def main_pipline(args,param): """ Algorithm a follows: 1 Filter bam file to only consider interesting reads 2 Estimate library parameters (lib_est) and print to library_info.txt. (mu, sigam, adjusted mu, sigma, ESS etc.) 3 Parse bamfile and get mean and stddev over each position in assembly (get_bp_stats) Print to bp_stats.csv 4 Get gap coordinates in assembly (get_gap_coordinates) print to gap_coordinates.csv 5 Calculate pvalues based on expected span mean and stddev (calc_pvalues) print ctg_accesion, pos, pvalues to p_values.csv 5' Cluster p-values into significant cliques and print significant locations on GFF format. """ if not os.path.exists(args.outfolder): os.makedirs(args.outfolder) # 1 bam_out = os.path.join(args.outfolder,'bam_filtered.bam') filter_bamfile(args,param) # 2 lib_est.LibrarySampler(bam_out,param) # 3 collect_libstats(args,args.outfolder,param) get_bp_stats.parse_bam(bam_out, param) # 4 #get_gap_coordinates. gap_coordinates(args,param) # 5-5' # sample_file_path = os.path.join(args.outfolder,'sample_se.txt') # sample_ess_correction.main(sample_file_path, param) p_value_cluster(args,param)
def bp_stats(args,param): bam_in = os.path.join(args.outfolder,'bam_filtered.bam') collect_libstats(args,args.outfolder, param) get_bp_stats.parse_bam(bam_in, param)