comparison galaxy-tools/biobank/utils/before_prepare_seq_dsample_inputs.py @ 3:43be74e62bfe draft

Uploaded

3:43be74e62bfe

"""
This tool produce files used as input by 'prepare_seq_dsample_inputs'.

It needs as input an Illumina samplesheet and produce as output:
the same samplesheet with a new column 'sample_project'
a configuration file
The configuration file is a YAML file with the following structure:

 config_parameters:
   study_label: study_label

where study_label is mandatory
"""

import csv, sys, argparse, logging, yaml


LOG_FORMAT = '%(asctime)s|%(levelname)-8s|%(message)s'
LOG_DATEFMT = '%Y-%m-%d %H:%M:%S'
LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']

def make_parser():
    parser = argparse.ArgumentParser(description='prepare inputs for VLUTIL.prepare_seq_dsample_inputs')
    parser.add_argument('--logfile', type=str, help='log file (default=stderr)')
    parser.add_argument('--loglevel', type=str, choices=LOG_LEVELS,
                        help='logging level', default='INFO')
    parser.add_argument('--in-file', '-i', type=str, required=True,
                        help='input file')
    parser.add_argument('--samplesheet-output-file', type=str,
                        help='output file containing flowcell samplesheet',
                        default='./samplesheet.tsv')
    parser.add_argument('--config-output-file', type=str,
                        help='output file containing config definitions',
                        default='./config_parameters.yaml')
    parser.add_argument('--study', type=str, required=True,
                        help='study label parameter for YAML file')
    return parser


def read_samplesheet(in_file):
    with open(in_file, 'rU') as f:       
        reader = csv.DictReader(f, delimiter='\t')
        recs = [r for r in reader]
        fieldnames = reader.fieldnames
    return recs, fieldnames


def write_samplesheet_extended(recs, fields, out_file, sample_project_label):
    with open(out_file, 'wb') as f:
        fields.append('SampleProject')
        writer = csv.DictWriter(f, fields, delimiter='\t')
        writer.writeheader()
        for row in recs:
            row['SampleProject'] = sample_project_label
            writer.writerow(row)     


def write_yaml_config_file(out_file, study_label):
        config_data = {'config_parameters': {'study_label': study_label}}
        with open(out_file, 'w') as f:
            yaml.dump(config_data, f)


def main(argv):
    parser = make_parser()
    args = parser.parse_args(argv)

    log_level = getattr(logging, args.loglevel)
    kwargs = {'format': LOG_FORMAT,
              'datefmt': LOG_DATEFMT,
              'level': log_level}
    if args.logfile:
        kwargs['filename'] = args.logfile
    logging.basicConfig(**kwargs)
    logger = logging.getLogger('before_prepare_seq_dsample_inputs')

    logger.info('Loading data from file %s' % args.in_file)    
    recs, out_file_header = read_samplesheet(args.in_file)
    logger.debug('Retrieved %d records', len(recs))
    
    logger.info('Writing file %s' % args.samplesheet_output_file)
    write_samplesheet_extended(recs, out_file_header, args.samplesheet_output_file,
                               args.study)

    logger.info('Writing file %s' % args.config_output_file)
    write_yaml_config_file(args.config_output_file, args.study)

if __name__ == '__main__':
    main(sys.argv[1:])