nextflow.config

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

params {
    // Workflow flags:

    // Mandatory arguments
    input = null      // No default input
    step  = 'mapping' // Starts with mapping

    // References
    genome           = 'GATK.GRCh38'
    igenomes_base    = 's3://ngi-igenomes/igenomes'
    igenomes_ignore  = false
    save_reference   = false // Built references not saved
    build_only_index = false // Only build the reference indexes
    download_cache   = false // Do not download annotation cache

    // Main options
    no_intervals           = false      // Intervals will be built from the fasta file
    nucleotides_per_second = 200000     // Default interval size
    tools                  = null       // No default Variant_Calling or Annotation tools
    skip_tools             = null       // All tools (markduplicates + baserecalibrator + QC) are used by default
    split_fastq            = 50000000   // FASTQ files will not be split by default by FASTP

    // Modify fastqs (trim/split) with FASTP
    trim_fastq          = false // No trimming
    clip_r1             = 0
    clip_r2             = 0
    three_prime_clip_r1 = 0
    three_prime_clip_r2 = 0
    trim_nextseq        = 0
    save_trimmed        = false
    save_split_fastqs   = false

    // UMI tagged reads
    umi_read_structure    = null        // no UMI
    group_by_umi_strategy = 'Adjacency' // default strategy when running with UMI for GROUPREADSBYUMI

    // Preprocessing
    aligner            = 'bwa-mem'  // Default is bwa-mem, bwa-mem2 and dragmap can be used too
    use_gatk_spark     = null       // GATK Spark implementation of their tools in local mode not used by default
    save_mapped        = false      // Mapped BAMs not saved
    save_output_as_bam = false      // Output files from preprocessing are saved as bam and not as cram files
    seq_center         = null       // No sequencing center to be written in read group CN field by aligner
    seq_platform       = 'ILLUMINA' // Default platform written in read group PL field by aligner

    // Variant Calling
    only_paired_variant_calling   = false // if true, skips germline variant calling for normal-paired samples
    ascat_ploidy                  = null  // default value for ASCAT
    ascat_min_base_qual           = 20    // default value for ASCAT
    ascat_min_counts              = 10    // default value for ASCAT
    ascat_min_map_qual            = 35    // default value for ASCAT
    ascat_purity                  = null  // default value for ASCAT
    cf_ploidy                     = "2"   // default value for Control-FREEC
    cf_coeff                      = 0.05  // default value for Control-FREEC
    cf_contamination              = 0     // default value for Control-FREEC
    cf_contamination_adjustment   = false // by default we are not using this in Control-FREEC
    cf_mincov                     = 0     // ControlFreec default values
    cf_minqual                    = 0     // ControlFreec default values
    cf_window                     = null  // by default we are not using this in Control-FREEC
    cnvkit_reference              = null  // by default the reference is build from the fasta file
    concatenate_vcfs              = false // by default we don't concatenate the germline-vcf-files
    ignore_soft_clipped_bases     = false // no --dont-use-soft-clipped-bases for GATK Mutect2
    wes                           = false // Set to true, if data is exome/targeted sequencing data. Used to use correct models in various variant callers
    joint_germline                = false // g.vcf & joint germline calling are not run by default if HaplotypeCaller is selected
    joint_mutect2                = false // if true, enables patient-wise multi-sample somatic variant calling
    sentieon_haplotyper_emit_mode = "variant" // default value for Sentieon haplotyper

