--- # Configuration file for running ChIP-seq workflow # Here is where the reference genomes are specified reference: # name of the genome NC_004431.1: # location of the genbanks. If put in the location and format shown # below the pipeline will attempt to pull this file from NCBI by # accession number genbanks: - resources/genbanks/NC_004431.1.gbk # This is the fasta file for each chromosome in the genome # If specified in this location then it is automatically parsed # from the genbank. fastas: - results/alignment/process_genbank/NC_004431.1/NC_004431.1.fna # This is the expected total size in basepair of the final genome genome_size: 5231428 # Options to control genome coverage calculations coverage: # what resolution in bp do you want the coverage to be calculated? resolution: 5 # Options to control normalization of coverage signals normalization: # how to normalize within a sample. Options include: # RPKM, CPM, BPM, RPGC, median, and SES. See deeptools manual for # details on these normalization methods. within: CPM # Robust Z scale the log2ratio of extracted to input RobustZ: FALSE # Options to control quality control quality_control: # what column to group samples by for ChIP-QC output plots? group_by: genome # Options to control peak calling peak_calling: # Options that control CMARRT calling cmarrt: # Can specify individual parameters based on a column group_by: genome # for each value in the column specify the parameters NC_004431.1: # Half the size of the window in *entries* thus this would be 25 # * 5 bp resolution for a half window size of 125 bp wi: 25 # Number of entries to consolidate peaks over i.e. two peaks within # 10 * 5bp = 50 bp will get merged into one peak. consolidate: 10 macs2: group_by: genome NC_004431.1: # call broad peaks? broad: true