nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    BioimageAnalysisCoreWEHI/prepare_celltune_features Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {

    // Input options
    geojson_dir                  = null
    pixel_size                   = null
    celltune_cell_table          = null

    // Arcsinh normalization options
    cofactor                     = 100
    skip_arcsinh                 = false

    // Mask renaming options
    mask_suffix                  = '_mask.tiff'

    // Boilerplate options
    output                       = 'celltune_features.parquet'
    outdir                       = null
    publish_dir_mode             = 'copy'
    monochrome_logs              = false
    help                         = false
    version                      = false

    // Schema validation default options
    validate_params              = true
}

profiles {
    debug {
        dumpHashes              = true
        process.beforeScript    = 'echo $HOSTNAME'
        cleanup                 = false
        nextflow.enable.configProcessNamesValidation = true
    }
    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
        docker.runOptions       = '-u $(id -u):$(id -g)'
    }
    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
    }
    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
    }

    // For images 150GB and below — targets sml nodes (28 cores, 113GB)
    small {
        process {
            executor = 'slurm'
            queue = 'regular'

            withLabel: 'process_low' {
                cpus   = { 1 }
                memory = { 4.GB * task.attempt }
                time   = { 2.h }
            }
            withLabel: 'process_medium' {
                cpus   = { 1 }
                memory = { 24.GB * task.attempt }
                time   = { 48.h }
            }
            withLabel: 'process_heavy' {
                cpus   = { 1 }
                memory = { 36.GB * task.attempt }
                time   = { 48.h }
            }
        }
        executor {
            queueSize = 50
            submitRateLimit = '10 sec'
        }
    }
    // For images 300GB and below — targets med nodes (28 cores, 491GB) / il nodes (48 cores, 491GB)
    medium {
        process {
            executor = 'slurm'
            queue = 'regular'

            withLabel: 'process_low' {
                cpus   = { 1 }
                memory = { 4.GB * task.attempt }
                time   = { 2.h }
            }
            withLabel: 'process_medium' {
                cpus   = { 1 }
                memory = { 48.GB * task.attempt }
                time   = { 48.h }
            }
            withLabel: 'process_heavy' {
                cpus   = { 1 }
                memory = { 120.GB * task.attempt }     // med/il: 491GB (120*2=240GB)
                time   = { 48.h }
            }
        }
        executor {
            queueSize = 50
            submitRateLimit = '10 sec'
        }
    }
    // For images 600GB and below — targets lrg nodes (64 cores, 1498GB)
    large {
        process {
            executor = 'slurm'
            queue = 'regular'

            withLabel: 'process_low' {
                cpus   = { 1 }
                memory = { 8.GB * task.attempt }
                time   = { 2.h }
            }
            withLabel: 'process_medium' {
                cpus   = { 1 }
                memory = { 192.GB * task.attempt }
                time   = { 48.h }
            }
            withLabel: 'process_heavy' {
                cpus   = { 1 }
                memory = { 450.GB * task.attempt }     // lrg: 1498GB (450*2=900GB)
                time   = { 48.h }
            }
        }
        executor {
            queueSize = 50
            submitRateLimit = '10 sec'
        }
    }
}

// Export these variables to prevent local Python libraries from conflicting with those in the container
env {
    PYTHONNOUSERSITE = 1
}

// 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",         // Returns the status of the last command to exit..
    "pipefail"    //   ..with a non-zero status or zero if all successfully execute
]

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

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"
}

manifest {
    name            = 'BioimageAnalysisCoreWEHI/prepare_celltune_features'
    author          = """WEHI SODA Hub"""
    homePage        = 'https://github.com/BioimageAnalysisCoreWEHI/prepare_celltune_features'
    description     = """Extract cell measurements from QuPath geojson.gz files and format for CellTune import"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=24.04.2'
    version         = '0.1.0'
}

// Nextflow plugins
plugins {
    id 'nf-schema@2.1.1' // Validation of pipeline parameters and creation of an input channel from a sample sheet
}