def run_query(args):
predicates = get_row_predicates(args)
add_required_columns_to_query(args)
formatter = select_formatter(args)
genotypes_needed = needs_genotypes(args)
gene_needed = needs_gene(args)
try:
subjects = get_subjects(args)
except KeyError:
subjects = []
kwargs = {}
if args.bcolz:
import gemini_bcolz
kwargs['variant_id_getter'] = gemini_bcolz.filter
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter, **kwargs)
gq.run(args.query,
args.gt_filter,
args.show_variant_samples,
args.sample_delim,
predicates,
genotypes_needed,
gene_needed,
args.show_families,
subjects=subjects)
if args.use_header and gq.header:
print gq.header
if not args.dgidb:
for row in gq:
print row
else:
# collect a list of all the genes that need to be queried
# from DGIdb
genes = defaultdict()
for row in gq:
genes[row['gene']] = True
# collect info from DGIdb
dgidb_info = query_dgidb(genes)
# rerun the query (the cursor is now consumed)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
gq.run(args.query,
args.gt_filter,
args.show_variant_samples,
args.sample_delim,
predicates,
genotypes_needed,
gene_needed,
args.show_families,
subjects=subjects,
**kwargs)
# report the query results with DGIdb info added at the end.
for row in gq:
print str(row) + "\t" + str(dgidb_info[row['gene']])
def family_wise_predicate(args):
formatter = select_formatter(args)
families = get_family_dict(args)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
predicates = []
for f in families.values():
family_names = [x.name for x in f]
subjects = get_subjects_in_family(args, f).values()
predicates.append(select_subjects_predicate(subjects, args,
family_names))
def predicate(row):
return sum([p(row) for p in predicates]) >= args.min_kindreds
return predicate
def run_query(args):
predicates = get_row_predicates(args)
add_required_columns_to_query(args)
formatter = select_formatter(args)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
gq.run(args.query, args.gt_filter, args.show_variant_samples,
args.sample_delim, predicates, needs_genotypes(args))
if args.use_header and gq.header:
print gq.header
for row in gq:
print row
def region(parser, args):
if os.path.exists(args.db):
formatter = select_formatter(args)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
if args.region is not None and args.gene is not None:
sys.exit('EXITING: Choose either --reg or --gene, not both.\n')
elif args.region is not None:
get_region(args, gq)
elif args.gene is not None:
get_gene(args, gq)
def run_query(args):
predicates = get_row_predicates(args)
add_required_columns_to_query(args)
formatter = select_formatter(args)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
gq.run(args.query, args.gt_filter, args.show_variant_samples,
args.sample_delim, predicates, needs_genotypes(args))
if args.use_header and gq.header:
print gq.header
for row in gq:
print row
def family_wise_predicate(args):
formatter = select_formatter(args)
families = get_family_dict(args)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
predicates = []
for f in families.values():
family_names = [x.name for x in f]
subjects = get_subjects_in_family(args, f).values()
predicates.append(select_subjects_predicate(subjects, args,
family_names))
def predicate(row):
return sum([p(row) for p in predicates]) >= args.min_kindreds
return predicate
def run_query(args):
predicates = get_row_predicates(args)
add_required_columns_to_query(args)
formatter = select_formatter(args)
genotypes_needed = needs_genotypes(args)
gene_needed = needs_gene(args)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
gq.run(
args.query,
args.gt_filter,
args.show_variant_samples,
args.sample_delim,
predicates,
genotypes_needed,
gene_needed,
args.show_families,
)
if args.use_header and gq.header:
print gq.header
if not args.dgidb:
for row in gq:
print row
else:
# collect a list of all the genes that need to be queried
# from DGIdb
genes = defaultdict()
for row in gq:
genes[row["gene"]] = True
# collect info from DGIdb
dgidb_info = query_dgidb(genes)
# rerun the query (the cursor is now consumed)
gq = GeminiQuery.GeminiQuery(args.db, out_format=formatter)
gq.run(
args.query,
args.gt_filter,
args.show_variant_samples,
args.sample_delim,
predicates,
genotypes_needed,
gene_needed,
args.show_families,
)
# report the query results with DGIdb info added at the end.
for row in gq:
print str(row) + "\t" + str(dgidb_info[row["gene"]])
def run_query(args):
start_time = time.time()
predicates = get_row_predicates(args)
add_required_columns_to_query(args)
formatter = select_formatter(args)
genotypes_needed = needs_genotypes(args)
gene_needed = needs_gene(args)
sample_names_needed = args.sample_filter or args.family_wise
gq = GeminiQuery.GeminiQuery(args.contact_points, args.keyspace, out_format=formatter)
gq.run(args.query, args.gt_filter, args.show_variant_samples,
args.sample_delim, predicates, genotypes_needed,
gene_needed, args.show_families, args.testing,
sample_names_needed, args.cores, start_time,
args.use_header, args.exp_id, args.timeout,
args.batch_size)
def run_query(args):
start_time = time.time()
predicates = get_row_predicates(args)
add_required_columns_to_query(args)
formatter = select_formatter(args)
genotypes_needed = needs_genotypes(args)
gene_needed = needs_gene(args)
sample_names_needed = args.sample_filter or args.family_wise
gq = GeminiQuery.GeminiQuery(args.contact_points,
args.keyspace,
out_format=formatter)
gq.run(args.query, args.gt_filter, args.show_variant_samples,
args.sample_delim, predicates, genotypes_needed, gene_needed,
args.show_families, args.testing, sample_names_needed, args.cores,
start_time, args.use_header, args.exp_id, args.timeout,
args.batch_size)
