nextflow.config

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    HPCBio/TADA Nextflow config file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Default config options for all compute environments
----------------------------------------------------------------------------------------
*/

// Global default params, used in configs
params {
    input                      = null
    multiqc_config             = null
    multiqc_title              = null
    multiqc_logo               = null
    max_multiqc_email_size     = '25.MB'
    multiqc_methods_description = null

    // TODO: these aren't used at the moment. With some it's possible 
    // to use the name as a key to preset parameters, and with others
    // run a Figaro-like step in preqc to evaluate reads and determine 
    // potential downstream settings.
    amplicon                   = "16S"
    amplicon_name              = ""
    min_predicted_length       = 0
    max_predicted_length       = 0
    paired_type                = "overlapping" // "full_length", "overlapping", "dovetail", "mix", "nonoverlapping"
    
    // TODO: platform is used in a generally hacky way here, but we 
    // could use this to possibly preset some parameters
    platform                   = "illumina" // "illumina", "pacbio"; ONT, 454, Element, others may be added
    
    // TODO: remove and determine on the fly from the sample sheet
    strategy                   = "paired"  // method for trimming and denoising reads; "single" or "paired"

    // QC
    preqc_only                 = false
    preqc_samples              = 0
    skip_FASTQC                = false
    skip_dadaQC                = false
    skip_MultiQC               = false
    skip_merging_check         = true
    // TODO: This one needs a related graph; for an example see:
    // https://github.com/benjjneb/dada2/issues/236#issuecomment-422865307
    skip_ee_check              = true

    // Trimming
    skip_trimming              = false
    trimmer                    = "dada2"

    // when true (default), this sets cutadapt's trimming 
    // (which uses linked adapters) to require 
    // *both* primers be present.  

    // With some kits like StrainID this can be an issue (can have 
    // some truncated reads at the 5' or 3' end) and so can be relaxed 
    // by setting to false.
    cutadapt_strict_match      = true

    // for paired end data only: set if there is a potential for R1 
    // to sequence into the 5' primer for R2 (e.g., as seen with ITS)
    cutadapt_dovetail          = false

    // required for cutadapt
    for_primer                 = ""
    rev_primer                 = ""

    // general trimming settings
    trim_for                   = 0
    trim_rev                   = 0
    trunc_for                  = 0
    trunc_rev                  = 0

    // read filtering
    // cutadapt only has one setting, takes the max of the two
    maxEE_for                  = 2
    maxEE_rev                  = 2
    truncQ                     = 2
    maxN                       = 0
    min_read_len               = 50
    max_read_len               = 10000
    // a general flag for trimming with Illumina modern two-color sequencing
    illumina_twocolor          = false
    // I think we can make these bool 'false' as above with R coersion (either through as.logical or using optparse in a Rscript)
    rmPhiX                     = false

    // learnErrors options
    // TODO: deprecate quality_binning in favor of models
    // Set to true if using binned qualities (NovaSeq, PacBio Revio)
    quality_binning            = false 
    // NYI
    // this should be checked at the beginning
    learnerrors_function        = "loessErrfun"
    // loessErrfun, PacBioErrfun, makeBinnedQualErrfun, noqualErrfun, custom
    // this should be checked at the beginning if error_function="custom"
    learnerrors_custom_code     = ""
    // this is currently required to be set if makeBinnedQualErrfun is set
    learnerrors_quality_bins    = ""

    // TODO: some of the common ones overlap with dada options, 
    // so we should try finding some way to make this simpler 
    // between the two
    learnerrors_opts            = ""

    /* DADA function options */
    // The prior version allowed for key-val pairings, but 
    // these pairings in Groovy don't always translate well 
    // to R parameters, so we use simple strings for now
    // TODO: needs to be fixed
    dada_opts                   = ""

    // ASV inference pooling
    pool                       = "pseudo"
    for_priors                 = ""
    rev_priors                 = ""

    // Merging
    min_overlap                = 20
    max_mismatch               = 0
    trim_overhang              = false
    just_concatenate           = false
    rescue_unmerged            = false

    // Pre-chimera sequence tables. This pulls in one or more sequence tables
    // from independent sequencing runs, merges them, and runs
    // downstream analysis. The only supported sequence table format
    // is the original version from DADA2 (ASV names are the
    // sequence, with counts per sample). As these are run through
    // chimera detection, these should be pre-chimera removal data.
    // seq_tables = false
    
    // Chimera detection
    skip_chimera_detection     = false
    removeBimeraDenovo_options = ""

    // General ASV filtering
    min_asv_len                = 0 // Only run if set > 1
    max_asv_len                = 0 // Only run if set > 1

    // Search-based filtering 
    // This is still alpha!!!
    search_filter              = "none" // currently only "mmseqs"
    search_filter_dryrun       = true
    mmseqs_method              = "search" // search; profile, taxonomy TBI
    mmseqs_args                = "" 
    mmseqs_fasta               = "" // FASTA sequences to format
    mmseqs_database            = "" // path to database with prefix name
    infernal_model             = "" // NYI
    tax_filter                 = false
    tax_filter_rank            = "Phylum"

    // other options to be added when needed
    // Taxonomic assignment
    // TODO: set flag to skip these explicitly
    // skip_taxonomic_assignment = false
    tax_assignment_method      = 'rdp'
    reference                  = ""
    species                    = ""
    min_boot                   = 50
    tax_ranks                  = ""

    // batch size of ASVs to run through assignTaxonomy/assignSpecies, 0 = run everything
    tax_batch                  = 0  

    // Multiple Sequence Alignment
    skip_alignment             = false
    aligner                    = 'DECIPHER' // default
    // infernalCM  = false

    // Phylogenetic analysis, requires MSA above
    skip_tree                  = false
    phylo_tool                 = 'fasttree' // default, current alternative is 'phangorn'

    // MultiQC

    // additional outputs
    to_BIOM                    = true   // generate BIOM v1 output
    to_QIIME2                  = true   // generate QZA artifacts for QIIME2

    // Renaming
    id_type                    = "md5"  // simple, md5; others may be added

    // other parameters
    random_seed                = 100

    // 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

    // 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            = false
    validationSchemaIgnoreParams     = '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 h3abionet/TADA custom profiles from different institutions.
// Warning: Uncomment only if a pipeline-specific institutional config already exists on nf-core/configs!
// try {
//   includeConfig "${params.custom_config_base}/pipeline/tada.config"
// } catch (Exception e) {
//   System.err.println("WARNING: Could not load nf-core/config/tada profiles: ${params.custom_config_base}/pipeline/tada.config")
// }
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
        channels               = ['conda-forge', 'bioconda', 'defaults']
        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)'
    }
    arm {
        docker.runOptions      = '-u $(id -u):$(id -g) --platform=linux/amd64'
    }
    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
    }
    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
    }
    gitpod {
        executor.name          = 'local'
        executor.cpus          = 4
        executor.memory        = 8.GB
    }
    test         { includeConfig 'conf/test.config'              }
    test_se      { includeConfig 'conf/test_illumina_se.config'  }
    test_pacbio  { includeConfig 'conf/test_pacbio.config'       }
    test_full    { includeConfig 'conf/test_full.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@1.1.3' // Validation of pipeline parameters and creation of an input channel from a sample sheet
}

// 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']

// 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            = 'h3abionet/TADA'
    author          = """Chris Fields"""
    homePage        = 'https://github.com/h3abionet/TADA'
    description     = """Targeted Amplicon Diversity Analysis"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=23.04.0'
    version         = '2.0.0-alpha.1'
    doi             = ''
}

// 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
        }
    }
}