nextflow.config

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

/* -----------------------------
   additions to nf-core config
   --------------------------- 
*/

// enable dsl2 syntax
nextflow.enable.dsl = 2

// nf-core enabling code
manifest {
    name            = 'somatem'
    description     = 'A best practices pipeline for long-read metagenomic analysis'
    version         = '1.0.0'
    nextflowVersion = '>=25.10.2'
    homePage        = 'https://github.com/treangenlab/somatem'
    mainScript      = 'workflows/main.nf'
}

plugins {
    id 'nf-schema@2.7.2'  // latest version, 15/May/26
}

// NOTE: Default Settings: will be overridden by profiles ----------------


// ---------------------------------
// default nf-core config follows
// ---------------------------------


// Global default params, used in configs
params {

    // TODO nf-core: Specify your pipeline's command line flags
    // Input options -----------------------------------------------------
    input                      = "${projectDir}/assets/samplesheet.csv" // bundled default file should resolve from the installed pipeline root
    db_base_dir = System.getenv('SOMATEM_DB_DIR') ?: "${System.getenv('HOME')}/somatem_databases"
    unified_db_base_dir        = System.getenv('SOMATEM_UNIFIED_DB_DIR') ?: "${params.db_base_dir}/unified/refseq03032025"

    // metadata defaults ---------------------------------------------------
    // Actual values read in from metadata_template.yaml or .._params.yml override these) 

    data_type                  = "metagenomic" // options: 16S, isolate, metagenomic
    analysis_type              = "taxonomic-profiling" // taxonomic-profiling, assembly, isolate-analysis, genome-dynamics, pathogen-detection
    sample_status              = "cross-section" // longitudinal
    sequencing_technology      = "nanopore" // nanopore, pacbio

    // References --------------------------------------------------------
    genome                     = null
    igenomes_base              = 's3://ngi-igenomes/igenomes/'
    igenomes_ignore            = true
    
    // Quality filtering -------------------------------------------------
    maxlength                  = 30000
    minlen                     = 250
    minq                       = 10
    contam_ref                 = null // path to reference .fa file of contaminants to remove, chopper (not used currently: somatem.nf)

    // Host sequence removal (hostile) -----------------------------------
    hostile_index              = 'human-t2t-hla-argos985-mycob140.mmi' // remove host reads: masked index (https://github.com/bede/hostile?tab=readme-ov-file#indexes)
    hostile_db                 = "${params.db_base_dir}/hostile"
    // whether hostile is run or not is computed below in `run_hostile` param


    // taxonomic profiling ----------------------------------------------------------
    // EMU defaults
    emu_db                     = "${params.db_base_dir}/emu_db/emu_db_mar2026/"
    sample_size                = null
    seqtype                    = params.sequencing_technology == "nanopore" ? "map-ont" : "map-pb"
    min_abundance              = 0.0001
    minimap_max_alignments     = 50
    minibatch_size             = 500000000
    keep_read_assignments      = true // gms_16S: changes from default
    keep_files                 = false 
    output_unclassified        = true // gms_16S: changes from default

    // LEMUR-MAGNET
    lemur_db                   = "${params.db_base_dir}/lemur_221_db/"
    lemur_db_zenodo_id         = 10802546
    lemur_taxonomy             = "${params.lemur_db}/taxonomy.tsv"
    rank                       = "species"

    // Ensemble species detection (unified DBs for Ganon, Kraken2 and Sylph)
    ganon_db                   = "${params.unified_db_base_dir}/ganon2_abvf_030325/" // Ganon2 database
    kraken2_db                 = "${params.unified_db_base_dir}/k2_abfv_030325/" // Kraken2 database
    kraken2_save_output_fastqs = false
    kraken2_save_reads_assignment = true
    sylph_db                   = "${params.unified_db_base_dir}/sylph_abf_030325/database.syldb" // Sylph database
    
    // Sylph : Standalone DBs for different taxonomic groups
    sylph_prok_db_file = "${params.db_base_dir}/gtdb-r220-c200-dbv1.syldb" // placeholder ; will use a dir/ when auto-downloading
    // TODO: need to make a conditional in the sylph calling subworkflow to use the proper variable for Prok?/ Viral/ Fungal DBs

