taxprofiler/nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    nf-core/taxprofiler Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {

    // Input options
    input                      = null


    // References
    genome                     = null
    igenomes_base              = 's3://ngi-igenomes/igenomes'
    igenomes_ignore            = false
    // MultiQC options
    multiqc_config             = null
    multiqc_title              = null
    multiqc_logo               = null
    max_multiqc_email_size     = '25.MB'
    multiqc_methods_description = null

    // Boilerplate options
    outdir                     = null
    tracedir                   = "${params.outdir}/pipeline_info"
    publish_dir_mode           = 'copy'
    email                      = null
    email_on_fail              = null
    plaintext_email            = false
    monochrome_logs            = false
    hook_url                   = null
    help                       = false
    version                    = false
    validate_params            = true
    show_hidden_params         = false
    schema_ignore_params       = 'genomes,fasta'


    // Config options
    custom_config_version      = 'master'
    custom_config_base         = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
    config_profile_description = null
    config_profile_contact     = null
    config_profile_url         = null
    config_profile_name        = null


    // Max resource options
    // Defaults only, expecting to be overwritten
    max_memory                 = '128.GB'
    max_cpus                   = 16
    max_time                   = '240.h'

    // Databases
    databases = null

    // FASTQ preprocessing
    preprocessing_qc_tool            = 'fastqc'

    perform_shortread_qc             = false
    shortread_qc_tool                = 'fastp'
    shortread_qc_skipadaptertrim     = false
    shortread_qc_mergepairs          = false
    shortread_qc_includeunmerged     = false
    shortread_qc_adapter1            = null
    shortread_qc_adapter2            = null
    shortread_qc_adapterlist         = null
    shortread_qc_minlength           = 15

    perform_longread_qc                   = false
    longread_qc_skipadaptertrim           = false
    longread_qc_skipqualityfilter         = false
    longread_qc_qualityfilter_minlength   = 1000
    longread_qc_qualityfilter_keeppercent = 90
    longread_qc_qualityfilter_targetbases = 500000000

    save_preprocessed_reads          = false

    // Complexity filtering
    perform_shortread_complexityfilter                   = false
    shortread_complexityfilter_tool                      = 'bbduk'
    shortread_complexityfilter_entropy                   = 0.3
    shortread_complexityfilter_bbduk_windowsize          = 50
    shortread_complexityfilter_bbduk_mask                = false
    shortread_complexityfilter_prinseqplusplus_mode      = 'entropy'
    shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
    shortread_complexityfilter_fastp_threshold           = 30
    save_complexityfiltered_reads                        = false

    // run merging
    perform_runmerging          = false
    save_runmerged_reads        = false

    // Host Removal
    perform_shortread_hostremoval          = false
    perform_longread_hostremoval           = false
    hostremoval_reference                  = null
    shortread_hostremoval_index            = null
    longread_hostremoval_index             = null
    save_hostremoval_index                 = false
    save_hostremoval_bam                    = false
    save_hostremoval_unmapped              = false


    // MALT
    run_malt                   = false
    malt_mode                  = 'BlastN'
    malt_generate_megansummary = false
    malt_save_reads            = false // added via map + database args extension in profiling.nf

    // kraken2
    run_kraken2                     = false
    kraken2_save_reads              = false // added directly to module in profiling.nf
    kraken2_save_readclassification = false // added directly to module in profiling.nf
    kraken2_save_minimizers         = false

    //krakenuniq
    run_krakenuniq                      = false
    krakenuniq_ram_chunk_size           = '16G'
    krakenuniq_save_reads               = false // added directly to module in profiling.nf
    krakenuniq_save_readclassifications = false // added directly to module in profiling.nf

    // Bracken
    run_bracken = false

    // centrifuge
    run_centrifuge             = false
    centrifuge_save_reads      = false // added directly to module in profiling.nf

    // metaphlan3
    run_metaphlan3             = false

    // kaiju
    run_kaiju                  = false
    kaiju_taxon_rank           = 'species'

    // diamond
    run_diamond                = false
    diamond_output_format      = 'tsv'  // TSV is only format with taxonomic information apparently
    diamond_save_reads         = false // this will override default diamond output format so no taxonomic profile is generated! added directly to module in profiling.nf

    // mOTUs
    run_motus                       = false
    motus_use_relative_abundance    = false
    motus_remove_ncbi_ids           = false
    motus_save_mgc_read_counts      = false

    // krona
    run_krona                  = false
    krona_taxonomy_directory   = null

    // profile standardisation
    run_profile_standardisation             = false
    standardisation_taxpasta_format         = 'tsv'
    taxpasta_taxonomy_dir                   = null
    taxpasta_add_name                       = false
    taxpasta_add_rank                       = false
    taxpasta_add_lineage                    = false
    taxpasta_add_idlineage                  = false
    standardisation_motus_generatebiom      = false
}

