def main():
db = mds.get_db()
schema_version = mds.get_schema_version(db)
if schema_version is not None:
hit_schema_version = False
for from_version, conversion_func in SCHEMA_UPGRADE_FUNCTIONS:
if hit_schema_version or schema_version == from_version:
hit_schema_version = True
observed_from_version = mds.get_schema_version(db)
if observed_from_version != from_version:
raise Exception(
'Aborting schema upgrade. '
'Expected schema version to be {} but observed {}'.
format(
mds.version_to_str(from_version),
mds.version_to_str(observed_from_version),
))
print('upgrading schema from version:',
mds.version_to_str(from_version))
conversion_func(db)
mds.init_db(db)
print(
'successfully upgraded schema to version:',
mds.version_to_str(mds.get_schema_version(db)),
)
def main():
# parse command line arguments
parser = argparse.ArgumentParser(description='import SNP annotations')
parser.add_argument(
'platform',
help=
'the platform for the data we are importing. eg: MegaMUGA or GigaMUGA')
parser.add_argument(
'snp_annotation_txt',
help=
'the tab-delimited snp annotation file. There should be a header row and one row per SNP'
)
args = parser.parse_args()
import_snp_anno(args.snp_annotation_txt, args.platform, mds.init_db())
def main():
# parse command line arguments
parser = argparse.ArgumentParser(
description='import the final report with probe intensities')
parser.add_argument(
'--generate-ids',
action='store_true',
help=
'this option indicates that the "Sample ID" column should be treated as a non-canonical identifier and '
'a canonical ID will be automatically generated for each sample',
)
parser.add_argument(
'--on-duplicate',
choices=['halt', 'skip', 'replace'],
help=
'this option is only meaningful if --canonical-ids is also set. This indicates what action to take if a '
'duplicate canonical ID is encountered during import: halt the import process with an error message, '
'skip the sample with a warning message or replace the existing sample with a warning',
)
parser.add_argument(
'platform',
help='the platform for the data we are importing. eg: MegaMUGA')
parser.add_argument(
'final_report',
help=
'the final report file as exported by GenomeStudio Genotyping Module. This report must '
'be tab separated, must be in the "Standard" format and must contain '
'at least the following columns: '
'SNP Name, Sample ID, X, Y, Allele1 - Forward, Allele2 - Forward')
parser.add_argument(
'sample_annotation_txt',
nargs='*',
help=
'an (optional) tab-delimited sample annotation file. There should be a header row and one row per sample'
)
args = parser.parse_args()
sample_anno_dicts = dict()
for sample_anno_filename in args.sample_annotation_txt:
curr_dicts = sai.sample_anno_dicts(sample_anno_filename)
sample_anno_dicts = sai.merge_dicts(sample_anno_dicts, curr_dicts)
report_name = splitext(basename(args.final_report))[0]
import_final_report(args.generate_ids, args.on_duplicate,
args.final_report, sample_anno_dicts, args.platform,
[report_name, args.platform], mds.init_db())
def main():
# parse command line arguments
parser = argparse.ArgumentParser(
description='import annotations for genetically-engineered constructs')
parser.add_argument(
'platform',
help=
'the platform for the data we are importing. eg: MegaMUGA or GigaMUGA')
parser.add_argument(
'annotation_txt',
help=
'the tab-delimited file with header columns: "Target", "Marker" and "Informative axis". '
'The target column contains an identifiers for the genetically-engineered construct being '
'targeted by the marker. Informative axis will be "x" or "y" and indicates which axis '
'is informative for performing a presence/absence call for the genetically-engineered '
'constructs (the non-informative axis will be ignored)')
args = parser.parse_args()
import_gemm_anno(args.annotation_txt, args.platform, mds.init_db())
def main():
# parse command line arguments
parser = argparse.ArgumentParser(
description='import the final report with probe intensities')
parser.add_argument(
'platform',
help='the platform for the data we are importing. eg: MegaMUGA')
parser.add_argument(
'tag',
help='a tag name that should be associated with all imported samples')
parser.add_argument('geno_matrix_csv',
help='comma-separated genotype values matrix')
parser.add_argument('x_matrix_csv',
help='comma-separated X intensity values matrix')
parser.add_argument('y_matrix_csv',
help='comma-separated Y intensity values matrix')
args = parser.parse_args()
import_samples(args.platform, args.geno_matrix_csv, args.x_matrix_csv,
args.y_matrix_csv, [args.tag, args.platform], mds.init_db())