Busco subworkflow

assets/samplesheet.csv

@@ -1,3 +1,5 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+sample,datatype,datafile
+mMelMel3,hic,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/analysis/mMelMel3.2_paternal_haplotype/read_mapping/hic/GCA_922984935.2.subset.unmasked.hic.mMelMel3.cram
+mMelMel1,illumina,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/analysis/mMelMel3.2_paternal_haplotype/read_mapping/illumina/GCA_922984935.2.subset.unmasked.illumina.mMelMel1.cram
+mMelMel2,illumina,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/analysis/mMelMel3.2_paternal_haplotype/read_mapping/illumina/GCA_922984935.2.subset.unmasked.illumina.mMelMel2.cram
+mMelMel3,ont,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/analysis/mMelMel3.2_paternal_haplotype/read_mapping/ont/GCA_922984935.2.subset.unmasked.ont.mMelMel3.cram

assets/schema_input.json

@@ -9,28 +9,22 @@
         "properties": {
             "sample": {
                 "type": "string",
+                "description": "Sample Name",
                 "pattern": "^\\S+$",
                 "errorMessage": "Sample name must be provided and cannot contain spaces"
             },
-            "fastq_1": {
+            "datatype": {
                 "type": "string",
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "pattern": "^\\S+$",
+                "enum": ["hic", "illumina", "ont", "pacbio"],
+                "errorMessage": "Data type, and must be one of: 'hic' or 'illumina' or 'ont' or 'pacbio'"
             },
-            "fastq_2": {
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
-                "anyOf": [
-                    {
-                        "type": "string",
-                        "pattern": "^\\S+\\.f(ast)?q\\.gz$"
-                    },
-                    {
-                        "type": "string",
-                        "maxLength": 0
-                    }
-                ]
+            "datafile": {
+                "type": "string",
+                "pattern": "^\\S+\\.cram$",
+                "errorMessage": "Data file for reads cannot contain spaces and must have extension 'cram'"
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["datafile", "datatype", "sample"]
     }
 }

bin/tol_input.sh

@@ -1,16 +1,13 @@
 #!/bin/bash
 
-PROJECT_BASEDIR=/lustre/scratch123/tol/projects
-
-if [ $# -ne 2 ]; then echo -e "Script to create a samplesheet for a species.\nUsage: $0 <tol_id> <tol_project>.\nVersion: 1.0"; exit 1; fi
+if [ $# -ne 2 ]; then echo -e "Script to create a samplesheet for a species.\nUsage: $0 <tol_id> <tol_projectDir>.\nVersion: 1.0"; exit 1; fi
 
 id="$1"
-project="$2"
-data="$PROJECT_BASEDIR/$project/data"
+data="$2/data"
 
 if [[ ! -d "$data" ]]
 then
-    echo "Project "$project" cannot be found under $PROJECT_BASEDIR"
+    echo "Project directory "$data" does not exist"
     exit 1
 fi
 

conf/modules.config

@@ -29,6 +29,13 @@ process {
     withName: FASTQC {
         ext.args = '--quiet'
     }
+    withName: GOAT_TAXONSEARCH {
+         ext.args = '-l -b'
+     }
+
+    withName: BUSCO {
+         ext.args = '--mode genome'
+     }
 
     withName: CUSTOM_DUMPSOFTWAREVERSIONS {
         publishDir = [
@@ -38,4 +45,7 @@ process {
         ]
     }
 
+    withName: 'SAMTOOLS_VIEW' {
+        ext.args = "--output-fmt bam --write-index"
+    }
 }

conf/test.config

@@ -12,33 +12,23 @@
 // Resource settings - normally provided through pipeline `nextflow.config`
 params {
     // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
+    max_cpus   = 4
+    max_memory = '12.GB'
     max_time   = '6.h'
 
     // Set default values
     outdir   = './results'
     tracedir = "${params.outdir}/pipeline_info"
 
     // Input test data
-    input   = "mMelMel3"
-    project = ".sandbox"
-}
+    input   = "${projectDir}/assets/samplesheet.csv"
+    fasta = "https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/assembly/release/mMelMel3.1_paternal_haplotype/GCA_922984935.2.subset.fasta.gz"
 
-// Singularity settings - normally provided through `conf/sanger.config`
-singularity.enabled    = true
-singularity.autoMounts = true
-singularity.runOptions = '--bind /lustre --bind /nfs'
+    // goat_taxon_search
+    taxon = 'Meles meles'
+    taxa_file = ''
 
-// Publishing settings - normally provided through pipeline `conf/modules.config`
-process {
-    publishDir = { "${params.outdir}/pipeline_info" }
+    // BUSCO
+    busco_lineages_path = '/lustre/scratch123/tol/resources/nextflow/test-data/busco_2021_06_reduced'
 
