NanoFilt.py 文件源码

def filter_using_summary(fq, args):
    """Use quality scores from albacore summary file for filtering

    Use the summary file from albacore for more accurate quality estimate
    Get the dataframe from nanoget, convert to dictionary
    """
    data = {entry[0]: entry[1] for entry in process_summary(
        summaryfile=args.summary,
        threads="NA",
        readtype=args.readtype,
        barcoded=False)[
        ["readIDs", "quals"]].itertuples(index=False)}
    try:
        for record in SeqIO.parse(fq, "fastq"):
            if data[record.id] > args.quality and len(record) > args.length:
                print(record[args.headcrop:args.tailcrop].format("fastq"), end="")
    except KeyError:
        logging.error("mismatch between summary and fastq: \
                       {} was not found in the summary file.".format(record.id))
        sys.exit('\nERROR: mismatch between sequencing_summary and fastq file: \
                 {} was not found in the summary file.\nQuitting.'.format(record.id))