nextflow.config

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

// Global default params, used in configs
params {

    // Input options
    input                      = null

    // References
    genome                     = null
    splicesites                = null
    gtf_extra_attributes       = 'gene_name'
    gtf_group_features         = 'gene_id'
    featurecounts_feature_type = 'exon'
    featurecounts_group_type   = 'gene_biotype'
    gencode                    = false
    save_reference             = false
    igenomes_base              = 's3://ngi-igenomes/igenomes'
    igenomes_ignore            = false

    // UMI handling
    with_umi                   = false
    skip_umi_extract           = false
    umitools_extract_method    = 'string'
    umitools_grouping_method   = 'directional'
    umitools_dedup_stats       = false
    umitools_bc_pattern        = null
    umitools_bc_pattern2       = null
    umitools_umi_separator     = null
    umi_discard_read           = null
    save_umi_intermeds         = false

    // Trimming
    min_trimmed_reads          = 10000
    clip_r1                    = null
    clip_r2                    = null
    three_prime_clip_r1        = null
    three_prime_clip_r2        = null
    trim_nextseq               = null
    save_trimmed               = false
    skip_trimming              = false

    // BBSplit genome filtering
    bbsplit_fasta_list         = null
    save_bbsplit_reads         = false
    skip_bbsplit               = true

    // Ribosomal RNA removal
    remove_ribo_rna            = false
    save_non_ribo_reads        = false
    ribo_database_manifest     = "${projectDir}/assets/rrna-db-defaults.txt"

    // Alignment
    aligner                    = 'star_salmon'
    pseudo_aligner             = null
    seq_center                 = null
    bam_csi_index              = false
    star_ignore_sjdbgtf        = false
    salmon_quant_libtype       = null
    hisat2_build_memory        = '200.GB'  // Amount of memory required to build HISAT2 index with splice sites
    stringtie_ignore_gtf       = false
    min_mapped_reads           = 5
    extra_star_align_args      = null
    extra_salmon_quant_args    = null
    save_merged_fastq          = false
    save_unaligned             = false
    save_align_intermeds       = false
    skip_markduplicates        = false
    skip_alignment             = false

    // QC
    skip_qc                    = false
    skip_bigwig                = false
    skip_stringtie             = false
    skip_fastqc                = false
    skip_preseq                = true
    skip_dupradar              = false
    skip_qualimap              = false
    skip_rseqc                 = false
    skip_biotype_qc            = false
    skip_deseq2_qc             = false
    skip_multiqc               = false
    deseq2_vst                 = true
    rseqc_modules              = 'bam_stat,inner_distance,infer_experiment,junction_annotation,junction_saturation,read_distribution,read_duplication'

    // 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
    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       = 'genomes'

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

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
        docker.userEmulation   = 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' }
}

// 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"
}

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            = 'nf-core/rnaseq'
    author          = """Harshil Patel, Phil Ewels, Rickard Hammarén"""
    homePage        = 'https://github.com/nf-core/rnaseq'
    description     = """RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control."""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=22.10.1'
    version         = '3.10.1'
    doi             = 'https://doi.org/10.5281/zenodo.1400710'
}

// 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
        }
    }
}