    // Annotation
    dbnsfp                    = null // No dbnsfp processed file
    dbnsfp_consequence        = null // No default consequence for dbnsfp plugin
    dbnsfp_fields             = "rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF" // Default fields for dbnsfp plugin
    dbnsfp_tbi                = null // No dbnsfp processed file index
    outdir_cache              = null // No default outdir cache
    snpeff_cache              = 's3://annotation-cache/snpeff_cache/'
    spliceai_indel            = null // No spliceai_indel file
    spliceai_indel_tbi        = null // No spliceai_indel file index
    spliceai_snv              = null // No spliceai_snv file
    spliceai_snv_tbi          = null // No spliceai_snv file index
    use_annotation_cache_keys = false
    vep_cache                 = 's3://annotation-cache/vep_cache/'
    vep_custom_args           = "--everything --filter_common --per_gene --total_length --offline --format vcf" // Default arguments for VEP
    vep_dbnsfp                = null // dbnsfp plugin disabled within VEP
    vep_include_fasta         = false // Don't use fasta file for annotation with VEP
    vep_loftee                = null // loftee plugin disabled within VEP
    vep_out_format            = "vcf"
    vep_spliceai              = null // spliceai plugin disabled within VEP
    vep_spliceregion          = null // spliceregion plugin disabled within VEP

    // 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
    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
    test_data_base             = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek3'

    // 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            = true
    validationSchemaIgnoreParams     = 'cf_ploidy,genomes,igenomes_base'
    validationShowHiddenParams       = false
    validate_params                  = true
}

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

profiles {
    debug {
        cleanup                = false
        dumpHashes             = true
        process.beforeScript   = 'echo $HOSTNAME'
    }
    conda {
        apptainer.enabled      = false
        charliecloud.enabled   = false
        conda.enabled          = true
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        singularity.enabled    = false
    }
    mamba {
        apptainer.enabled      = false
        charliecloud.enabled   = false
        conda.enabled          = true
        conda.useMamba         = true
        charliecloud.enabled   = false
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        singularity.enabled    = false
    }
    docker {
        apptainer.enabled      = false
        charliecloud.enabled   = false
        conda.enabled          = false
        docker.enabled         = true
        docker.userEmulation   = { params.use_gatk_spark ? false : true }.call()
        podman.enabled         = false
        shifter.enabled        = false
        singularity.enabled    = false
    }
    arm {
        docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64'
    }
    singularity {
        apptainer.enabled      = false
        charliecloud.enabled   = false
        conda.enabled          = false
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        singularity.autoMounts = true
        singularity.enabled    = true
    }
    podman {
        apptainer.enabled      = false
        charliecloud.enabled   = false
        conda.enabled          = false
        docker.enabled         = false
        podman.enabled         = true
        shifter.enabled        = false
        singularity.enabled    = false
    }
    shifter {
        apptainer.enabled      = false
        charliecloud.enabled   = false
        conda.enabled          = false
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = true
        singularity.enabled    = false
    }
    charliecloud {
        apptainer.enabled      = false
        charliecloud.enabled   = true
        conda.enabled          = false
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        singularity.enabled    = false
    }
    apptainer {
        apptainer.enabled      = true
        apptainer.autoMounts   = true
        charliecloud.enabled   = false
        conda.enabled          = false
        docker.enabled         = false
        podman.enabled         = false
        shifter.enabled        = false
        singularity.enabled    = false
    }
    gitpod {
        executor.cpus          = 4
        executor.memory        = 8.GB
        executor.name          = 'local'
    }
    // Basic test profile for CI
    test                       { includeConfig 'conf/test.config' }
    test_cache                 { includeConfig 'conf/test/cache.config' }
    // Extra test profiles for full tests on AWS
    test_full                  { includeConfig 'conf/test_full.config' }
    test_full_germline         { includeConfig 'conf/test_full_germline.config' }
    // Extra test profiles for more complete CI
    alignment_to_fastq         { includeConfig 'conf/test/alignment_to_fastq.config' }
    annotation                 { includeConfig 'conf/test/annotation.config' }
    markduplicates_bam         { includeConfig 'conf/test/markduplicates_bam.config' }
    markduplicates_cram        { includeConfig 'conf/test/markduplicates_cram.config' }
    no_intervals               { includeConfig 'conf/test/no_intervals.config' }
    pair                       { includeConfig 'conf/test/pair.config' }
    prepare_recalibration_bam  { includeConfig 'conf/test/prepare_recalibration_bam.config' }
    prepare_recalibration_cram { includeConfig 'conf/test/prepare_recalibration_cram.config' }
    recalibrate_bam            { includeConfig 'conf/test/recalibrate_bam.config' }
    recalibrate_cram           { includeConfig 'conf/test/recalibrate_cram.config' }
    save_bam_mapped            { includeConfig 'conf/test/save_bam_mapped.config' }
    sentieon_dedup_bam         { includeConfig 'conf/test/sentieon_dedup_bam.config' }
    sentieon_dedup_cram        { includeConfig 'conf/test/sentieon_dedup_cram.config' }
    skip_bqsr                  { includeConfig 'conf/test/skip_bqsr.config' }
    skip_markduplicates        { includeConfig 'conf/test/skip_markduplicates.config' }
    split_fastq                { includeConfig 'conf/test/split_fastq.config' }
    targeted                   { includeConfig 'conf/test/targeted.config' }
    tools                      { includeConfig 'conf/test/tools.config' }
    tools_germline             { includeConfig 'conf/test/tools_germline.config' }
    tools_somatic              { includeConfig 'conf/test/tools_somatic.config' }
    tools_somatic_ascat        { includeConfig 'conf/test/tools_somatic_ascat.config' }
    tools_tumoronly            { includeConfig 'conf/test/tools_tumoronly.config' }
    trimming                   { includeConfig 'conf/test/trimming.config' }
    umi                        { includeConfig 'conf/test/umi.config' }
    use_gatk_spark             { includeConfig 'conf/test/use_gatk_spark.config' }
    variantcalling_channels    { includeConfig 'conf/test/variantcalling_channels.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' // Validation of pipeline parameters and creation of an input channel from a sample sheet
    id 'nf-prov'       // Provenance reports for pipeline runs
}

