nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    bigbio/spectrafuse Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {
    // Input options
    parquet_dir = null

    // Optional path to an existing cluster DB. When set, the new QPX data is
    // clustered *together with* representative spectra from the existing DB,
    // and results are merged in (preserving cluster IDs where reps appear).
    existing_cluster_db = null
    // Default species/instrument when QPX metadata grouping is not yet implemented
    default_species = null
    default_instrument = null

    // MaraCluster parameters
    maracluster_pvalue_threshold = -10.0 // Set log10(p-value) threshold for MaraCluster (default -10.0 = p-value 1e-10)
    maracluster_verbose = false // Set to true to enable verbose output from MaraCluster
    maracluster_files_list_folder = null // Set to a folder containing a list of files to process with MaraCluster
    maracluster_output_folder = './' // Set to a folder to output the results of MaraCluster
    maracluster_precursor_tolerance = 20.0 // Set the precursor tolerance for MaraCluster
    cluster_threshold = 30 // Set the p-value threshold for MaRaCluster output file naming (e.g., *_p30.tsv)

    // Partitioning parameters
    skip_instrument = false // Set to true to cluster all instruments together (no instrument partitioning)

    // Precursor m/z windowing parameters (parallelizes MaRaCluster within each charge)
    mz_window_size = 300    // Width of each precursor m/z window in Da
    mz_window_overlap = 1.0 // Overlap between adjacent windows in Da (safety margin)

    // Incremental mode parameters (dat-based, no MGF)

    // MSP format generation parameters (consensus spectrum parameters)
    strategytype = 'best' // Strategy type for consensus spectrum generation
    sim = 'dot' // Similarity metric for consensus spectrum
    fragment_mz_tolerance = 0.02 // Fragment m/z tolerance for consensus spectrum
    min_mz = 100 // Minimum m/z value
    max_mz = 2000 // Maximum m/z value
    bin_size = 0.02 // Bin size for m/z binning
    peak_quorum = 0.25 // Peak quorum threshold
    edge_case_threshold = 0.5 // Edge case threshold
    diff_thresh = 0.01 // Difference threshold
    dyn_range = 1000 // Dynamic range
    min_fraction = 0.5 // Minimum fraction
    pepmass = 'lower_median' // Peptide mass calculation method
    msms_avg = 'weighted' // MS/MS averaging method

    // Boilerplate options
    outdir                     = './results'
    publish_dir_mode           = 'copy'
    email                      = null
    email_on_fail              = null
    plaintext_email            = false
    monochrome_logs            = false
    hook_url                   = System.getenv('HOOK_URL')
    help                       = false
    help_full                  = false
    show_hidden                = false
    version                    = false
    trace_report_suffix        = new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')

    // 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_description = null
    config_profile_contact     = null
    config_profile_url         = null

    // Schema validation default options
    validate_params            = true

    // Resource limits
    max_memory = 128.GB
    max_cpus = 16
    max_time = 240.h
}

// Function to ensure that resource requirements don't go beyond a maximum limit
// Must be defined before base.config is included
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
        }
    }
}

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

profiles {
    debug {
        dumpHashes              = true
        process.beforeScript    = 'echo $HOSTNAME'
        cleanup                 = false
        nextflow.enable.configProcessNamesValidation = true
    }
    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)'
    }
    arm64 {
        process.arch            = 'arm64'
        apptainer.ociAutoPull   = true
        singularity.ociAutoPull = true
        wave.enabled            = true
        wave.freeze             = true
        wave.strategy           = 'conda,container'
    }
    emulate_amd64 {
        docker.runOptions       = '-u $(id -u):$(id -g) --platform=linux/amd64'
    }
    singularity {
        singularity.enabled     = true
        singularity.autoMounts  = true
        // Large images (~1+ GB) can exceed the default 20-minute pull timeout.
        singularity.pullTimeout = '3 h'
        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
    }
    wave {
        apptainer.ociAutoPull   = true
        singularity.ociAutoPull = true
        wave.enabled            = true
        wave.freeze             = true
        wave.strategy           = 'conda,container'
    }
    gpu {
        docker.runOptions       = '-u $(id -u):$(id -g) --gpus all'
        apptainer.runOptions    = '--nv'
        singularity.runOptions  = '--nv'
    }
    // EBI Codon SLURM cluster profile (includeConfig conf/codon_slurm.config)
    codon_slurm {
        includeConfig 'conf/codon_slurm.config'
    }
    test { includeConfig 'conf/tests/test.config' }
}

// Load nf-core custom profiles from different institutions
// If params.custom_config_base is set AND either the NXF_OFFLINE environment variable is not set or params.custom_config_base is a local path, the nfcore_custom.config file from the specified base path is included.
includeConfig params.custom_config_base && (!System.getenv('NXF_OFFLINE') || !params.custom_config_base.startsWith('http')) ? "${params.custom_config_base}/nfcore_custom.config" : "/dev/null"

// Set default registry for Apptainer, Docker, Podman, Charliecloud and Singularity independent of -profile
// Will not be used unless Apptainer / Docker / Podman / Charliecloud / 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'
charliecloud.registry = 'quay.io'

// Export these variables to prevent local Python/R libraries from conflicting with those in the container
env {
    PYTHONNOUSERSITE = 1
    R_PROFILE_USER   = "/.Rprofile"
    R_ENVIRON_USER   = "/.Renviron"
}

// Set bash options
process.shell = [
    "bash",
    "-C",         // No clobber - prevent output redirection from overwriting files.
    "-e",         // Exit if a tool returns a non-zero status/exit code
    "-u",         // Treat unset variables and parameters as an error
    "-o",         // Enable the pipefail option for bash
    "pipefail"    // Returns the status of the last command to exit with a non-zero status, or zero if all commands succeed
]

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

timeline {
    enabled = true
    file    = "${params.outdir}/pipeline_info/execution_timeline_${params.trace_report_suffix}.html"
}
report {
    enabled = true
    file    = "${params.outdir}/pipeline_info/execution_report_${params.trace_report_suffix}.html"
}
trace {
    enabled = true
    file    = "${params.outdir}/pipeline_info/execution_trace_${params.trace_report_suffix}.txt"
}
dag {
    enabled = true
    file    = "${params.outdir}/pipeline_info/pipeline_dag_${params.trace_report_suffix}.html"
}

manifest {
    name            = 'bigbio/spectrafuse'
    homePage        = 'https://github.com/bigbio/spectrafuse'
    description     = """Incremental spectral clustering pipeline from quantms data"""
    mainScript      = 'main.nf'
    defaultBranch   = 'master'
    nextflowVersion = '!>=23.04.0'
    version         = '0.1.0'
}