default.yaml

star_exe:  # STAR aligner runnable
  "/home/arendeiro/workspace/STAR-2.7.0e/bin/Linux_x86_64_static/STAR"
star_genome_dir:  # directory with STAR aligner indexes
  "/home/arendeiro/resources/genomes/hg38/indexed_STAR-2.7.0e/"
gtf_file:  # Transcriptomg GTF file
  "/home/arendeiro/resources/genomes/hg38/10X/refdata-cellranger-GRCh38-1.2.0/genes/genes.gtf"
featurecounts_exe:
  "subread-2.0.1-Linux-x86_64/bin/featureCounts"
# star_genome_dir:
#   "/home/arendeiro/resources/genomes/hg38_mm10_transgenes_Tcrlibrary/indexed_STAR_2.7.0e/"
# gtf_file:
#   "/home/arendeiro/resources/genomes/hg38_mm10_transgenes_Tcrlibrary/Homo_sapiens-Mus_musculus.Ensembl92.dna.primary_assembly.Tcr_lambda_spiked.gtf"
root_output_dir:  # default directory for outputs
  /scratch/lab_bock/shared/projects/sci-rna/data/$(RUN_NAME)
expected_cell_number:  # default expected number of cells
  200000
min_umi_output:  # minimum number of UMIs a barcode must have to be reported
  3
annotation:  # round2 CSV annotation. Superceeded by values in sample CSV annotation.
  "/scratch/lab_bock/shared/projects/sci-rna/metadata/sciRNA-seq.PD190_humanmouse.oligos_2019-09-05.csv"
variables:  # variables in round1 CSV annotation to bring along, Superceeded by values in sample CSV annotation
  - "plate_well"
species_mixing:  # whether experiment contains more than one species. Superceeded by value in sample CSV annotatiton
  1
array_size:  # SLURM job array size
  24
chunks:
  1000
chunk_batch_size:
  25
grna_pbs_sequence:
  GTGGAAAGGACGAAACACCG
submission_command:
  "sbatch"

resources:
  map:
    cpus: 4
    mem: 60000
    queue: "shortq"
    time: "08:00:00"
  filter:
    cpus: 1
    mem: 8000
    queue: "shortq"
    time: "01:00:00"
  join:
    cpus: 1
    mem: 8000
    queue: "shortq"
    time: "00:30:00"
  report:
    cpus: 4
    mem: 80000
    queue: "longq"
    time: "3-00:00:00"