nextflow.config

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

// Global default params, used in configs
params {

    // specifies the analysis to run
    workflow                   = null

    outdir                     = null

    // inputs
    input                       = null
    data_path                   = null
    mgi                         = false
    
    // required for demux
    rundir                      = null
    demuxdir                    = "${params.outdir}/demux_fastq"
    tracedir                    = "${params.outdir}/pipeline_info"

    user_group                  = "compute-dspencer"
    queue                       = "dspencer"
    job_group_name              = "/dspencer/nextflow"
    dragen_container            = "apldx/oracle8-dragen-4.3.6"

    // References
    fasta                      = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/sequence/hg38_mgi_patch.fa"
    fasta_index                = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/sequence/hg38_mgi_patch.fa.fai"

    // Optional inputs
    udiumi                     = false
    solid_tumor                = false
    mark_duplicates            = true
    alignment_file_format      = 'CRAM'
    targeted_sequencing        = false
    downsample_rna             = false
    dux4caller                 = false
    target_bed_file            = null
    hotspot_vcf                = null
    hotspot_vcf_index          = null
    readfamilysize             = 3
    dragen_args                = null
    nirvana                    = false
    dragendir                  = null

    // VEP annotation cache
    vepcache                   = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/VEP_cache"

    // Dragen inputs

    dragen_inputs {
        reference                   = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/dragen_hg38v4.3.6"
        methylation_reference       = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/dragen_hg38_5mCv4.3.6"
        annotation_file             = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/ensemble/Homo_sapiens.GRCh38.105.chr.sorted.gtf.gz"
        transcript_table            = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/ensemble/Homo_sapiens.GRCh38.105.transcript_table.txt"
        snv_noisefile               = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/dragenfiles/IDPF_WGS_hg38_v.2.0.0_systematic_noise.snv.bed.gz"
        sv_noisefile                = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/dragenfiles/IDPF_WGS_hg38_v3.0.0_systematic_noise.sv.bedpe.gz"
        nirvana                     = "/storage1/fs1/dspencer/Active/spencerlab/refdata/hg38/dragen_align_inputs/hg38/nirvana_annotation_data_323"
        dbsnp                       = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/dragen_align_inputs/hg38/dbsnp.vcf.gz"
        dbsnp_index                 = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/dragen_align_inputs/hg38/dbsnp.vcf.gz.tbi"
        pop_af_vcf                  = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/dragen_align_inputs/hg38/1000G_phase1.snps.high_confidence.hg38.vcf.gz"
        pop_af_vcf_index            = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/dragen_align_inputs/hg38/1000G_phase1.snps.high_confidence.hg38.vcf.gz.tbi"
        dragen_adapter1             = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/dragen_align_inputs/hg38/dragen_adapter1.fa"
        dragen_adapter2             = "/storage1/fs1/dspencer/Active/clinseq/projects/chromoseq/refdata/dragen_align_inputs/hg38/dragen_adapter2.fa"
        input_cram_reference        = "${params.fasta}"
        input_cram_reference_index  = "${params.fasta_index}"        
    }

    dragen_exe_path            = "/opt/dragen/4.3.6/bin"

    // For AWS hybrid execution
    aws_dragen_container        = "ghcr.io/dhslab/docker-dragen:el8.4.3.6"

    // TODO nf-core: Specify your pipeline's command line flags
    // Input options
    // References
    genome                     = null
    igenomes_base              = 's3://ngi-igenomes/igenomes'
    igenomes_ignore            = true
    
    // 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
    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

}

plugins {
    id 'nf-amazon'
    id 'nf-validation' // Validation of pipeline parameters and creation of an input channel from a sample sheet
}

//fusion {
//    enabled = true
//}
//
//wave {
//    enabled = true
//}

aws {
    region                        = 'us-east-1'
    batch {
        cliPath                   = '/home/ec2-user/miniconda/bin/aws'
        volumes                   = ['/staging','/dev/shm:/dev/shm']
    }
    accessKey                     = secrets.AWS_ACCESS_KEY
    secretKey                     = secrets.AWS_SECRET_KEY
}

