def run(args, _gwas=None):
start = timer()
if not args.overwrite and os.path.exists(args.output_file):
logging.info("%s already exists, move it or delete it if you want it done again", args.output_file)
return
logging.info("Started metaxcan association")
context = MetaxcanUtilities.build_context(args, _gwas)
model_snps = context.get_model_snps()
total_snps = len(model_snps)
snps_found=set()
reporter = Utilities.PercentReporter(logging.INFO, total_snps)
i_genes, i_snps = context.get_data_intersection()
results = []
for gene in i_genes:
r, snps = AssociationCalculation.association(gene, context, return_snps=True)
results.append(r)
snps_found.update(snps)
reporter.update(len(snps_found), "%d %% of model's snps found so far in the gwas study")
Utilities.ensure_requisite_folders(args.output_file)
reporter.update(len(snps_found), "%d %% of model's snps used", force=True)
results = AssociationCalculation.dataframe_from_results(zip(*results))
results = MetaxcanUtilities.format_output(results, context, args.keep_ens_version)
results.to_csv(args.output_file, index=False)
end = timer()
logging.info("Sucessfully processed metaxcan association in %s seconds"%(str(end - start)))
def run_metaxcan(args, context):
logging.info("Started metaxcan association")
model_snps = context.get_model_snps()
total_snps = len(model_snps)
snps_found=set()
reporter = Utilities.PercentReporter(logging.INFO, total_snps)
i_genes, i_snps = context.get_data_intersection()
results = []
for gene in i_genes:
logging.log(7, "Processing gene %s", gene)
r, snps = AssociationCalculation.association(gene, context, return_snps=True)
results.append(r)
snps_found.update(snps)
reporter.update(len(snps_found), "%d %% of model's snps found so far in the gwas study")
reporter.update(len(snps_found), "%d %% of model's snps used", force=True)
results = AssociationCalculation.dataframe_from_results(results)
results = MetaxcanUtilities.format_output(results, context, args.remove_ens_version)
if args.output_file:
Utilities.ensure_requisite_folders(args.output_file)
results.to_csv(args.output_file, index=False)
return results
def run_additional(args, context):
logging.info("Started metaxcan additional stats")
i_genes, i_snps = context.get_data_intersection()
results = []
for gene in i_genes:
stats_ = AssociationCalculation.additional_stats(gene, context)
results.append(stats_)
results = AssociationCalculation.dataframe_from_aditional_stats(results)
results = MetaxcanUtilities.format_additional_output(results, context, args.remove_ens_version)
if args.additional_output:
Utilities.ensure_requisite_folders(args.additional_output)
results.to_csv(args.additional_output, index=False)
return results
def test_build_context(self):
c = _context()
r, snps = AssociationCalculation.association("A", c, return_snps=True)
assert_equal_tuple(self, r,
('A', 0.42313735862217716, 0.42845528455235105,
0.10250000000002803, 4, 4, 3))
r, snps = AssociationCalculation.association("B", c, return_snps=True)
assert_equal_tuple(self, r,
('B', 1.904102672555114, 1.4285714285708686,
0.16333333333323405, 6, 6, 6))
r, snps = AssociationCalculation.association("C", c, return_snps=True)
assert_equal_tuple(self, r,
('C', 0.089999999999999983, 0.049999999999999989,
0.013333333333320003, 3, 2, 1))
r, snps = AssociationCalculation.association("D", c, return_snps=True)
assert_equal_tuple(
self, r, ('D', numpy.nan, numpy.nan, numpy.nan, 2, numpy.nan, 0))
r, snps = AssociationCalculation.association("E", c, return_snps=True)
assert_equal_tuple(
self, r, ('E', numpy.nan, numpy.nan, numpy.nan, 1, numpy.nan, 0))
#The following is a case of "wrong" data
r, snps = AssociationCalculation.association("F", c, return_snps=True)
assert_equal_tuple(self, r, ('F', numpy.nan, numpy.nan, 0, 2, 2, 2))
r, snps = AssociationCalculation.association("G", c, return_snps=True)
assert_equal_tuple(self, r, ('G', numpy.nan, numpy.nan, 0, 1, 1, 1))
def run_metaxcan(args, context):
logging.info("Started metaxcan association")
model_snps = context.get_model_snps()
total_snps = len(model_snps)
