def get_bx_ids():
# Get all bx_ids present in source files organized by source
bx_ids = {}
files = get_reports_files(ARGS.ready_input_dir)
for file in files:
file_path = abspath(ARGS.ready_input_dir + file)
if file_path.endswith('.tsv'):
source = "ENIGMA"
bx_ids[source] = []
tsv_file = csv.DictReader(open(file_path, "r"), delimiter='\t')
for report in tsv_file:
ids = map(int, report['BX_ID'].split(','))
bx_ids[source] = bx_ids[source] + ids
else:
suffix = '.vcf'
source = file[:(len(file)-len(suffix))]
bx_ids[source] = []
vcf_reader = vcf.Reader(open(file_path, 'r'), strict_whitespace=True)
try:
for record in vcf_reader:
ids = map(int, record.INFO['BX_ID'])
bx_ids[source] = bx_ids[source] + ids
except ValueError as e:
print e
return bx_ids
def test_aggregate_reports_maintains_proper_variant_effect_lovd_formatting(self):
LOVD_reports_file = [INPUT_DIRECTORY + r for r in aggregate_reports.get_reports_files(INPUT_DIRECTORY) if r == 'LOVD.vcf']
reports = aggregate_reports.aggregate_reports(LOVD_reports_file, self.columns, self.genome_regions_symbol_dict)
# Check that two of each source are present
variant_effect_lovd_index = self.columns.index("Variant_effect_LOVD")
for variant in reports:
self.assertIn(variant[variant_effect_lovd_index][0], ['?/.', '+/+'])
def test_aggregate_reports_maintains_proper_variant_effect_lovd_formatting(self):
LOVD_reports_file = [INPUT_DIRECTORY + r for r in aggregate_reports.get_reports_files(INPUT_DIRECTORY) if r == 'LOVD.vcf']
reports = aggregate_reports.aggregate_reports(LOVD_reports_file, self.columns)
# Check that two of each source are present
variant_effect_lovd_index = self.columns.index("Variant_effect_LOVD")
for variant in reports:
self.assertIn(variant[variant_effect_lovd_index][0], ['?/.', '+/+'])
def test_aggregate_reports(self):
reports_files = [INPUT_DIRECTORY + r for r in aggregate_reports.get_reports_files(INPUT_DIRECTORY)]
reports = aggregate_reports.aggregate_reports(reports_files, self.columns, self.genome_regions_symbol_dict)
# Each test file contains two reports, check that all reports are present
self.assertEqual(len(reports), (len(self.sources) * 2))
# Check that two of each source are present
source_reports = {}
source_column_index = self.columns.index("Source")
for report in reports:
source = report[source_column_index]
if source not in source_reports:
source_reports[source] = 1
else:
source_reports[source] += 1
for source in self.sources:
self.assertEqual(source_reports[source], 2)
def test_aggregate_reports(self):
reports_files = [INPUT_DIRECTORY + r for r in aggregate_reports.get_reports_files(INPUT_DIRECTORY)]
reports = aggregate_reports.aggregate_reports(reports_files, self.columns)
# Each test file contains two reports, check that all reports are present
self.assertEqual(len(reports), (len(self.sources) * 2))
# Check that two of each source are present
source_reports = {}
source_column_index = self.columns.index("Source")
for report in reports:
source = report[source_column_index]
if source not in source_reports:
source_reports[source] = 1
else:
source_reports[source] += 1
for source in self.sources:
self.assertEqual(source_reports[source], 2)
def test_get_reports_files(self):
reports_files = aggregate_reports.get_reports_files(INPUT_DIRECTORY)
self.assertEqual(len(reports_files), 9)
self.assertNotIn("1000_Genomesready.vcf", reports_files)
def test_get_reports_files(self):
reports_files = aggregate_reports.get_reports_files(INPUT_DIRECTORY)
self.assertEqual(len(reports_files), 9)
self.assertNotIn("1000_Genomesready.vcf", reports_files)