config-template.yaml

genome:
    # genome size, use hs as for human, check MACS2 document for more details
    size: hs
    # path to genome reference fasta
    fasta: /share/references/hg38/fasta/hg38.fa
    # path to genome bwa index
    bwa_index: /share/references/hg38/bwa_index/hg38.fa
    # path to sorted genome blacklist, download from ENCODE
    blacklist: /share/references/hg38/blacklist/hg38.blacklist.sorted.bed
    # gene annotation in bgzip bed format, must indexed using tabix, download from UCSC
    refgene: /share/references/hg38/refgene_anno/hg38.refGene.gene.bed.gz
    # path to reference genome size file
    mock_regions: /share/references/hg38/1000_Genomes_Project/20160622.allChr.pilot_mask.bed
    # path to bed file than you want to mock ecDNA

# path to ATAC-Seq adapter
adapter: /path/to/resource/adapter.fa

# reads filter parameters
params:
    # minimum mapq
    mapq: 10
    # flag include
    include: 1
    # flag exclude
    exclude: 1548
    # maximum mismatch rate
    mismatch: 0.05
    # minimum depth for considering a junction coverage, optional
    depth: 10
    # maximum output circle
    limit: 1000

# path to workspace, all final output and intermediate output will be written to this directory
workspace: /path/to/circlehunter/workspace

# sample list
samples:
  GSM3832731: # sample id
    fastq:
      SRR8236755: # library id
        # path to fastq of read1
        fq1: /path/to/fastq/PRJNA506071/GSM3832731/SRR8236755/SRR8236755_1.fastq.gz
        # path to fastq of read2
        fq2: /path/to/fastq/PRJNA506071/GSM3832731/SRR8236755/SRR8236755_2.fastq.gz
      # specific another library of the same sample like upon if needed
      # circlehunter will merge them automatically for you
  GSM3832732:
    bam:
      # bam file as input, circlehunter will use the aligned and sorted bam file instead
      SRR8236756: /path/to/bam/PRJNA506071/GSM3832732/SRR8236756/SRR8236756.sorted.bam
      # specific another library of the same sample like upon if needed
      # circlehunter will merge them automatically for you

# ## following config only use in simulation
# simulation:
#     # random seed
#     seed: 1665331200
#     # number of ecDNA mix in one sample
#     num: 2
#     # benchmark one sample repeat times
#     repeat: 5

#     # simulation reads fragment size
#     fragment_size_mean: 250
#     fragment_size_std: 180

#     # read coverage params
#     read_depth_test_length: 100
#     read_depth_ranges:
#         - 10
#         - 20
#         - 30
#         - 40
#         - 50

#     # read length params
#     read_length_test_depth: 30
#     read_length_ranges:
#         - 35
#         - 50
#         - 75
#         - 100