nextflow.config

/*
 * Configuration File to run fmalmeida/mpgap pipeline.
 */

/*
 * Pipeline parameters
 */
params {

                  /* 
                   * Input parameter
                   */


// Path to YAML samplesheet file.
// Please read the documentation https://mpgap.readthedocs.io/en/latest/samplesheet.html to know how to create a samplesheet file.
      input = ""

                  /*
                   * Output parameters
                   */


// Output folder name
      output = "output"


                  /*
                   * Resources parameters
                   */
                

// Number of threads to be used by each software.
      threads = 3

// Number of jobs to run in parallel. Be aware that each job (in parallel) can consume
// N threads (set above). Be sure to carefully check your resources before augmenting
// this parameter. For example: parallel_jobs = 2 + threads = 5 can consume until 10
// threads at once.
// If not given, let's nextflow automatically handle it.
      parallel_jobs = 

// Memory allocation for pilon polish.
// Values in Gb. Default 50G. 50G has been proved to be enough in most cases.
// This step is crucial because with not enough memory will crash and not correct your assembly.
      pilon_memory_limit = 50

                  /*
                   * General parameters
                   *
                   * These parameters will set the default for all samples.
                   * However, they can also be set inside the YAML, if this happens 
                   * the pipeline will use the value inside the YAML to overwrite 
                   * the parameter for that specific sample.
                   * 
                   * Please read the documentation https://mpgap.readthedocs.io/en/latest/samplesheet.html to know more about the samplesheet file.
                   */


// This parameter only needs to be set if the software chosen is Canu, wtdbg2 or Haslr. Is optional for Flye.
// It is an estimate of the size of the genome. Common suffices are allowed, for example, 3.7m or 2.8g
      genome_size = ""

// Select the appropriate value to pass to wtdbg2 to assemble input.
// Options are: "ont" for Nanopore reads, "rs" for PacBio RSII, "sq" for PacBio Sequel, "ccs" for PacBio CCS reads.
// By default, if not given, the pipeline will use the value "ont" if nanopore reads are used and "sq" if pacbio reads are used
      wtdbg2_technology = ""

// Select the appropriate shasta config to use for assembly
// Since shasta v0.8 (Oct/2021) this parameter is now mandatory.
      shasta_config = "Nanopore-Oct2021"

// Tells the pipeline to interpret the long reads as "corrected" long reads.
// This will activate (if available) the options for corrected reads in the
// assemblers: -corrected (in canu), --pacbio-corr|--nano-corr (in flye), etc.
// Be cautious when using this parameter. If your reads are not corrected, and
// you use this parameter, you will probably do not generate any contig.
      corrected_long_reads = false

// This parameter below (hybrid_strategy) is to select the hybrid strategies adopted by the pipeline.
// Read the documentation https://mpgap.readthedocs.io/en/latest/manual.html to know more about the hybrid strategies.
//
// Whenever using this parameter, it is also possible to polish the longreads-only assemblies with Nanopolish,
// Medaka or VarianCaller (Arrow) before the polishing with shortreads (using Pilon). For that it is necessary to set
// the right parameters: pacbio_bam and nanopolish_fast5 (files given only inside YAML) or medaka_model.
      hybrid_strategy = 1

// Default medaka model used for polishing nanopore long reads assemblies.
// Please read their manual https://github.com/nanoporetech/medaka to know more about the available models.
      medaka_model = "r941_min_high_g360"

// This parameter sets to nanopolish the max number of haplotypes to be considered.
// Sometimes the pipeline may crash because to much variation was found exceeding the limit
      nanopolish_max_haplotypes = 1000


                /*
                 * Advanced parameters
                 * 
                 * Controlling the execution of assemblers
                 * It must be set as true to skip the software and false to use it.
                 * Also adding the possibility to pass additional parameters to them
                 * Additional parameters must be in quotes and separated by spaces.
                 */


      quast_additional_parameters = ""            // Give additional parameters to Quast while assessing assembly metrics.
                                                  // Must be given as shown in Quast manual. E.g. " --large --eukaryote ".