    // TODO: will be downloaded with automatic scripts soon
    sylph_prok_db              = "${params.db_base_dir}/sylph_prok_db/"
    sylph_vir_db               = "${params.db_base_dir}/sylph_vir_db/"

    // MAG/assembly Workflow ----------------------------------------------------------
    // checkm2
    checkm2_db                 = "${params.db_base_dir}/checkm2_db/"
    checkm2_db_zenodo_id       = 14897628
    checkm2_completeness_threshold = 80

    // bakta
    bakta_db                   = "${params.db_base_dir}/bakta_db/" 

    // singlem
    singlem_db                 = "${params.db_base_dir}/singlem_db/"

    // flye
    flye_mode                  = "nano-hq" //sequencing data type for Flye // take from params.sequencing_technology later

    // isolate/hybrid assembly workflow -------------------------------------------
    assembler                  = "autocycler"
    hybrid_assembly            = false
    autocycler_subsamples      = 4
    autocycler_min_read_depth  = 25
    autocycler_seed            = 0
    autocycler_subsample_depth = null
    autocycler_genome_size     = null
    autocycler_assemblers      = "flye"
    autocycler_flye_mode       = params.flye_mode
    autocycler_flye_args       = ''
    run_polypolish            = true
    polypolish_args           = ''
    polypolish_filter_args    = ''
    run_pypolca               = true
    pypolca_args              = '--careful'
    shortread_mapper          = 'bwa'
    min_shortread_depth_for_pypolca = 25
    run_btyper3              = false
    btyper3_args              = ''

    // semibin
    sample_environment        = "human_gut" // sample environment for SemiBin2's built-in model
      // options: human_gut/dog_gut/ocean/soil/cat_gut/human_oral/mouse_gut/pig_gut/built_environment/wastewater/chicken_caecum/global
    semibin2_random_seed      = 42 // random seed for SemiBin2 reproducibility (keep same across runs ; chose default of 42 on a whim)

    // optional iterative MAG binning
    mag_iterative_binning_enabled = true
    mag_binning_iterations = 5
    mag_iterative_consensus_tool = "dastool"
    mag_iterative_seed_step = 1
    pigeon_selection_score_mode = "pigeon_loss"
    pigeon_selection_min_delta_score = 0.005
    pigeon_selection_patience = 2
    pigeon_residual_rebinning = false
    pigeon_residual_ksize = 21
    pigeon_residual_min_unexplained_fraction = 0.50
    pigeon_residual_min_contig_len = 1500
    pigeon_residual_min_contigs = 10
    metabat2_seed = 42
    vamb_seed = 42
    vamb_minfasta = 200000
    dastool_search_engine = "diamond"

    // Pigeon parameters (unitigs, contigs, bins comparison)
    pigeon_ksize = 17
    pigeon_scaled = 1000
    pigeon_seed = 42
    pigeon_top_bins = 20
    pigeon_reads_subsample = 0
    pigeon_skip_db = false
    
    // Other tools
    seqscreen_db = "${params.db_base_dir}/SeqScreenDB_23.4/"
    seqscreen_mode = "fast"

    // Computed parameters ----------------------------------------------
    // these will be evaluated when config is loaded
    
    // Host sequence removal (hostile) -----------------------------
    // Conditional HOSTILE_FETCH and _CLEAN based on data_type and sample_environment
    run_hostile = params.sample_environment =~ /human/ && params.data_type != "16S"

    // TODO: future update: enable hostile db change between human default and mouse based on params.sample_environment
    // Then change the matcher to =~ /human|mouse/ to pick up both!
    // hostile_index = params.sample_environment == "human" ? "human_genome_index" : "mouse_genome_index"


