class TestUcscSnpDao(unittest.TestCase):
#---------------------------------------------
# Constants
#---------------------------------------------
#---------------------------------------------
# Setup Methods
#---------------------------------------------
def setUp(self):
'''Use a localhost UCSC copy.'''
url = 'mysql://*****:*****@localhost/ucsc'
self.engine = create_engine(url)
self.dao = SnpDao(url)
# Base.metadata.create_all(self.engine)
def tearDown(self):
'''Drop the database.'''
pass
#---------------------------------------------
# Test Methods
#---------------------------------------------
def test_num_records(self):
'''Test getting the total # of SNP records.'''
assert_equal(self.dao.num_records(), 54212080, 'Wrong row count from SNP table')
# Slow test; can take ~20 seconds
@nottest
def inactive_test_snps_on_chromosome(self):
'''Test retrieving SNPs by chromosome.'''
chrom = 22
assert_equal(len(list(self.dao.chrom_snps(chrom))), 730365, 'Wrong number of SNPs on chromosome %d' % (chrom,))
def test_get_snps(self):
'''Test retrieving SNPs by chromosome.'''
snps = self.dao.get_snps(['rs144773400', 'rs143255646', 'rs145599635'])
assert_equal(len(snps), 3, 'Wrong number returned SNPs entries')
assert_equal([snp.bp for snp in snps], [10229, 10145, 10234], 'Wrong SNP base-pair positions')
####################################################################################
if __name__ == '__main__':
'''
--------------------------------------------------
Main program
--------------------------------------------------
'''
options, args = __parse_command_line_args(sys.argv)
var_file_prefix, input_file, output_file = args
genotype_filter = __GENOTYPE_FILTER[options.genotype_filter]
genotype_cleaner = __GENOTYPE_CLEANER[options.genotype_filter]
allele_start_index = 1 if options.type == 'imputed' else 0
try:
# Read location list
snp_dao = SnpDao(options.db_url)
input_file = sys.stdin if args[1] == '-' else open(input_file, 'rb')
# Sample IDs are read from the pedigree, and must match the genotype files' ordering
pedigree = io_pedigree.read(options.pedigree_file,
options.genotype_id_file)
node_of = pedigree.node_of
sample_id = np.loadtxt(
options.id_file, dtype=np.int,
ndmin=1) if options.id_file else pedigree._sample_id
N = pedigree.num_genotyped
sample_index = np.array(
filter(lambda x: x is not None and x < N,
map(node_of.get, sample_id))
) # Filter FINDIVs that are not in the imputed FINDIV set
def setUp(self):
'''Use a localhost UCSC copy.'''
url = 'mysql://*****:*****@localhost/ucsc'
self.engine = create_engine(url)
self.dao = SnpDao(url)