      skip_spades    = false                      // Hybrid and shortreads only assemblies
      spades_additional_parameters = ""           // Must be given as shown in Spades manual. E.g. " --meta --plasmids "

      skip_shovill   = false                      // Paired shortreads only assemblies
      shovill_additional_parameters = ""          // Must be given as shown in Shovill manual. E.g. " --depth 15 "
                                                  // The pipeline already executes shovill with spades, skesa and megahit, so please, do not use it with shovill's ``--assembler`` parameter.

      skip_unicycler = false                      // Hybrid and shortreads only assemblies
      unicycler_additional_parameters = ""        // Must be given as shown in Unicycler manual. E.g. " --mode conservative --no_correct "

      skip_haslr     = false                      // Hybrid assemblies
      haslr_additional_parameters = ""            // Must be given as shown in Haslr manual. E.g. " --cov-lr 30 "

      skip_canu      = false                      // Longreads only assemblies
      canu_additional_parameters = ""             // Must be given as shown in Canu manual. E.g. " correctedErrorRate=0.075 corOutCoverage=200 "

      skip_flye      = false                      // Longreads only assemblies
      flye_additional_parameters = ""             // Must be given as shown in Flye manual. E.g. " --meta --iterations 4 "

      skip_raven     = false                      // Longreads only assemblies
      raven_additional_parameters = ""            // Must be given as shown in Raven manual. E.g. " --polishing-rounds 4 "

      skip_wtdbg2    = false                      // Longreads only assemblies
      wtdbg2_additional_parameters = ""           // Must be given as shown in wtdbg2 manual. E.g. " --tidy-reads 5000 "

      skip_shasta    = false                      // Nanopore longreads only assemblies
      shasta_additional_parameters = ""           // Must be given as shown in shasta manual. E.g. " --Reads.minReadLength 5000 "

}


/*
 * Configuring Nextflow reports
 */

// Trace Report
trace {
    enabled = false
    file = "${params.output}" + "/mpgap_trace.txt"
    fields = "task_id,name,status,exit,realtime,cpus,%cpu,memory,%mem,rss"
}

// Timeline Report
timeline {
    enabled = false
    file = "${params.output}" + "/mpgap_timeline.html"
}

// Complete Report
report {
    enabled = true
    file = "${params.output}" + "/mpgap_nextflow_report.html"
}

/*
                                    Setting up NF profiles
                            To use different profiles and executors
            please read more at: https://www.nextflow.io/docs/latest/config.html#config-profiles
 */
profiles {

  // standard local profile
  // uses docker by default
  standard {
    // using docker as default
    singularity.enabled = false
    docker.enabled      = true
    docker.runOptions   = '-u \$(id -u):\$(id -g)'
    fixOwnership        = true
    process.container   = "fmalmeida/mpgap:v3.1"
    // QueueSize limit
    if (params.parallel_jobs) {
      executor.local.queueSize = params.parallel_jobs
    }
  }

  // local executor
  local {
    // QueueSize limit
    if (params.parallel_jobs) {
      executor.local.queueSize = params.parallel_jobs
    }
  }

  // conda profile
  conda {
    singularity.enabled   = false
    docker.enabled        = false
    process.conda         = "$CONDA_PREFIX/envs/mpgap-3.1"
  }

  // docker profile
  docker      {
    singularity.enabled = false
    docker.enabled      = true
    docker.runOptions   = '-u \$(id -u):\$(id -g)'
    fixOwnership        = true
    process.container   = "fmalmeida/mpgap:v3.1"
  }

  // singularity profile
  singularity {
    docker.enabled         = false
    singularity.enabled    = true
    singularity.autoMounts = true
    process.container      = "docker://fmalmeida/mpgap:v3.1"
    singularity.autoMounts = true
  }

}

/*
                                    Adding manifest
*/
manifest {
  name = "fmalmeida/mpgap"
  author = "Felipe Almeida"
  description = "Nextflow pipeline for de novo genome assembly"
  homePage = "https://github.com/fmalmeida/mpgap"
  mainScript = "main.nf"
  nextflowVersion = ">=20.10.0"
  version = "3.1"
}

// specifying number of threads wanted
process.cpus = params.threads