def vcf_results(taboo_store, input_path, rsnumber_stream, force=False):
"""Load genotypes from a VCF."""
logger.info('loading genotypes')
try:
gt_samples = load_vcf(taboo_store, input_path, rsnumber_stream,
experiment='sequencing')
except IntegrityError:
logger.warn('sample genotypes already loaded')
taboo_store.session.rollback()
return None
return gt_samples
def genotype(context, force):
"""Upload results from sequencing to the genotype platform."""
mip_case = context.obj["case"]
store = TabooDatabase(context.obj["taboo_db"])
with codecs.open(context.obj["rsnumber_ref"]) as rs_stream:
if mip_case.bcf_path and mip_case.bcf_path.exists():
analyses = load_bcf(store, mip_case.bcf_path, rs_stream, force=force)
else:
analyses = load_vcf(store, mip_case.ready_vcf, rs_stream, force=force)
for analysis in analyses:
logger.info("added analysis: %s", analysis.sample.sample_id)
sample_id = analysis.sample.sample_id
ped_sex = mip_case.ped.individuals[sample_id].sex
analysis.sample.expected_sex = SEX[ped_sex]
store.save()
def parse_payload(db, payload, config, force=False):
"""Process an action to upload genotypes."""
taboo_db = TabooDatabase(config['TABOO_URI'])
mip_analysis = load_analysis(payload['family_dir'])
with open(config['TABOO_RSNUMBERS']) as rs_stream:
if mip_analysis.bcf_path and mip_analysis.bcf_path.exists():
analyses = load_bcf(taboo_db, mip_analysis.bcf_path, rs_stream,
force=force)
else:
analyses = load_vcf(taboo_db, mip_analysis.ready_vcf, rs_stream,
force=force)
for analysis in analyses:
logger.info("added analysis: %s", analysis.sample.sample_id)
sample_id = analysis.sample.sample_id
ped_sex = mip_analysis.ped.individuals[sample_id].sex
analysis.sample.expected_sex = SEX[ped_sex]
taboo_db.save()
def post_samples(input_type, input_path, rs_stream, prepend=None,
include_key=None, force=False):
"""Add samples from VCF or Excel sheet."""
if input_type == 'vcf':
logger.info("loading genotypes from VCF: {}".format(input_path))
gt_samples = load_vcf(db, input_path, rs_stream,
experiment='sequencing', force=force)
source_id = input_path
elif input_type == 'excel':
logger.info("loading genotypes from Excel: {}".format(input_path))
file_name = path(input_path).normpath().basename()
source_data = parse_filname(file_name)
source_id = source_data['id']
sample_prepend = prepend or "{}-{}".format(source_id, include_key or '')
gt_samples = maf_results(db, input_path, prepend=sample_prepend,
include_key=include_key)
else:
raise ValueError("'input_type' must be either 'vcf' or 'excel'")
return dict(samples=gt_samples, source_id=source_id)
