Sparsity_Badger_Template

Badger script to calculate Sparsity for each gene using Gemma

---
definitions:

  # command and template must always be specified.
  command: gemma
  template: /gpfs/data/im-lab/nas40t2/Github/badger/examples/PBS_example_template.jinja

  copy_to_item: true

  default_arguments:
    job_memory: "4gb"
    job_walltime: "6:00:00"
    logs_folder: /gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac/logs
    setup: "module load gcc/6.2.0 \n module load gemma/0.94 \n cd /gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac "

  # This specifies what the script does once an individual file is generated.
  submission:
    !PBSQueue
      jobs_folder: /gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac/jobs
      job_name_key: job_name # Jobs will be written to job_name.sh files with the generated job_name argument filled in.
      fake_submission: true # Specifying this just writes the files and does not run a submission command.

  constants:
    GRM_dir: &GRM_DIR "/gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac/GRMs/"
    pheno_file: &PHENO_FILE "/gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac/phenotype_files/"
    geno_pref: &GENO_PREF "/gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac/genotype_files/"
# There are a lot of different types of arguments, and only a few are shown here.
arguments:

  - !Scalar { name: argument_4, prefix: "-bslmm", value: 1 }
  - !Scalar { name: argument_5, prefix: "-n", value: 1 }

  - !FilesInFolder
    name: argument_1
    prefix: "-g"
    folder: "/gpfs/data/im-lab/nas40t2/natasha/rat_genomics/GEMMA/Ac/genotype_files"
    regexp_filter: "geno(.*)"
    metadata_rules:
      - !ExtractFromFileNameRegexpMetadata
        paths: [ gene_name ]

  - !ArgumentFromMetadata
    name: argument_2
    prefix: "-p"
    prepend: *PHENO_FILE
    format_rule: "tmp.pheno.{gene_name}"
    sources: [ { path: gene_name, destination: gene_name }]
    
  - !ArgumentFromMetadata
    name: argument_3
    prefix: "-k"
    prepend: *GRM_DIR
    format_rule: "grm_Ac_{gene_name}.cXX.txt"
    sources: [ { path: gene_name, destination: gene_name }]
  
  - !ArgumentFromMetadata
    name: argument_6
    prefix: "-o"
    format_rule: "Ac_out_{gene_name}"
    sources: [ { path: gene_name, destination: gene_name }]

  - !ArgumentFromMetadata
    name: job_name
    format_rule: "gemma_sub_Ac-{gene_name}"
    sources: [ { path: gene_name, destination: gene_name }]