// 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    = "${params.outdir}/pipeline_info/execution_timeline_${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"
}
prov {
    enabled = true
    file    = "${params.outdir}/pipeline_info/manifest_${trace_timestamp}.bco.json"
}

manifest {
    name            = 'nf-core/sarek'
    author          = """Maxime Garcia, Szilveszter Juhos, Friederike Hanssen"""
    homePage        = 'https://github.com/nf-core/sarek'
    description     = """An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=23.04.0'
    version         = '3.3.2'
    doi             = '10.12688/f1000research.16665.2, 10.1101/2023.07.19.549462, 10.5281/zenodo.3476425'
}

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

// Load more modules specific config for DSL2 module specific options

// prepare reference
includeConfig 'conf/modules/prepare_cache.config'
includeConfig 'conf/modules/prepare_genome.config'
includeConfig 'conf/modules/prepare_intervals.config'

// preprocessing
includeConfig 'conf/modules/aligner.config'
includeConfig 'conf/modules/alignment_to_fastq.config'
includeConfig 'conf/modules/markduplicates.config'
includeConfig 'conf/modules/sentieon_dedup.config'
includeConfig 'conf/modules/prepare_recalibration.config'
includeConfig 'conf/modules/recalibrate.config'
includeConfig 'conf/modules/trimming.config'
includeConfig 'conf/modules/umi.config'

// variant calling
includeConfig 'conf/modules/ascat.config'
includeConfig 'conf/modules/cnvkit.config'
includeConfig 'conf/modules/controlfreec.config'
includeConfig 'conf/modules/deepvariant.config'
includeConfig 'conf/modules/freebayes.config'
includeConfig 'conf/modules/haplotypecaller.config'
includeConfig 'conf/modules/joint_germline.config'
includeConfig 'conf/modules/manta.config'
includeConfig 'conf/modules/mpileup.config'
includeConfig 'conf/modules/msisensorpro.config'
includeConfig 'conf/modules/mutect2.config'
includeConfig 'conf/modules/sentieon_haplotyper.config'
includeConfig 'conf/modules/sentieon_joint_germline.config'
includeConfig 'conf/modules/strelka.config'
includeConfig 'conf/modules/tiddit.config'

includeConfig 'conf/modules/post_variant_calling.config'

//annotate
includeConfig 'conf/modules/annotate.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
        }
    }
}