nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    bbglab/deepCSA Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Pipeline params
params {

    // Input options
    input                                    = null
    fasta                                    = null
    input_maf                                = null

    features_table                           = null
    features_table_separator                 = 'comma'
    features_unique_identifier               = null
    features_groups_list                     = null
    features_genes_list                      = null

    custom_groups                            = false
    custom_groups_file                       = null
    custom_groups_separator                  = 'tab'

    customize_annotation                     = false
    custom_annotation_tsv                    = ''

    use_custom_bedfile                       = false
    custom_bedfile                           = null
    use_custom_minimum_depth                 = 30

    hotspots_annotation                      = false
    hotspots_definition_file                 = ''

    mutationdensity                          = false

    profileall                               = false
    profilenonprot                           = false
    profileexons                             = false
    profileintrons                           = false
    profile_smoothing                        = false
    positive_selection_non_protein_affecting = false

    oncodrivefml                             = false
    oncodriveclustl                          = false

    oncodrive3d                              = false
    o3d_raw_vep                              = false
    o3d_plot                                 = false
    o3d_plot_chimerax                        = false

    omega                                    = false
    omega_multi                              = false
    omega_globalloc                          = false
    omega_mutabilities                       = false
    site_comparison_grouping                 = 'all'
    omega_plot                               = false

    create_subgenic_regions                  = false
    autodomains                              = false
    autoexons                                = false
    subgenic_regions_complement              = false
    domains_file                             = null
    subgenic_bedfile                         = null
    hotspot_expansion                        = 0

    mutated_cells_vaf                        = false
    mutepi_genes_to_recode                   = null
    expected_mutated_cells                   = false

    dnds                                     = false

    indels                                   = false

    signatures                               = false

    plot_only_allsamples                     = true

    confidence_level                         = 'med'
    pileup_all_duplex                        = false
    plot_depths                              = false
    plot_mutation_specific_qc                = true
    store_depths                             = false

    use_custom_depths                        = false
    custom_depths_table                      = null

    contamination                            = false

    downsample                               = false
    downsample_proportion                    = 1

    regressions                              = false
    bbgr_mode                                = "default"


    filter_criteria                          = ["notcontains low_mappability", "notcontains not_covered", "notcontains no_pileup_support", "notcontains nanoseq_noise", "notcontains NM20", "notcontains cohort_n_rich", "notcontains n_rich", "notcontains cohort_n_rich_threshold"]
    filter_criteria_somatic                  = ["notcontains nanoseq_snp", "notcontains gnomAD_SNP"]
    no_filter                                = false


    // depth and panel
    sample_panel_min_depth                   = 40
    consensus_panel_min_depth                = 200
    consensus_compliance                     = 0.8
    min_muts_per_sample                      = 0
    selected_genes                           = ''
    panel_with_canonical                     = true
    panel_sites_chunk_size                   = 1000000  // 0 means no chunking (default), set to positive integer to enable chunking

    germline_threshold                       = 0.3
    mutation_depth_threshold                 = 100
    gnomad_af_threshold                      = 1e-3

    repetitive_variant_thres                 = 5
    prop_samples_nrich                       = 0.1
    blacklist_mutations                      = null


    cosmic_ref_signatures                    = "COSMIC_v3.4_SBS_GRCh38.txt"
    indel_ref_signatures                     = "COSMIC_v3.4_ID_GRCh37.txt" // note that for IDs it has been defined in the GRCh37 genome version
    wgs_trinuc_counts                        = "assets/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
    cadd_scores                              = "CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz"
    cadd_scores_ind                          = "CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz.tbi"

    // dnds
    dnds_ref_transcripts                     = "RefCDS_human_latest_intogen.rda"
    dnds_covariates                          = "covariates_hg19_hg38_epigenome_pcawg.rda"

    // oncodrive3d
    datasets3d                               = "oncodrive3d/datasets"
    annotations3d                            = "oncodrive3d/annotations"

    // nanoseq masks
    nanoseq_snp                              = null
    nanoseq_noise                            = null

    // sigprofilerassignment
    exclude_subgroups                        = null


    // References for Ensembl VEP
    vep_cache                                = ".vep"

    // Ensembl VEP for homo_sapiens
    vep_genome                               = "GRCh38"
    vep_species                              = "homo_sapiens"
    vep_cache_version                        = 111
    vep_out_format                           = "tab"
    vep_params                               = "--no_stats --cache --offline --symbol --protein --canonical --af_gnomadg --af_gnomade"
    vep_params_panel                         = "--no_stats --cache --offline --symbol --protein --canonical"
}

// Load default regressions parameters
includeConfig 'conf/tools/regressions.config'



// Global default params, used in configs
params {

    // 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

    // Config options
    config_profile_name         = null
    config_profile_description  = null

    // Max resource options
    // Defaults only, expecting to be overwritten
    max_memory                  = 950.GB
    max_cpus                    = 196
    max_time                    = 30.d

    validate_params             = true
}

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



profiles {
    debug {
        dumpHashes           = true
        process.beforeScript = 'echo $HOSTNAME'
        cleanup              = false
    }
    conda {
        conda.enabled        = true
        docker.enabled       = false
        singularity.enabled  = false
        podman.enabled       = false
        shifter.enabled      = false
        charliecloud.enabled = false
        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
    }
    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
    }
    irbcluster {
        includeConfig 'conf/general_files_IRB.config'
    }
    local {
        includeConfig 'conf/local.config'
    }
    test {
        includeConfig 'conf/test.config'
    }
    test_real {
        includeConfig 'conf/test_real.config'
    }
    test_regressions {
        includeConfig 'conf/deepcsa_config_bbgregressions_test.config'
    }

    basic {
        includeConfig 'conf/modes/basic.config'
    }
    clonal_structure {
        includeConfig 'conf/modes/clonal_structure.config'
    }
    get_signatures {
        includeConfig 'conf/modes/get_signatures.config'
    }

    mice {
        includeConfig 'conf/mice.config'
    }

    exome {
        includeConfig 'conf/exome.config'
    }
}




// Nextflow plugins
plugins {
    id 'nf-schema@2.3.0'
}

// 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"
    BGDATA_OFFLINE   = "TRUE"
    HOME             = "/tmp"
}

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

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

manifest {
    name            = 'bbglab/deepCSA'
    author          = 'Ferriol Calvet'
    homePage        = 'https://github.com/bbglab/deepCSA'
    description     = 'deepCSA : deepClonalStructureAnalysis is a pipeline for the analysis of the clonal structure of tissues using duplex-sequencing data.'
    mainScript      = 'main.nf'
    nextflowVersion = '!>=25.04.2'
    version         = '1.0.1.dev'
    doi             = 'dx.doi.org/10.17504/protocols.io.dm6gp1jodgzp/v2'
}

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