def test_invalid_data(self):
with self.assertRaises(Exceptions.InvalidInputFormat) as ctx:
MatrixManager.load_matrix_manager("tests/_td/cov/cov.duplicate.txt.gz")
self.assertTrue("duplicate" in ctx.exception.msg.lower())
with self.assertRaises(Exceptions.InvalidInputFormat) as ctx:
MatrixManager.load_matrix_manager("tests/_td/cov/cov.uncontiguous.txt.gz")
self.assertTrue("contiguous" in ctx.exception.msg.lower())
def test_invalid_data(self):
with self.assertRaises(Exceptions.InvalidInputFormat) as ctx:
MatrixManager.load_matrix_manager(
"tests/_td/cov/cov.duplicate.txt.gz")
self.assertTrue("duplicate" in ctx.exception.msg.lower())
with self.assertRaises(Exceptions.InvalidInputFormat) as ctx:
MatrixManager.load_matrix_manager(
"tests/_td/cov/cov.uncontiguous.txt.gz")
self.assertTrue("contiguous" in ctx.exception.msg.lower())
def test_from_load(self):
m = MatrixManager.load_matrix_manager("tests/_td/cov/cov.txt.gz")
snps, cov = m.get("ENSG00000239789.1")
self.assertEqual(snps, cov_data.SNPS_ENSG00000239789_1)
numpy.testing.assert_array_almost_equal(cov,
cov_data.COV_ENSG00000239789_1)
n = m.n_snps("ENSG00000239789.1")
self.assertEqual(n, len(cov_data.SNPS_ENSG00000239789_1))
with self.assertRaises(Exceptions.InvalidArguments) as ctx:
snps, cov = m.get("ENSG00000183742.8", ["rs7806506", "rs12718973"])
self.assertTrue("whitelist" in ctx.exception.message) #?
whitelist = ["rs3094989", "rs7806506", "rs12536095", "rs10226814"]
snps, cov = m.get("ENSG00000183742.8", whitelist)
self.assertEqual(snps, cov_data.SNPS_ENSG00000183742_8_w)
numpy.testing.assert_array_almost_equal(
cov, cov_data.COV_ENSG00000183742_8_w)
snps, cov = m.get("ENSG00000004766.11")
self.assertEqual(snps, cov_data.SNPS_ENSG00000004766_11)
numpy.testing.assert_array_almost_equal(
cov, cov_data.COV_ENSG00000004766_11)
n = m.n_snps("ENSG00000004766.11")
self.assertEqual(n, len(cov_data.COV_ENSG00000004766_11))
def test_from_load(self):
m = MatrixManager.load_matrix_manager("tests/_td/cov/cov.txt.gz")
snps, cov = m.get("ENSG00000239789.1")
self.assertEqual(snps, cov_data.SNPS_ENSG00000239789_1)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_ENSG00000239789_1)
n = m.n_ids("ENSG00000239789.1")
self.assertEqual(n, len(cov_data.SNPS_ENSG00000239789_1))
with self.assertRaises(Exceptions.InvalidArguments) as ctx:
snps, cov = m.get("ENSG00000183742.8", ["rs7806506", "rs12718973"])
self.assertTrue("whitelist" in ctx.exception.message) #?
whitelist = ["rs3094989", "rs7806506", "rs12536095", "rs10226814"]
snps, cov = m.get("ENSG00000183742.8", whitelist)
self.assertEqual(snps, cov_data.SNPS_ENSG00000183742_8_w)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_ENSG00000183742_8_w)
snps, cov = m.get("ENSG00000004766.11")
self.assertEqual(snps, cov_data.SNPS_ENSG00000004766_11)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_ENSG00000004766_11)
n = m.n_ids("ENSG00000004766.11")
self.assertEqual(n, len(cov_data.COV_ENSG00000004766_11))
def _context():
gwas = _gwas()
model = _prediction_model()
s = SampleData.dataframe_from_covariance(SampleData.sample_covariance_s_1())
covariance = MatrixManager.MatrixManager(s, D)
c = Utilities._build_context(model, covariance, gwas)
return c
def test_flatten(self):
labels = cov_data.SNPS_ENSG00000183742_8_w
matrix = cov_data.COV_ENSG00000183742_8_w
name= "test"
flat = MatrixManager._flatten_matrix_data([(name, labels, matrix)])
expected = \
[('test', 'rs7806506', 'rs7806506', 0.28428631),
('test', 'rs7806506', 'rs12536095', -0.01636001),
('test', 'rs7806506', 'rs10226814', -0.00157224),
('test', 'rs12536095', 'rs12536095', 0.35760734),
('test', 'rs12536095', 'rs10226814', 0.00815426),
('test', 'rs10226814', 'rs10226814', 0.44923289)]
numpy.testing.assert_array_equal(flat, expected)
X = [0,1,3]
cov = numpy.cov([X])
flat = MatrixManager._flatten_matrix_data([("a", "b", cov)])
expected = [('a', 'b', 'b', 2.33333333333333)]
numpy.testing.assert_array_equal(flat, expected)
def test_flatten(self):
labels = cov_data.SNPS_ENSG00000183742_8_w
matrix = cov_data.COV_ENSG00000183742_8_w
name = "test"
flat = MatrixManager._flatten_matrix_data([(name, labels, matrix)])
expected = \
[('test', 'rs7806506', 'rs7806506', 0.28428631),
('test', 'rs7806506', 'rs12536095', -0.01636001),
('test', 'rs7806506', 'rs10226814', -0.00157224),
('test', 'rs12536095', 'rs12536095', 0.35760734),
('test', 'rs12536095', 'rs10226814', 0.00815426),
('test', 'rs10226814', 'rs10226814', 0.44923289)]
numpy.testing.assert_array_equal(flat, expected)
X = [0, 1, 3]
cov = numpy.cov([X])
flat = MatrixManager._flatten_matrix_data([("a", "b", cov)])
expected = [('a', 'b', 'b', 2.33333333333333)]
numpy.testing.assert_array_equal(flat, expected)
def run(args):
if os.path.exists(args.snp_covariance_output):
logging.info("%s already exists, you have to move it or delete it if you want it done again", args.snp_covariance_output)
return
start = timer()
logging.info("Loading models...")
