nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    mycobactopia-org/MTBseq-nf Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {

    // TODO nf-core: Specify your pipeline's command line flags
    // Input options
    input                      = null// 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
    publish_dir_mode           = 'copy'
    email                      = null
    email_on_fail              = null
    plaintext_email            = false
    monochrome_logs            = false
    hook_url                   = null
    help                       = false
    version                    = false

    // Subworkflows
    only_qc                    = false
    parallel                   = false


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

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

    // Schema validation default options
    validationFailUnrecognisedParams = false
    validationLenientMode            = false
    validationSchemaIgnoreParams     = 'genomes,igenomes_base'
    validationShowHiddenParams       = false
    validate_params                  = true



    //-------------------------------------
    // OPTIONS FROM MTBSEQ MANUAL
    //-------------------------------------

    // Hidden parameters
    user                       = "root"
    mtbseq_path                = "MTBseq"


    // Name of the project and the analysis
    cohort_tsv                 = null
    project                    = "mtbseqnf"

    // Setting this OPTION will add an additional filter that excludes all variants except SNPs.
    snp_vars = false

    // Setting this OPTION has major implications on how the mapping data for each position is processed. By default, the majority allele is called and taken for further calculations.
    // If the --lowfreq_vars OPTION is set, MTBseq will consider the majority allele distinct from wild type, if such an allele is present.
    // This means that only in this detection mode, MTBseq will report variants present only in subpopulations, i.e. low frequency mutations.
    // Of course, OPTIONS --mincovf, --mincovr, --minphred and --minfreq need to be set accordingly.
    // Please be aware that output generated in this detection mode should not be used for phylogenetic analysis.
    lowfreq_vars = false

    // The OPTION sets a threshold for the sequence data quality to be used for the mpileup creation
    minbqual = 13

    // The OPTION sets a minimum forward read coverage threshold. Alleles must have a forward coverage of this VALUE or higher to be considered.
    mincovf = 4

    // The OPTION sets a minimum reverse read coverage threshold. Alleles must have a reverse coverage of this VALUE or higher to be considered.
    mincovr = 4

    // The OPTION sets a minimum number of reads indicating an allele with a phred score of at least 20.
    minphred = 4

    // The OPTION sets a minimum frequency for an allele.
    minfreq = 75

    // The option sets a minimum percentage of samples with unambiguous information for position.
    unambig = 95

    // The OPTION sets a window size in which the algorithm scans for the occurrence of multiple variants within the same sample.
    // If more than one variant occurs within this window in the same sample, the positions will be excluded.
    window = 12

    // The OPTION sets a SNP distance that is used to classify samples into groups of samples, using agglomerative clustering.
    // If SNP distances between samples are less or equal this VALUE, they are grouped together.
    distance = 12

    // The OPTION sets the maximum number of CPUs to use within the pipeline.
    // You can use more than one core in order to execute the pipeline faster. 8 is the current maximum.
    threads = 8

    ref_and_indexes_path = "${projectDir}/data/references/ref/"



    //--------------
    //
    //TODO: Described in https://github.com/mtb-bioinformatics/mtbseq-nf/issues/53
    // --ref This OPTION sets the reference genome for the read mapping.
    // By default, the genome of Mycobacterium tuberculosis H37Rv (NC_000962.3) is set as reference.
    // User supplied FASTA files for other reference genomes should be placed in the directory /MTBseq_source/var/ref/, and the respective name given without .fasta extension.

