def main(config_file): with open(config_file) as in_handle: config = yaml.load(in_handle) region_size = int(config["algorithm"]["region_size"]) num_regions = int(config["algorithm"]["num_regions"]) bam_files = prepare_bam_files(config) regions = counts.random_regions(bam_files[0].all_regions(), num_regions, region_size) values = [] for i, bam1 in enumerate(bam_files): for bam2 in bam_files[i+1:]: values.extend(compare_bam_files(bam1, bam2, regions)) scatter_plot(values, bam1.name, bam2.name, region_size, config["files"]["coverage_pdf"])
def main(config_file): with open(config_file) as in_handle: config = yaml.load(in_handle) picard = PicardRunner(config["program"]["picard"]) bams = [NormalizedBam(align["name"], align["file"], picard) for align in config["alignments"]] for rconfig in config["regions"]: with open(rconfig["file"]) as in_handle: assert rconfig["name"] == "CES" regions = read_ces_regions(in_handle, rconfig["size"]) rregions = random_regions(regions, rconfig["random"], rconfig["size"]) counts = region_counts(bams, regions, rconfig["name"]) rcounts = region_counts(bams, rregions, "background") out_file = "%s-distribution%s.pdf" % (rconfig["name"], "-smoothed" if rconfig["smoothed"] else "") plot_count_distribution(out_file, counts + rcounts, rconfig["smoothed"])