pipeline.py 文件源码

def sample_to_run_data_mapping(samples_dir):
    '''
    return dict
    each key is string "sample_id"
    each value is a list of tuples ("library", "barcode")
    '''
    runs_file = samples_dir + "runs.tsv"
    sr_mapping = {}
    with open(runs_file) as tsv:
        for row in csv.DictReader(tsv, delimiter="\t"):
            sample = row["sample_id"]
            rb_pair = (row["run_name"], row["barcode_id"])
            if sample not in sr_mapping:
                sr_mapping[sample] = []
            sr_mapping[sample].append(rb_pair)
    return sr_mapping