// Load base.config by default for all pipelines
includeConfig 'conf/base.config'

// Load nf-core custom profiles from different Institutions
try {
    includeConfig "${params.custom_config_base}/nfcore_custom.config"
} catch (Exception e) {
    System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
}

// Load nf-core/taxprofiler custom profiles from different institutions.
// Warning: Uncomment only if a pipeline-specific instititutional config already exists on nf-core/configs!
try {
    includeConfig "${params.custom_config_base}/pipeline/taxprofiler.config"
} catch (Exception e) {
    System.err.println("WARNING: Could not load nf-core/config/taxprofiler profiles: ${params.custom_config_base}/pipeline/taxprofiler.config")
}


profiles {
    debug { process.beforeScript = 'echo $HOSTNAME' }
    conda {
        conda.enabled          = true
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
    }
    mamba {
        conda.enabled          = true
        conda.useMamba         = true
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
    }
    docker {
        docker.enabled         = true
        docker.userEmulation   = true
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
    }
    arm {
        docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64'
    }
    singularity {
        singularity.enabled    = true
        singularity.autoMounts = true
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
    }
    podman {
        podman.enabled         = true
        docker.enabled         = false
        singularity.enabled    = false
        shifter.enabled        = false
        charliecloud.enabled   = false
    }
    shifter {
        shifter.enabled        = true
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        charliecloud.enabled   = false
    }
    charliecloud {
        charliecloud.enabled   = true
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
    }
    gitpod {
        executor.name          = 'local'
        executor.cpus          = 16
        executor.memory        = 60.GB
    }
    test                    { includeConfig 'conf/test.config'      }
    test_full               { includeConfig 'conf/test_full.config' }
    test_noprofiling        { includeConfig 'conf/test_noprofiling.config' }
    test_nopreprocessing    { includeConfig 'conf/test_nopreprocessing.config' }
    test_nothing            { includeConfig 'conf/test_nothing.config' }
    test_motus              { includeConfig 'conf/test_motus.config' }
    test_krakenuniq         { includeConfig 'conf/test_krakenuniq.config' }
}


// Load igenomes.config if required

if (!params.igenomes_ignore) {
    includeConfig 'conf/igenomes.config'
} else {
    params.genomes = [:]
}


// Export these variables to prevent local Python/R libraries from conflicting with those in the container
// The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
// See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.

env {
    PYTHONNOUSERSITE = '1'
    R_PROFILE_USER   = "/.Rprofile"
    R_ENVIRON_USER   = "/.Renviron"
    JULIA_DEPOT_PATH = "/usr/local/share/julia"
}

// Capture exit codes from upstream processes when piping
process.shell = ['/bin/bash', '-euo', 'pipefail']

def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
timeline {
    enabled = true
    file    = "${params.tracedir}/execution_timeline_${trace_timestamp}.html"
}
report {
    enabled = true
    file    = "${params.tracedir}/execution_report_${trace_timestamp}.html"
}
trace {
    enabled = true
    file    = "${params.tracedir}/execution_trace_${trace_timestamp}.txt"
}
dag {
    enabled = true
    file    = "${params.tracedir}/pipeline_dag_${trace_timestamp}.html"
}

manifest {
    name            = 'nf-core/taxprofiler'
    author          = """James A. Fellows Yates, Sofia Stamouli, Moritz E. Beber, Lauri Mesilaakso, Thomas A. Christensen II, Jianhong Ou, Mahwash Jamy, Maxime Borry, Rafal Stepien, Tanja Normark"""
    homePage        = 'https://github.com/nf-core/taxprofiler'
    description     = """Taxonomic classification and profiling of shotgun metagenomic data"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=22.10.1'
    version = '1.1.0dev'
    doi             = ''
}

// Load modules.config for DSL2 module specific options
includeConfig 'conf/modules.config'

// Function to ensure that resource requirements don't go beyond
// a maximum limit
def check_max(obj, type) {
    if (type == 'memory') {
        try {
            if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1)
                return params.max_memory as nextflow.util.MemoryUnit
            else
                return obj
        } catch (all) {
            println "   ### ERROR ###   Max memory '${params.max_memory}' is not valid! Using default value: $obj"
            return obj
        }
    } else if (type == 'time') {
        try {
            if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1)
                return params.max_time as nextflow.util.Duration
            else
                return obj
        } catch (all) {
            println "   ### ERROR ###   Max time '${params.max_time}' is not valid! Using default value: $obj"
            return obj
        }
    } else if (type == 'cpus') {
        try {
            return Math.min( obj, params.max_cpus as int )
        } catch (all) {
            println "   ### ERROR ###   Max cpus '${params.max_cpus}' is not valid! Using default value: $obj"
            return obj
        }
    }
}