nextflow.config

/*
 * -------------------------------------------------
 *  nf-core/rnaseq Nextflow config file
 * -------------------------------------------------
 * Default config options for all environments.
 */

// Global default params, used in configs
params {

  // Pipeline Options
  // Workflow flags
  genome = false
  reads = "data/*.fastq.gz"
  singleEnd = false

  // References
  genome = false
  salmon_index = false
  transcript_fasta = false
  splicesites = false
  saveReference = false
  gencode = false
  compressedReference = false

  // Strandedness
  forwardStranded = false
  reverseStranded = false
  unStranded = false

  // Trimming
  skipTrimming = false
  clip_r1 = 0
  clip_r2 = 0
  three_prime_clip_r1 = 0
  three_prime_clip_r2 = 0
  trim_nextseq = 0
  pico = false
  saveTrimmed = false

  // Ribosomal RNA removal
  removeRiboRNA = false
  save_nonrRNA_reads = false
  rRNA_database_manifest = false

  // Alignment
  aligner = 'star'
  pseudo_aligner = false
  stringTieIgnoreGTF = false
  seq_center = false
  saveAlignedIntermediates = false
  skipAlignment = false
  saveUnaligned = false

  // Read Counting
  fc_extra_attributes = 'gene_name'
  fc_group_features = 'gene_id'
  fc_count_type = 'exon'
  fc_group_features_type = 'gene_biotype'
  sampleLevel = false
  // See https://bit.ly/3p8fhiN for setting below error with GRCh38
  skipBiotypeQC = true

  // QC
  skipQC = false
  skipFastQC = false
  skipPreseq = false
  skipDupRadar = false
  skipQualimap = false
  skipRseQC = false
  skipEdgeR = false
  skipMultiQC = false

  // Defaults
  project = false
  markdup_java_options = '"-Xms4000m -Xmx7g"' //Established values for markDuplicate memory consumption, see issue PR #689 (in Sarek) for details
  hisat_build_memory = 200 // Required amount of memory in GB to build HISAT2 index with splice sites
  readPaths = null
  star_memory = false // Cluster specific param required for hebbe
  rRNA_database_manifest = "$baseDir/assets/rrna-db-defaults.txt"

  // Boilerplate options
  clusterOptions = false
  outdir = './results'
  name = false
  multiqc_config = "$baseDir/assets/multiqc_config.yaml"
  email = false
  email_on_fail = false
  max_multiqc_email_size = 25.MB
  plaintext_email = false
  monochrome_logs = false
  help = false
  //igenomes_base = "./iGenomes"
  igenomes_base = '/ceph01/projects/reference-databases'
  tracedir = "${params.outdir}/pipeline_info"
  awsqueue = false
  awsregion = 'eu-west-1'
  igenomesIgnore = false
  custom_config_version = 'master'
  custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
  hostnames = false
  config_profile_description = false
  config_profile_contact = false
  config_profile_url = false
}

// Container slug. Stable releases should specify release tag!
// Developmental code should specify :dev
process.container = 'nfcore/rnaseq:1.4.2'

// 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")
}

profiles {
  awsbatch { includeConfig 'conf/awsbatch.config' }
  conda { process.conda = "$baseDir/environment.yml" }
  debug { process.beforeScript = 'echo $HOSTNAME' }
  docker { docker.enabled = true }
  singularity { singularity.enabled = true
                singularity.autoMounts = true }
  test { includeConfig 'conf/test.config' }
  cuba { includeConfig 'conf/cuba.config' }
  test_gz { includeConfig 'conf/test_gz.config' }
  cluster { includeConfig 'conf/cluster.config' }
}

// Avoid this error:
// WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
// Testing this in nf-core after discussion here https://github.com/nf-core/tools/pull/351, once this is established and works well, nextflow might implement this behavior as new default.
docker.runOptions = '-u \$(id -u):\$(id -g)'

// Load igenomes.config if required
if (!params.igenomesIgnore) {
  includeConfig 'conf/igenomes.config'
}

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

timeline {
  enabled = true
  file = "${params.tracedir}/execution_timeline.html"
}
report {
  enabled = true
  file = "${params.tracedir}/execution_report.html"
}
trace {
  enabled = true
  file = "${params.tracedir}/execution_trace.txt"
}
dag {
  enabled = true
  file = "${params.tracedir}/pipeline_dag.svg"
}

manifest {
  name = 'nf-core/rnaseq'
  author = 'Phil Ewels, Rickard Hammarén'
  homePage = 'https://github.com/nf-core/rnaseq'
  description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.'
  mainScript = 'main.nf'
  nextflowVersion = '>=19.04.0'
  version = '1.4.2'
}

// 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
    }
  }
}