nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    MDHHS-Bioinformatics/corge Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {

    // Input and output options
    input                               = null
    outdir                              = "${launchDir}/corge_results"
    cgmlst_schemas                      = null // CSV containing paths to cgmlst schemas per species
    rename_files                        = true // Rename input files to use sample name instead of the assembly name
    mode                                = 'default'
    hc_thresholds                       = '15,20,40,150'
    samples_to_remove                   = null // CSV containing sample ids and species to remove from database if mode is 'remove'
    species                             = null // String separated by commas with species to regroup if mode is 'regroup' or to build ML tree if mode 'tree' using prior results
    use_previous_partitions_for_snp     = false // Do not use prior partition nomenclature to run ReporTree when using SNPs

    // PoODLE manifest options
    master_paths                        = null
    phoenix_path                        = null
    bactopia_path                       = null
    
    // cgMLST download
    trn_files                           = "${baseDir}/training_files"
    schema_info                         = "${baseDir}/assets/schemas_info.csv"
    species_schemas                     = "${baseDir}/assets/species_schemas.csv"
    schema_ids                          = null

    // cgMLST create
    assembly_sheet                      = null
    reference_path                      = null
    cgmlst_threshold                    = 0.95

    // ReporTree metadata options
    metadata                            = null
    columns_summary_report              = null
    metadata2report                     = null
    filter                              = null
    frequency_matrix                    = null
    count_matrix                        = null

    // Microreact visualization 
    microreact_template                 = "${projectDir}/assets/template_corge.microreact"
    microreact_template_ml              = "${projectDir}/assets/template_corge_ml.microreact"

    // Phylogenetic tree options
    tree                                = false

    // MultiQC options
    multiqc_config             = null
    multiqc_title              = null
    multiqc_logo               = null
    max_multiqc_email_size     = '25.MB'
    multiqc_methods_description = null

    // Boilerplate options
    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       = 'schema_ids,species_schemas,schema_info,trn_files,mode,rename_files,hc_thresholds,microreact_template,cgmlst_schemas,schemas_file,bactopia_path,phoenix_path,master_paths,count_matrix,frequency_matrix,filter,metadata2report,columns_summary_report,metadata,microreact_template_ml,species_to_regroup,use_previous_partitions_for_snp'


    // 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'

}

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

// Load modules_default.config if running samples
if( params.mode == 'default' ) {
    includeConfig 'conf/modules_default.config'
}

// Load modules_download_cgmlst.config if downloading schemas
if( params.mode == 'download_schema' ) {
    includeConfig 'conf/modules_download_cgmlst.config'
}

// Load modules_create_cgmlst.config if downloading schemas
if( params.mode == 'create_schema' ) {
    includeConfig 'conf/modules_create_cgmlst.config'
}

// Load modules_remove.config if removing samples
if( params.mode == 'remove' ) {
    includeConfig 'conf/modules_remove.config'
}

// Load modules_regroup.config if regrouping samples
if( params.mode == 'regroup' ) {
    includeConfig 'conf/modules_regroup.config'
}

// Load modules_tree.config if building phylogenetic tree
if( params.mode == 'tree' ) {
    includeConfig 'conf/modules_tree.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 MDHHS-Bioinformatics/corge 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/corgeplus.config"
// } catch (Exception e) {
//   System.err.println("WARNING: Could not load nf-core/config/corgeplus profiles: ${params.custom_config_base}/pipeline/corgeplus.config")
// }


profiles {
    debug {
        dumpHashes              = true
        process.beforeScript    = 'echo $HOSTNAME'
        cleanup                 = false
        nextflow.enable.configProcessNamesValidation = true
    }
    docker {
        docker.enabled          = true
        singularity.enabled     = false
        podman.enabled          = false
        shifter.enabled         = false
        charliecloud.enabled    = false
        apptainer.enabled       = false
        docker.runOptions       = '-u $(id -u):$(id -g)'
    }
    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
        apptainer.enabled       = false
    }
    podman {
        podman.enabled          = true
        docker.enabled          = false
        singularity.enabled     = false
        shifter.enabled         = false
        charliecloud.enabled    = false
        apptainer.enabled       = false
    }
    shifter {
        shifter.enabled         = true
        docker.enabled          = false
        singularity.enabled     = false
        podman.enabled          = false
        charliecloud.enabled    = false
        apptainer.enabled       = false
    }
    charliecloud {
        charliecloud.enabled    = true
        docker.enabled          = false
        singularity.enabled     = false
        podman.enabled          = false
        shifter.enabled         = false
        apptainer.enabled       = false
    }
    apptainer {
        apptainer.enabled       = true
        apptainer.autoMounts    = true
        docker.enabled          = false
        singularity.enabled     = false
        podman.enabled          = false
        shifter.enabled         = false
        charliecloud.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' }
}


// 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            = 'MDHHS-Bioinformatics/corge'
    author          = "Karla Vasco, Douglas Maldonado-Torres, Heather Blankenship & Arianna Miles-Jay"
    homePage        = 'https://github.com/MDHHS-Bioinformatics/corge'
    description     = """Core Genome plus"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=22.10.1'
    version         = '1.0.0'
    doi             = 'https://doi.org/10.5281/zenodo.20857090'
}

// 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
        }
    }
}