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:
from . 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 amend_sample(args):
loaded_subjects = get_subjects(args)
ped_dict = load_ped_file(args.sample)
header = get_ped_fields(args.sample)
with database_transaction(args.db) as c:
add_columns(header, c, args.clear)
for k, v in loaded_subjects.items():
if k in ped_dict:
item_list = map(quote_string, ped_dict[k])
sample = zip(header, item_list)
set_str = ",".join([str(x) + "=" + str(y) for (x, y) in sample])
sql_query = "update samples set {0} where sample_id={1}"
c.execute(sql_query.format(set_str, v.sample_id))
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:
from . 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 all_samples_predicate(args):
""" returns a predicate that returns True if, for a variant,
the only samples that have the variant have a given phenotype
"""
subjects = get_subjects(args).values()
return select_subjects_predicate(subjects, args)
def all_samples_predicate(args):
""" returns a predicate that returns True if, for a variant,
the only samples that have the variant have a given phenotype
"""
subjects = get_subjects(args).values()
return select_subjects_predicate(subjects, args)