-    withName: SAMTOOLS_VIEW {
-        publishDir = [
-            path: { "${params.outdir}/testing" },
-            mode: 'copy',
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
 }

modules.json

@@ -2,15 +2,43 @@
     "name": "nf-core/blobtoolkit",
     "homePage": "https://github.com/nf-core/blobtoolkit",
     "repos": {
+<<<<<<< HEAD
         "nf-core/modules": {
-            "custom/dumpsoftwareversions": {
-                "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
+<<<<<<< HEAD
+            "nf-core/custom/dumpsoftwareversions": {
+                "git_sha": "8022c68e7403eecbd8ba9c49496f69f8c49d50f0"
             },
-            "multiqc": {
-                "git_sha": "5138acca0985ca01c38a1c4fba917d83772b1106"
+            "busco": {
+                "git_sha": "89a84538bede7c6919f7c042fdb4c79e5e2d9d2a"
             },
-            "samtools/view": {
-                "git_sha": "6b64f9cb6c3dd3577931cc3cd032d6fb730000ce"
+            "nf-core/fastawindows": {
+                "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+            },
+            "nf-core/gunzip": {
+                "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+            },
+            "nf-core/mosdepth": {
+                "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+            },
+            "nf-core/samtools/view": {
+                "git_sha": "202683bfc98ddecdd456ea73268e330bca2e5c5a"
+=======
+            "git_url": "https://github.com/nf-core/modules.git",
+=======
+        "https://github.com/nf-core/modules.git": {
+>>>>>>> installed new busco nf-core module
+            "modules": {
+                "nf-core": {
+                    "busco": {
+                        "branch": "master",
+                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+                    },
+                    "multiqc": {
+                        "branch": "master",
+                        "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+                    }
+                }
+>>>>>>> removed samtools/viewmodule
             }
         }
     }

modules/local/create_bed.nf

@@ -0,0 +1,31 @@
+process CREATE_BED {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda (params.enable_conda ? "conda-forge::gawk=5.1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    'https://depot.galaxyproject.org/singularity/gawk:5.1.0' :
+    'quay.io/biocontainers/gawk:5.1.0' }"
+
+    input:
+    tuple val(meta), path(tsv)      //path to tsv output from fasta windows
+
+    output:
+    path '*.bed'       , emit: bed
+    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}"
+    """
+    cut -f 1,2,3 $tsv | sed '1d' $args > ${prefix}.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        create_bed: 1.01
+    END_VERSIONS
+    """
+}

modules/local/extract_busco_genes.nf

@@ -0,0 +1,25 @@
+process EXTRACT_BUSCO_GENES {
+    tag "$meta.id"
+
+    container "genomehubs/blobtoolkit-blobtools:3.3.4"
+
+    input:
+    tuple val(meta), path(arc), path(bac), path(euk)
+
+    output:
+    tuple val(meta), path('*_busco_genes.fasta') , emit: fasta
+    path "versions.yml"                          , emit: versions
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def tables = ["\"$arc\"", "\"$bac\"", "\"$euk\""]
+    """
+    btk pipeline extract-busco-genes \\
+        --busco $tables \\
+        --out ${prefix}_busco_genes.fasta
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        blobtoolkit: \$(btk --version | cut -d' ' -f2 | sed 's/v//')
+    END_VERSIONS
+    """
+}

modules/local/goat_taxon_search.nf

@@ -0,0 +1,40 @@
+
+process GOAT_TAXONSEARCH {
+    tag "$meta.id"
+
+    conda (params.enable_conda ? "bioconda::goat=0.2.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/goat:0.2.0--h92d785c_0':
+        'quay.io/biocontainers/goat:0.2.0--h92d785c_0' }"
+
+    input:
+    tuple val(meta), val(taxon), path(taxa_file)
+
+    output:
+    path "*.tsv" 	    , emit: taxonsearch
+    tuple val(meta), path("*.txt"), emit: busco_lineages
+    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}"
+    input = taxa_file ? "-f ${taxa_file}" : "-t ${taxon}"
+    if (!taxon && !taxa_file) error "No input. Valid input: single taxon identifier or a .txt file with identifiers"
+    if (taxon && taxa_file ) error "Only one input is required: a single taxon identifier or a .txt file with identifiers"
+    // ${prefix}.txt contains the list of BUSCO (odb10) lineages, one lineage per line without empty lines
+    """
+    goat-cli taxon search \\
+        $args \\
+        "$input" > ${prefix}.tsv
+    cat ${prefix}.tsv | cut -f5 | sed '1d' | grep . > ${prefix}.txt
+    echo "bacteria_odb10" >> ${prefix}.txt
+    echo "archaea_odb10" >> ${prefix}.txt
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        goat: \$(goat-cli --version | cut -d' ' -f2)
+    END_VERSIONS
+    """
+}