snps_found = set()
reporter = Utilities.PercentReporter(logging.INFO, total_snps)
i_genes, i_snps = context.get_data_intersection()
results = []
additional = []
for i, gene in enumerate(i_genes):
if args.MAX_R and i + 1 > args.MAX_R:
logging.log("Early exit condition met")
break
logging.log(9, "Processing gene %i:%s", i, gene)
r, snps = AssociationCalculation.association(gene,
context,
return_snps=True)
results.append(r)
snps_found.update(snps)
reporter.update(
len(snps_found),
"%d %% of model's snps found so far in the gwas study")
if args.additional_output:
stats_ = AssociationCalculation.additional_stats(gene, context)
additional.append(stats_)
reporter.update(len(snps_found), "%d %% of model's snps used", force=True)
results = AssociationCalculation.dataframe_from_results(results)
results = MetaxcanUtilities.format_output(results, context,
args.remove_ens_version)
if args.additional_output:
additional = AssociationCalculation.dataframe_from_aditional_stats(
additional)
results = MetaxcanUtilities.merge_additional_output(
results, additional, context, args.remove_ens_version)
if args.output_file:
Utilities.ensure_requisite_folders(args.output_file)
results.to_csv(args.output_file, index=False)
return results
def test_dataframe_from_results(self):
results = [
('A', 0.42313735862217716, 0.42845528455235105, 0.10250000000002803, 4, 4, 3),
('B', 1.904102672555114, 1.4285714285708686, 0.16333333333323405, 6, 6, 6),
('C', 0.089999999999999983, 0.049999999999999989, 0.013333333333320003, 3, 2, 1)]
d = AssociationCalculation.dataframe_from_results(results)
A = AssociationCalculation.ARF
r_ = list(zip(*results))
numpy.testing.assert_array_equal(d[A.K_GENE], r_[A.GENE])
numpy.testing.assert_array_equal(d[A.K_ZSCORE], r_[A.ZSCORE])
numpy.testing.assert_array_equal(d[A.K_EFFECT_SIZE], r_[A.EFFECT_SIZE])
numpy.testing.assert_array_equal(d[A.K_N_SNPS_IN_MODEL], r_[A.N_SNPS_IN_MODEL])
numpy.testing.assert_array_equal(d[A.K_N_SNPS_IN_COV], r_[A.N_SNPS_IN_COV])
numpy.testing.assert_array_equal(d[A.K_N_SNPS_USED], r_[A.N_SNPS_USED])
def test_dataframe_from_results(self):
results = [
('A', 0.42313735862217716, 0.42845528455235105, 0.10250000000002803, 4, 4, 3),
('B', 1.904102672555114, 1.4285714285708686, 0.16333333333323405, 6, 6, 6),
('C', 0.089999999999999983, 0.049999999999999989, 0.013333333333320003, 3, 2, 1)]
d = AssociationCalculation.dataframe_from_results(results)
A = AssociationCalculation.ARF
r_ = zip(*results)
numpy.testing.assert_array_equal(d[A.K_GENE], r_[A.GENE])
numpy.testing.assert_array_equal(d[A.K_ZSCORE], r_[A.ZSCORE])
numpy.testing.assert_array_equal(d[A.K_EFFECT_SIZE], r_[A.EFFECT_SIZE])
numpy.testing.assert_array_equal(d[A.K_N_SNPS_IN_MODEL], r_[A.N_SNPS_IN_MODEL])
numpy.testing.assert_array_equal(d[A.K_N_SNPS_IN_COV], r_[A.N_SNPS_IN_COV])
numpy.testing.assert_array_equal(d[A.K_N_SNPS_USED], r_[A.N_SNPS_USED])
def test_build_context(self):
c = _context()
r, snps = AssociationCalculation.association("A", c, return_snps=True)
self.assertEqual(r, ('A', 0.42313735862217716, 0.42845528455235105, 0.10250000000002803, 4, 4, 3))
r, snps = AssociationCalculation.association("B", c, return_snps=True)
self.assertEqual(r, ('B', 1.904102672555114, 1.4285714285708686, 0.16333333333323405, 6, 6, 6))
r, snps = AssociationCalculation.association("C", c, return_snps=True)
self.assertEqual(r, ('C', 0.089999999999999983, 0.049999999999999989, 0.013333333333320003, 3, 2, 1))
r, snps = AssociationCalculation.association("D", c, return_snps=True)
self.assertEqual(r, ('D', numpy.nan, numpy.nan, numpy.nan, 2, numpy.nan, 0))
r, snps = AssociationCalculation.association("E", c, return_snps=True)
self.assertEqual(r, ('E', numpy.nan, numpy.nan, numpy.nan, 1, numpy.nan, 0))
#The following is a case of "wrong" data
r, snps = AssociationCalculation.association("F", c, return_snps=True)
self.assertEqual(r, ('F', numpy.nan, numpy.nan, 0, 2, 2, 2))
r, snps = AssociationCalculation.association("G", c, return_snps=True)
self.assertEqual(r, ('G', numpy.nan, numpy.nan, 0, 1, 1, 1))