nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    sfglab/dchichip Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {
    /* ========= GENERAL OPTIONS ========= */
    ref_short = "hg38"

    /* ========= REFERENCES & ANNOTATION ========= */
    jaspar_motif = "http://expdata.cmmt.ubc.ca/JASPAR/downloads/UCSC_tracks/2022/hg38/MA0139.1.tsv.gz"
    blacklist = "$projectDir/assets/ENCFF356LFX.bed.gz"
    gtf = "s3://ngi-igenomes/igenomes/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf"
    chrom_size = "$projectDir/assets/hg38.chrom.sizes"
    genomics_features = "https://raw.githubusercontent.com/HuMingLab/MAPS/refs/heads/master/MAPS_data_files/hg38/genomic_features/F_GC_M_MboI_10Kb_el.GRCh38.txt"

    /* ========= MAPPING & FILTERING ========= */
    mapq = 30
    se_samtools_args = null
    se_bwa_mem_args = null
    bwa_mem_args="-M -v 0"
    samtools_fixmate_args="-m"
    optical_duplicate_distance = 0
    remove_duplicates_args="-n"
    filter_quality_args=null
    filter_paires_args=null
    samtools_markdup_args=null
    samtools_sort_2_args="-n"
    bwa_mem_samtools_args=null

    /* ========= PEAKS & LOOPS ========= */
    peak_quality = 0.05
    genome_size = "hs"
    macs3_callpeak_args= null
    maps_args=null
    skip_maps = false

    /* ========= CONTACT MATRICES & BINNING ========= */
    cool_bin = 1000
    cooler_cload_args="pairs --zero-based  -c1 2 -p1 3 -c2 4 -p2 5"
    cooler_zoomify_res = "1000N"
    cooler_zoomify_args= null
    insulation_resultions = ["1000N": "1000 2000 5000 10000 20000 50000 100000 200000 500000"]
    cooltools_eigscis_args="--n-eigs 1"
    cooler_eigscis_resultion = 100000
    calder_bin = 100000
    calder_chrom= "1:22" // needs to be "1,2,3,4,10,12"
    gstripe_args="--fix_bin_start"

    /* ========= VISUALIZATION & QC ========= */
    plot_method = 'spearman'
    plot_type = 'heatmap'
    fastqc_args = "--quiet"
    deeptools_plotcoverage_args = "--skipZeros "
    deeptools_plotcorrelation_args = "--skipZeros --plotTitle \"Spearman Correlation of Read Counts\"  --colorMap RdYlBu --plotNumbers"
    pairtools_parse2_args = null
    juicertools_args = null

    /* ========= Chromatin contact domains (CCD) calling ========= */
    ccd_caller_args=null
    min_loops =  2
    min_length = 15000

    /* ========= 3D GENOME MODELLING (MULTIMM) ========= */
    multimm_platform = "CPU"
    multimm_modelling_level = "chrom"
    multimm_gene_name = null
    multimm_chrom = "chr21"
    multimm_loc_start = null
    multimm_loc_end = null
    multimm_args=null

    // 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
    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

    // 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 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 sfglab/dchichip 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/dchichip.config"
// } catch (Exception e) {
//   System.err.println("WARNING: Could not load nf-core/config/dchichip profiles: ${params.custom_config_base}/pipeline/dchichip.config")
// }

docker.registry = 'quay.io'

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
        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' }
}


// 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            = 'sfglab/dchichip'
    author          = """Ziad Al-Bkhetan"""
    homePage        = 'https://github.com/sfglab/dchichip'
    description     = """Workflow description - to be filled"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=22.10.1'
    version         = '1.0dev'
    doi             = ''
}

plugins {
    id 'nf-schema@2.4.2' // Validation of pipeline parameters and creation of an input channel from a sample sheet
}

validation {
    defaultIgnoreParams = ["insulation_resultions.1000N"]
    monochromeLogs = params.monochrome_logs
    help {
        enabled = true
        command = "nextflow run nf-core/proteinfold -profile <docker/singularity/.../institute> --input samplesheet.csv --outdir <OUTDIR>"
        fullParameter = "help_full"
        showHiddenParameter = "show_hidden"
        beforeText = ""
        afterText = """${manifest.doi ? "\n* The pipeline\n" : ""}${manifest.doi.tokenize(",").collect { "    https://doi.org/${it.trim().replace('https://doi.org/','')}"}.join("\n")}${manifest.doi ? "\n" : ""}

* Software dependencies
    https://github.com/nf-core/proteinfold/blob/master/CITATIONS.md
"""
    }
    summary {
        beforeText = validation.help.beforeText
        afterText = validation.help.afterText
    }
}


// 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
        }
    }
}