share_novaseq_b1.yaml

output_dir: "/path/to/output/folder/"

## Uncomment these lines to do a trial run with only two small test chunks per sublibrary
# chunk_size: 2_000_000
# test_chunks: 2
chunk_size: 20_000_000

## Check the genomes
# importantly, make sure the STAR index is compatible with your STAR version
genome:
  bowtie2: /oak/stanford/groups/wjg/bliu/resources/shareseq_references/hg38/bowtie2/hg38
  star: /oak/stanford/groups/wjg/bliu/resources/shareseq_references/hg38/star # this is for STAR 2.7+ 
  gene_annotation: /oak/stanford/groups/wjg/bliu/resources/shareseq_references/hg38/gencode.v41.annotation.filtered.gtf

## Uncomment the line below to run in a container
# singularity: "/oak/stanford/groups/wjg/bliu/containers/shareseq_latest.sif"

## Regular expressions for 1st round barcodes that should be mapped to each sample
# Must cover all 1st round barcodes, can use resources like regex101.com to check syntax 
# (use a dummy Undetermined sample if some 1st round barcodes are unused)
samples:
  sample1_b1:  "A[0-9][0-9]"
  sample2_b1:  "B[0-9][0-9]"
  sample3_b1: "C[0-9][0-9]"
  sample4_b1:  "D[0-9][0-9]"
  sample5_b1:  "E[0-9][0-9]"
  sample6_b1:  "F[0-9][0-9]"
  sample7_b1:  "G[0-9][0-9]"
  sample8_b1:  "H[0-9][0-9]"

sequencing:
  220920:
    type: bcl
    run_dir: /oak/stanford/groups/wjg/seqruns/220920_A00509_0608_AHNT5JDSX3
    tile_chunks: 20 # speed up bcl2fastq 
    ATAC_I2:
      CL2: CTCTCTAT
      CL4: AGAGTAGA
      CL7: AAGGAGTA
      CL8: CTAAGCCT
    RNA_I2:
      CL2: AGGTTGCC
      CL4: CAGCAACG
      CL7: GATTCCCA
      CL8: CGGACTGC