aws_maca_small_skip_umitools_skip_star.conf

/*
 * -------------------------------------------------
 *  Nextflow config file for running tests
 * -------------------------------------------------
 * Defines bundled input files and everything required
 * to run a fast and simple test. Use as follows:
 *   nextflow run nf-core/sicilian -profile test,<docker/singularity>
 */

params {
  config_profile_name = 'Test profile'
  config_profile_description = 'Minimal test dataset to check pipeline function'

  // max_cpus = 2
  // max_memory = 14.GB
  // max_time = 48.h
  // outdir = 's3://salzman-lab/nf-sicilian-outputs/aws-maca-small-chr19'
  // Input data
  // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
  // TODO nf-core: Give any required params for the test so that command line flags are not needed
  single_end = true
  input = false
  skip_umitools = true
  input_paths = [
    ['MACA_24m_M_BLADDER_58', [
      // It's weird that it's only one read and it says R2, but for 10x/droplet-based single cell, R1 is the 
      // barcode read and R2 is the "interesting" read that will actually align to the genome
      'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/testdata/MACA_24m_M_BLADDER_58.Aligned.out.sorted.chr19.bam', 
      ]],
    ['MACA_24m_M_BLADDER_59', [
      'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/testdata/MACA_24m_M_BLADDER_59.Aligned.out.sorted.chr19.bam', 
      ]],
  ]
  star_index = 's3://salzman-lab/nf-sicilian-outputs/aws-maca-small-chr19/genome/index/star/'
  fasta = 'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/reference/mm10_chrom19.fa'
  gtf = 'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/reference/GCF_000001635.26_GRCm38.p6_genomic.chr19.gtf.gz'
  domain = 's3://salzman-lab/hg38_ref_files/domain_file.txt'
  save_reference = true
  stranded = true
  tenx = true
  annotator = 'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/reference/sicilian/GCF_000001635_gene_names.pkl'
  exon_bounds = 'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/reference/sicilian/GCF_000001635_exon_bounds.pkl'
  splices = 'https://github.com/czbiohub/test-datasets/raw/olgabot/sicilian/reference/sicilian/GCF_000001635_gene_names.pkl'
  // Ignore `--input` as otherwise the parameter validation will throw an error
  schema_ignore_params = 'genomes,input_paths,input'

  // AWS params
  // job_queue = "TowerForge-32pmXwKfAgvOyBacurFhwX"
}


process {
  // executor = 'awsbatch'
  // queue = 'default-971039e0-830c-11e9-9e0b-02c5b84a8036'
  // errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' }

  withLabel:process_high {
     process.executor = 'awsbatch'
    //  executor = 'awsbatch'
     process.queue = 'default-971039e0-830c-11e9-9e0b-02c5b84a8036'
     workDir = "s3://czb-nextflow/intermediates/"
     bucketDir = "s3://czb-nextflow/intermediates/"
     aws.region = 'us-west-2'
     aws.batch.cliPath = '/home/ec2-user/miniconda/bin/aws'
  }
}

bucketDir = "s3://czb-nextflow/intermediates/"

aws {
    region = 'us-west-2'
    batch {
      cliPath = '/home/ec2-user/miniconda/bin/aws'
    }
}