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

profiles {
    test { includeConfig 'conf/test.config' } // this run demux on first tile only
    stub { includeConfig 'conf/stub.config' } // local executor for testing
    
    ris {
        executor.queueSize        = 20
        executor.submitRateLimit  = '1/1sec'
        process {
            executor                  = "lsf"
            clusterOptions            =   { "-a 'docker(${task.container})' -q ${params.queue} -G ${params.user_group} -g ${params.job_group_name}" }
        }
    }
    
    dragen2 {
        process {
            withLabel: 'dragen' {
                queue = { "dragen-2" }
                memory  = 200.GB
                cpus = 20
                time = 16.h
                clusterOptions = { "-a 'gtac-mgi-dragen(${params.dragen_container})' -m compute1-dragen-2 -G ${params.user_group} -g ${params.job_group_name} -env 'all, LSF_DOCKER_DRAGEN=y'" }
                ext.intermediate_dir = '/staging/intermediate-results-dir'
                ext.dragen_exe_path  = "${params.dragen_exe_path}"

            }
        }
    }

    dragen4 {
        process {
            withLabel: 'dragen' {
                queue = { "dragen-4" }
                memory  = 300.GB
                cpus = 30
                time = 16.h                
                clusterOptions = { "-a 'gtac-mgi-dragen(${params.dragen_container})' -m compute1-dragen-4 -G ${params.user_group} -g ${params.job_group_name} -env 'all, LSF_DOCKER_DRAGEN=y'" }
                ext.intermediate_dir = '/staging/intermediate-results-dir'
                ext.dragen_exe_path  = "${params.dragen_exe_path}"
            }
        }
    }

    aws {
        process {
            executor             = 'awsbatch'
            queue                = 'nextflow-aws-queue'
        }
    }

    dragenaws {
        process {
            withLabel: dragenalign {
                executor                = 'awsbatch'
                ext.dragen_aws_image    = "${params.aws_dragen_container}"
                ext.dragen_license_args = "--lic-server 'https://${secrets.AWS_DRAGEN_USER}:${secrets.AWS_DRAGEN_PASSWORD}@license.edicogenome.com'"
                queue                   = 'nextflow-dragen-oracle8'
                containerOptions        = '--privileged --ulimit nofile=65535:65535 --ulimit nproc=16384:16384'
                maxErrors               = 1
                cpus                    = 16
                memory                  = 230.GB
                time                    = 24.h
                ext.intermediate_dir    = '/staging/intermediate-results-dir'
                ext.dragen_exe_path     = "/opt/edico/bin"
            }
        }
    }

    dragenawsl {
        process {
            withLabel: dragenalign {
                executor                = 'awsbatch'
                ext.dragen_aws_image    = "${params.aws_dragen_container}"
                ext.dragen_license_args = "--lic-server 'https://${secrets.AWS_DRAGEN_USER}:${secrets.AWS_DRAGEN_PASSWORD}@license.edicogenome.com'"
                queue                   = 'nextflow-dragen-oracle8-large'
                containerOptions        = '--privileged --ulimit nofile=65535:65535 --ulimit nproc=16384:16384'
                maxErrors               = 1
                cpus                    = 60
                memory                  = 968.GB
                time                    = 24.h
                ext.intermediate_dir    = '/staging/intermediate-results-dir'
                ext.dragen_exe_path     = "/opt/edico/bin"
            }
        }
    }
}

// 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'

// 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"
}

// Capture exit codes from upstream processes when piping
process.shell = ['/bin/bash', '-euo', 'pipefail']

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            = 'nf-core/dragenflow'
    author          = """Nidhi"""
    homePage        = 'https://github.com/nf-core/dragenflow'
    description     = """Run multple dragen workflows (5mc,rna,tumor_normal)"""
    mainScript      = 'main.nf'
    nextflowVersion = '!>=23.04.0'
    version         = '1.0dev'
    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
        }
    }
}