    // This OPTION sets the reference genome for the read mapping.
    // ref = "${params.ref_and_indexes_path}/M._tuberculosis_H37Rv_2015-11-13.fasta"

    //--------------

    // This OPTION sets a list of known variant positions associated to drug resistance for resistance prediction.
    resilist = "${projectDir}/data/references/res/MTB_Resistance_Mediating.txt"

    // This OPTION sets a list of interesting regions to be used for annotation of detected variants
    intregions = "${projectDir}/data/references/res/MTB_Extended_Resistance_Mediating.txt"

    // This OPTION specifies a gene categories file to annotate essential and non-essential genes as well as repetitive regions. SNPs in repetitive regions will be excluded for phylogenetic analysis.
    categories = "${projectDir}/data/references/cat/MTB_Gene_Categories.txt"

    // This OPTION specifies a file for base quality recalibration. The list must be in VCF format and should contain known SNPs.
    basecalib = "${projectDir}/data/references/res/MTB_Base_Calibration_List.vcf"




}

// 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 mycobactopia-org/MTBseq-nf custom profiles from different institutions.
// Warning: Uncomment only if a pipeline-specific institutional config already exists on nf-core/configs!
// try {
//   includeConfig "${params.custom_config_base}/pipeline/mtbseqnf.config"
// } catch (Exception e) {
//   System.err.println("WARNING: Could not load nf-core/config/mtbseqnf profiles: ${params.custom_config_base}/pipeline/mtbseqnf.config")
// }
profiles {
    debug {
        dumpHashes             = true
        process.beforeScript   = 'echo $HOSTNAME'
        cleanup                = false
        nextflow.enable.configProcessNamesValidation = true
    }
    conda {
        conda.enabled          = true
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
        channels               = ['conda-forge', 'bioconda', 'defaults']
        apptainer.enabled      = false
    }
    mamba {
        conda.enabled          = true
        conda.useMamba         = true
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
        apptainer.enabled      = false
    }
    docker {
        docker.enabled         = true
        conda.enabled          = false
        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
        conda.enabled          = false
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
        apptainer.enabled      = false
    }
    podman {
        podman.enabled         = true
        conda.enabled          = false
        docker.enabled         = false
        singularity.enabled    = false
        shifter.enabled        = false
        charliecloud.enabled   = false
        apptainer.enabled      = false
    }
    shifter {
        shifter.enabled        = true
        conda.enabled          = false
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        charliecloud.enabled   = false
        apptainer.enabled      = false
    }
    charliecloud {
        charliecloud.enabled   = true
        conda.enabled          = false
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        apptainer.enabled      = false
    }
    apptainer {
        apptainer.enabled      = true
        apptainer.autoMounts   = true
        conda.enabled          = false
        docker.enabled         = false
        singularity.enabled    = false
        podman.enabled         = false
        shifter.enabled        = false
        charliecloud.enabled   = false
    }
    gitpod {
        executor.name          = 'local'
        executor.cpus          = 4
        executor.memory        = 8.GB
    }
    test      { includeConfig 'conf/test.config'      }
    test_full { includeConfig 'conf/test_full.config' }
    test_publication { includeConfig 'conf/test_publication.config' }
}

// Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile
// Will not be used unless Apptainer / Docker / Podman / Singularity are enabled
// Set to your registry if you have a mirror of containers
apptainer.registry   = 'quay.io'
docker.registry      = 'quay.io'
podman.registry      = 'quay.io'
singularity.registry = 'quay.io'

// Nextflow plugins
plugins {
    id 'nf-validation@1.1.3' // Validation of pipeline parameters and creation of an input channel from a sample sheet
}

// 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']

// Disable process selector warnings by default. Use debug profile to enable warnings.
nextflow.enable.configProcessNamesValidation = false

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

manifest {
    name            = 'mycobactopia-org/MTBseq-nf'
    author          = """Abhinav Sharma (@abhi18av) and Davi Marcon (@mxrcon)"""
    homePage        = 'https://github.com/mycobactopia-org/MTBseq-nf'
    description     = """`MTBseq-nf` pipeline makes [MTBseq](https://github.com/ngs-fzb/MTBseq_source) simple and easy to use via [Nextflow](https://www.nextflow.io/) workflow manager."""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=23.04.0'
    version         = '1.0'
    doi             = '10.5281/zenodo.5498063'
}


// 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
        }
    }
}