model_manager = PredictionModel.load_model_manager(args.models_folder, name_pattern=args.models_pattern)
all_snps = model_manager.get_rsids()
logging.info("processing genotype")
for chromosome, metadata, dosage in GenotypeUtilities.genotype_by_chromosome_from_args(args, all_snps):
logging.log(9, "Processing chromosome %s", str(chromosome))
covariance_results = pandas.DataFrame()
context = GenotypeAnalysis.GenotypeAnalysisContext(metadata, dosage, model_manager)
genes = context.get_genes()
reporter = Utilities.PercentReporter(9, len(genes))
reporter.update(0, "%d %% of genes processed so far in chromosome " + str(chromosome))
for i,gene in enumerate(genes):
logging.log(6, "%d/%d:%s", i+1, len(genes), gene)
cov_data = GenotypeAnalysis.get_prediction_covariance(context, gene)
cov_data = MatrixManager._flatten_matrix_data([cov_data])
cov_data = Utilities.to_dataframe(cov_data, GenotypeAnalysis.COVARIANCE_COLUMNS, to_numeric="ignore", fill_na="NA")
covariance_results = pandas.concat([covariance_results, cov_data])
reporter.update(i, "%d %% of genes processed so far in chromosome "+str(chromosome))
reporter.update(len(genes), "%d %% of genes processed so far in chromosome " + str(chromosome))
logging.log(9, "writing chromosome results")
Utilities.save_dataframe(covariance_results, args.snp_covariance_output,
mode="w" if chromosome ==1 else "a",
header=chromosome==1)
end = timer()
logging.info("Ran covariance builder in %s seconds" % (str(end - start)))
def test_from_data(self):
s = SampleData.dataframe_from_covariance(
SampleData.sample_covariance_s_1())
m = MatrixManager.MatrixManager(s)
snps, cov = m.get("A")
self.assertEqual(snps, cov_data.SNPS_A)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_A)
snps, cov = m.get("B")
self.assertEqual(snps, cov_data.SNPS_B)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_B)
snps, cov = m.get("C")
self.assertEqual(snps, cov_data.SNPS_C)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_C)
snps, cov = m.get("C", ['rs100', 'rs101', 'rs102'])
self.assertEqual(snps, cov_data.SNPS_C)
numpy.testing.assert_array_almost_equal(cov, cov_data.COV_C)
with self.assertRaises(Exceptions.InvalidArguments) as ctx:
snps, cov = m.get("C", ["rs100", "rs12718973"])
self.assertTrue("whitelist" in ctx.exception.message)
def run(args):
if os.path.exists(args.snp_covariance_output):
logging.info("%s already exists, you have to move it or delete it if you want it done again", args.snp_covariance_output)
return
start = timer()
logging.info("Loading models...")
model_manager = PredictionModel.load_model_manager(args.models_folder, name_pattern=args.models_pattern, name_filter=args.models_filter)
all_snps = model_manager.get_rsids()
Utilities.ensure_requisite_folders(args.snp_covariance_output)
with gzip.open(args.snp_covariance_output, "w") as o:
o.write("GENE\tRSID1\tRSID2\tVALUE\n")
logging.info("processing genotype")
for chromosome, metadata, dosage in GenotypeUtilities.genotype_by_chromosome_from_args(args, all_snps):
logging.log(9, "Processing chromosome %s", str(chromosome))
context = GenotypeAnalysis.GenotypeAnalysisContext(metadata, dosage, model_manager)
genes = context.get_genes()
reporter = Utilities.PercentReporter(9, len(genes))
reporter.update(0, "%d %% of genes processed so far in chromosome " + str(chromosome))
for i,gene in enumerate(genes):
logging.log(6, "%d/%d:%s", i+1, len(genes), gene)
cov_data = GenotypeAnalysis.get_prediction_covariance(context, gene)
cov_data = MatrixManager._flatten_matrix_data([cov_data])
for e in cov_data:
l = "{}\t{}\t{}\t{}\n".format(e[0], e[1], e[2], e[3])
o.write(l)
reporter.update(i, "%d %% of genes processed so far in chromosome "+str(chromosome))
reporter.update(len(genes), "%d %% of genes processed so far in chromosome " + str(chromosome))
end = timer()
logging.info("Ran covariance builder in %s seconds" % (str(end - start)))
