comparison assess_alignment.py @ 5:0e556a3f85d6 draft

planemo upload for repository https://github.com/pvanheus/polio_report commit a99e10fec2fac5aae70974c977eb3b362a1a8429-dirty

4:1897677e107c

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--output_filename", help="Path to output file")
    parser.add_argument("--sample_name", help="Name of sample being analysed")
    parser.add_argument(
        "--dataset_names", type=comma_split, help="Comma separated names for datasets"
    )
    parser.add_argument("--datasets", nargs="+")
    args = parser.parse_args()

    offsets = {
        # these are in 0-based coordinates, so off-by-one from NCBI 1-based coordinates
        "poliovirus1sabin": 2479, # V01150

        if min_mismatches is None or mismatches < min_mismatches:
            min_mismatches = mismatches
            best_match_mismatch_list = mismatch_list
            best_match_quality = quality
            best_match_reference = dataset_name
            percent_mismatches = round(min_mismatches / lengths[best_match_reference] * 100, 2)

    info = {
        "sample_name": args.sample_name,
        "best_reference": best_match_reference,
        "mismatches": min_mismatches,
        "mismatch_list": best_match_mismatch_list,
        "quality": best_match_quality,
        "perc_mismatches": percent_mismatches
    }
    json.dump(info, open(args.output_filename, "w"))

5:0e556a3f85d6

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--output_filename", help="Path to output file")
    parser.add_argument("--consensus_output_filename", help="Path to output file for best consensus")
    parser.add_argument("--sample_name", help="Name of sample being analysed")
    parser.add_argument(
        "--dataset_names", type=comma_split, help="Comma separated names for datasets"
    )
    parser.add_argument("--datasets", nargs="+")
    parser.add_argument("--consensi", nargs="+")
    args = parser.parse_args()

    offsets = {
        # these are in 0-based coordinates, so off-by-one from NCBI 1-based coordinates
        "poliovirus1sabin": 2479, # V01150

        if min_mismatches is None or mismatches < min_mismatches:
            min_mismatches = mismatches
            best_match_mismatch_list = mismatch_list
            best_match_quality = quality
            best_match_reference = dataset_name
            best_consensus = args.consensi[file_index]
            percent_mismatches = round(min_mismatches / lengths[best_match_reference] * 100, 2)

    info = {
        "sample_name": args.sample_name,
        "best_reference": best_match_reference,
        "mismatches": min_mismatches,
        "mismatch_list": best_match_mismatch_list,
        "quality": best_match_quality,
        "perc_mismatches": percent_mismatches,
    }
    json.dump(info, open(args.output_filename, "w"))

    open(args.consensus_output_filename, "w").write(best_consensus)