Update busco module

modules/busco/main.nf

@@ -1,31 +1,31 @@
 process BUSCO {
     tag "$meta.id"
     label 'process_medium'
-    
+
-    conda (params.enable_conda ? "bioconda::busco=5.2.2" : null)
+    conda (params.enable_conda ? "bioconda::busco=5.3.2" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/busco:5.2.2--pyhdfd78af_0':
+        'https://depot.galaxyproject.org/singularity/busco:5.3.2--pyhdfd78af_0':
-        'quay.io/biocontainers/busco:5.2.2--pyhdfd78af_0' }"
+        'quay.io/biocontainers/busco:5.3.2--pyhdfd78af_0' }"
 
     input:
-    tuple val(meta), path(fasta)
+    tuple val(meta), path(fasta)  // Required:    meta map, and fasta sequence file
-    val(mode)
+    each lineage                  // Required:    lineage to check against
-    path(augustus_config)
+    path busco_lineages_path      // Recommended: path to busco lineages - downloads if not set
-    val(lineage)
+    path config_file              // Optional:    busco configuration file
 
     output:
-    tuple val(meta), path("${meta.id}/run_*/full_table.tsv"), emit: tsv
+    tuple val(meta), path("*-busco"), emit: busco_dir
-    tuple val(meta), path("${meta.id}/run_*/short_summary.txt"), emit: txt
+    path "versions.yml"             , emit: versions
-    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}-${lineage}"
-    if (lineage) args += " --lineage_dataset $lineage"
+    def busco_config = config_file ? "--config $config_file" : ''
+    def busco_lineage_dir = busco_lineages_path ? "--download_path ${busco_lineages_path}" : ''
     """
-    # Ensure the input is uncompressed
-    gzip -cdf $fasta > __UNCOMPRESSED_FASTA_FILE__
-    
     # Nextflow changes the container --entrypoint to /bin/bash (container default entrypoint: /usr/local/env-execute)
     # Check for container variable initialisation script and source it.
     if [ -f "/usr/local/env-activate.sh" ]; then
@@ -39,12 +39,30 @@ process BUSCO {
         . "/usr/local/etc/conda/activate.d/augustus.sh"
         . "/usr/local/etc/conda/activate.d/openjdk_activate.sh"
     fi
-    
+
-    # Copy the image's AUGUSTUS config directory if it was not provided to the module
+    # If the augustus config directory is not writable, then copy to writeable area
-    [ ! -e augustus_config ] && cp -a /usr/local/config augustus_config
+    if [ ! -w "\${AUGUSTUS_CONFIG_PATH}" ]; then
-    
+        # Create writable tmp directory for augustus
-    # Busco command
+        AUG_CONF_DIR=\$( mktemp -d -p \$PWD )
-    AUGUSTUS_CONFIG_PATH=augustus_config busco $args --augustus --mode $mode --cpu $task.cpus --in __UNCOMPRESSED_FASTA_FILE__ --out $meta.id
+        cp -r \$AUGUSTUS_CONFIG_PATH/* \$AUG_CONF_DIR
+        export AUGUSTUS_CONFIG_PATH=\$AUG_CONF_DIR
+        echo "New AUGUSTUS_CONFIG_PATH=\${AUGUSTUS_CONFIG_PATH}"
+    fi
+
+    # Ensure the input is uncompressed
+    gzip -cdf $fasta > ${prefix}_uncompressed.fasta
+
+    busco \\
+        --cpu $task.cpus \\
+        --in ${prefix}_uncompressed.fasta \\
+        --out ${prefix}-busco \\
+        --lineage_dataset $lineage \\
+        $busco_lineage_dir \\
+        $busco_config \\
+        $args
+
+    # clean up
+    rm ${prefix}_uncompressed.fasta
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

tests/modules/busco/main.nf

@@ -2,14 +2,22 @@
 
 nextflow.enable.dsl = 2
 
-include { BUSCO as BUSCO_BACTE } from '../../../modules/busco/main.nf'
+include { BUSCO } from '../../../modules/busco/main.nf'
 
 // This tests genome decompression, empty input channels and data download
 workflow test_busco {
-   input = [ [ id:'test' ], file(params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true) ]    
+
-   BUSCO_BACTE ( input,
+    input = [
-                 "genome",
+        [ id:'test', single_end:false ], // meta map
-                 [],
+        file( params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true)
-                 [] )
+    ]
+
+    BUSCO (
+        input,
+        'bacteria_odb10',
+        [], // Download busco lineage
+        [], // No config
+    )
+
 }
 

tests/modules/busco/nextflow.config

@@ -1,5 +1,6 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-    
+    ext.args = '--mode genome'
-}
+
+}

tests/modules/busco/test.yml

@@ -1,10 +1,7 @@
 - name: busco test_busco
-  command: nextflow run ./tests/modules/busco -entry test_busco -c ./tests/config/nextflow.config -c ./tests/modules/busco/nextflow.config
+  command: nextflow run tests/modules/busco -entry test_busco -c tests/config/nextflow.config
   tags:
     - busco
   files:
-    - path: output/busco/test/run_bacteroidales_odb10/full_table.tsv
+    - path: output/busco/versions.yml
-      md5sum: 8d7b401d875ecd9291b01bf4485bf080
+      md5sum: 921e2abe85bf73e63a8b494453dc83cf
-    - path: output/busco/test/run_bacteroidales_odb10/short_summary.txt
-      contains: ['Complete BUSCOs (C)']
-