ultra
+  files:
+    - path: output/gffread/genome_sorted.gtf
+      md5sum: c0b034860c679a354cd093109ed90437
+    - path: output/gunzip/test_hifi.fastq
+      md5sum: 20e41c569d5828c1e87337e13a5185d3
+    - path: output/ultra/all_splice_pairs_annotations.pickle
+    - path: output/ultra/all_splice_sites_annotations.pickle
+    - path: output/ultra/chr_to_id.pickle
+    - path: output/ultra/database.db
+    - path: output/ultra/exon_choordinates_to_id.pickle
+    - path: output/ultra/flank_choordinates.pickle
+    - path: output/ultra/gene_to_small_segments.pickle
+    - path: output/ultra/id_to_chr.pickle
+    - path: output/ultra/max_intron_chr.pickle
+    - path: output/ultra/parts_to_segments.pickle
+    - path: output/ultra/ref_exon_sequences.pickle
+    - path: output/ultra/ref_flank_sequences.pickle
+    - path: output/ultra/ref_part_sequences.pickle
+    - path: output/ultra/ref_segment_sequences.pickle
+    - path: output/ultra/refs_id_lengths.pickle
+    - path: output/ultra/refs_lengths.pickle
+    - path: output/ultra/segment_id_to_choordinates.pickle
+    - path: output/ultra/segment_to_gene.pickle
+    - path: output/ultra/segment_to_ref.pickle
+    - path: output/ultra/splices_to_transcripts.pickle
+    - path: output/ultra/test.bam
+      md5sum: b34c3631a899ba800602ff07b8183f87
+    - path: output/ultra/transcripts_to_splices.pickle

tests/modules/ultra/index/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ULTRA_INDEX } from '../../../../modules/ultra/index/main.nf'
+include { GFFREAD     } from '../../../../modules/gffread/main.nf'
+
+workflow test_ultra_index {
+
+    genome = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    gtf    = file(params.test_data['homo_sapiens']['genome']['genome_gtf']  , checkIfExists: true)
+    GFFREAD ( gtf )
+
+    ULTRA_INDEX ( genome, GFFREAD.out.gtf )
+}

tests/modules/ultra/index/nextflow.config

@@ -0,0 +1,14 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: GFFREAD {
+        ext.args = '--sort-alpha --keep-genes -T'
+        ext.prefix = { "${gff.baseName}_sorted" }
+    }
+
+    withName: ULTRA_INDEX {
+        ext.args = '--disable_infer'
+    }
+
+}

tests/modules/ultra/index/test.yml

@@ -0,0 +1,29 @@
+- name: ultra index test_ultra_index
+  command: nextflow run ./tests/modules/ultra/index -entry test_ultra_index -c ./tests/config/nextflow.config  -c ./tests/modules/ultra/index/nextflow.config
+  tags:
+    - ultra
+    - ultra/index
+  files:
+    - path: output/gffread/genome_sorted.gtf
+      md5sum: c0b034860c679a354cd093109ed90437
+    - path: output/ultra/all_splice_pairs_annotations.pickle
+    - path: output/ultra/all_splice_sites_annotations.pickle
+    - path: output/ultra/chr_to_id.pickle
+    - path: output/ultra/database.db
+    - path: output/ultra/exon_choordinates_to_id.pickle
+    - path: output/ultra/flank_choordinates.pickle
+    - path: output/ultra/gene_to_small_segments.pickle
+    - path: output/ultra/id_to_chr.pickle
+    - path: output/ultra/max_intron_chr.pickle
+    - path: output/ultra/parts_to_segments.pickle
+    - path: output/ultra/ref_exon_sequences.pickle
+    - path: output/ultra/ref_flank_sequences.pickle
+    - path: output/ultra/ref_part_sequences.pickle
+    - path: output/ultra/ref_segment_sequences.pickle
+    - path: output/ultra/refs_id_lengths.pickle
+    - path: output/ultra/refs_lengths.pickle
+    - path: output/ultra/segment_id_to_choordinates.pickle
+    - path: output/ultra/segment_to_gene.pickle
+    - path: output/ultra/segment_to_ref.pickle
+    - path: output/ultra/splices_to_transcripts.pickle
+    - path: output/ultra/transcripts_to_splices.pickle