    // Boilerplate options -----------------------------------------------
    max_cpus                     = null // auto-detected by conf/base.config when null
    max_memory_gb                = null // auto-detected by conf/base.config when null
    local_memory_reserve_gb      = 4    // RAM kept free for the OS during local runs
    outdir                       = "results/" // need to turn on publishDir in modules.config
    outputDir                    = params.outdir // alias for outdir, used in workflow outputs (future-proof, nf-core style)
    output_dir                   = params.outdir // alias for outdir, used in process level publish (Austin)
    publish_dir_mode             = 'copy'
    monochrome_logs              = false
    version                      = false
    pipelines_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/'
    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_contact     = null
    config_profile_url         = null

    validate_params            = true
}

// Shared cache defaults for all conda/micromamba-enabled runs. Profiles still
// decide whether conda is enabled; this only controls where environments live.
conda {
    cacheDir = System.getenv('NXF_CONDA_CACHEDIR') ?: "${env('HOME')}/.nextflow/conda" // change from default `work/conda/
    channels = ['conda-forge', 'bioconda']
    createTimeout = 2.h
}

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

// -------------------------
// Profiles
// -------------------------

profiles {
    standard { // default profile for local execution using micromamba
        conda {
            enabled = true
            useMicromamba = true
            channels = ['conda-forge', 'bioconda'] // channel precedence is important!
            createTimeout = 2.h
        }
    }
    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
        conda.channels          = ['conda-forge', 'bioconda']
        conda.createTimeout     = 2.h
        apptainer.enabled       = false
    }
    mamba {
        conda.enabled           = true
        conda.useMamba          = true
        conda.createTimeout     = 2.h
        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
    }
    wave {
        apptainer.ociAutoPull   = true
        singularity.ociAutoPull = true
        wave.enabled            = true
        wave.freeze             = true // Generates lock files automatically
        wave.strategy           = 'conda,container'
        // needs a tower.accessToken to use this without servece rate limits
        // https://www.nextflow.io/docs/latest/wave.html#wave-page
    }
    gpu {
        docker.runOptions       = '-u $(id -u):$(id -g) --gpus all'
        apptainer.runOptions    = '--nv'
        singularity.runOptions  = '--nv'
    }
    test      { includeConfig 'conf/test.config' }      
    test_full { includeConfig 'conf/test_full.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.
// Load nf-core/somatem custom profiles from different institutions.
includeConfig params.custom_config_base && (!System.getenv('NXF_OFFLINE') || !params.custom_config_base.startsWith('http')) ? "${params.custom_config_base}/nfcore_custom.config" : "/dev/null"


// Load nf-core/somatem custom profiles from different institutions.
// TODO nf-core: Optionally, you can add a pipeline-specific nf-core config at https://github.com/nf-core/configs
// includeConfig params.custom_config_base && (!System.getenv('NXF_OFFLINE') || !params.custom_config_base.startsWith('http')) ? "${params.custom_config_base}/pipeline/somatem.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'

// Load igenomes.config if required
includeConfig !params.igenomes_ignore ? 'conf/igenomes.config' : 'conf/igenomes_ignored.config'

// 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"
}

// 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
]

// nf-schema validation block
validation {
    defaultIgnoreParams = ["genomes"]
    monochromeLogs = params.monochrome_logs
}

// 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            = 'nf-core/somatem'
    contributors    = [
        // TODO nf-core: Update the field with the details of the contributors to your pipeline. New with Nextflow version 24.10.0
        [
            name: 'Prashant Kalvapalle',
            affiliation: 'Rice University',
            email: '',
            github: 'ppreshant',
            contribution: [], // List of contribution types ('author', 'maintainer' or 'contributor')
            orcid: ''
        ],
        [
            name: ' Austin Marshall',
            affiliation: 'Rice University',
            email: '',
            github: 'microbemarsh',
            contribution: [], // List of contribution types ('author', 'maintainer' or 'contributor')
            orcid: ''
        ],
    ]
    homePage        = 'https://github.com/nf-core/somatem'
    description     = """A long-read metagenomics pipeline with support for longitudinal analysis """
    mainScript      = 'main.nf'
    defaultBranch   = 'master'
    nextflowVersion = '>=25.10.2'
    version         = '1.0.0dev'
    doi             = ''
}



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