def main(p_dict):
bimfile = None
if p_dict['vbim'] is not None:
bimfile = p_dict['vbim']
elif p_dict['vgf'] is not None:
bimfile = p_dict['vgf'] + '.bim'
elif p_dict['gf'] is not None:
bimfile = p_dict['gf'] + '.bim'
else:
print('Set of validation SNPs is missing! Please specify either a validation PLINK genotype file, ' \
'or a PLINK BIM file with the SNPs of interest.')
if os.path.isfile(p_dict['out']):
print('Output file (%s) already exists! Delete, rename it, or use a different output file.'\
% (p_dict['out']))
raise Exception('Output file already exists!')
h5f = h5py.File(p_dict['out'], 'w')
summary_dict = {}
summary_dict[0]={'name':'Summary statistics filename:','value':p_dict['ssf']}
summary_dict[1]={'name':'LD reference genotypes filename:','value':p_dict['gf']}
summary_dict[3]={'name':'Coordinated data output filename:','value':p_dict['out']}
if p_dict['vgf'] is not None:
summary_dict[2]={'name':'Validation genotypes filename:','value':p_dict['vgf']}
sum_stats_parsers.parse_sum_stats(h5f, p_dict, bimfile, summary_dict)
coordinate_datasets(p_dict['gf'], h5f,summary_dict,
validation_genotype_file=p_dict['vgf'],
max_freq_discrep=p_dict['max_freq_discrep'],
min_maf=p_dict['maf'],
skip_coordination=p_dict['skip_coordination'],
debug=p_dict['debug'])
h5f.close()
reporting.print_summary(summary_dict, 'Summary of coordination step')
def main(p_dict):
bimfile = None
if p_dict['vbim'] is not None:
bimfile = p_dict['vbim']
elif p_dict['vgf'] is not None:
bimfile = p_dict['vgf'] + '.bim'
elif p_dict['gf'] is not None:
bimfile = p_dict['gf'] + '.bim'
else:
print('Set of validation SNPs is missing! Please specify either a validation PLINK genotype file, ' \
'or a PLINK BIM file with the SNPs of interest.')
if os.path.isfile(p_dict['out']):
print('Output file (%s) already exists! Delete, rename it, or use a different output file.'\
% (p_dict['out']))
raise Exception('Output file already exists!')
h5f = h5py.File(p_dict['out'], 'w')
summary_dict = {}
summary_dict[0]={'name':'Summary statistics filename:','value':p_dict['ssf']}
summary_dict[1]={'name':'LD reference genotypes filename:','value':p_dict['gf']}
summary_dict[3]={'name':'Coordinated data output filename:','value':p_dict['out']}
if p_dict['vgf'] is not None:
summary_dict[2]={'name':'Validation genotypes filename:','value':p_dict['vgf']}
sum_stats_parsers.parse_sum_stats(h5f, p_dict, bimfile, summary_dict)
coordinate_datasets(p_dict['gf'], h5f,summary_dict,
validation_genotype_file=p_dict['vgf'],
max_freq_discrep=p_dict['max_freq_discrep'],
min_maf=p_dict['maf'],
skip_coordination=p_dict['skip_coordination'],
debug=p_dict['debug'])
h5f.close()
reporting.print_summary(summary_dict, 'Summary of coordination step')
def test_parse_sum_stats(self):
p_dict = {
'ssf': os.path.join(TEST_DIR, 'test_data/sim1_0_ss.txt'),
'ssf_format': 'LDPRED',
'only_hm3': False,
'N': 10000,
'debug': True,
'z_from_se': False,
'match_genomic_pos': False,
'eff_type': 'LINREG'
}
bimfile = os.path.join(TEST_DIR, 'test_data/sim1_0_test.bim')
summary_dict = {}
out = '%s_parse_sum_stats.hdf5' % self.tmp_file_prefix
with h5py.File(out, 'w') as h5f:
sum_stats_parsers.parse_sum_stats(h5f, p_dict, bimfile,
summary_dict)
self.assertEqual(len(h5f['sum_stats']['chrom_1']['betas']), 2000)
p_dict = {
'ssf': os.path.join(TEST_DIR, 'test_data/sim4_0_ss.txt'),
'ssf_format': 'LDPRED',
'only_hm3': False,
'N': None,
'debug': True,
'z_from_se': True,
'match_genomic_pos': False,
}
bimfile = os.path.join(TEST_DIR, 'test_data/sim4_0_test.bim')
summary_dict = {}
out = '%s_parse_sum_stats.hdf5' % self.tmp_file_prefix
with h5py.File(out, 'w') as h5f:
sum_stats_parsers.parse_sum_stats(h5f, p_dict, bimfile,
summary_dict)
self.assertEqual(len(h5f['sum_stats']['chrom_1']['betas']), 2000)
def main(p_dict):
bimfile = None
if p_dict['N'] is None:
print('Please specify an integer value for the sample size used to calculate the GWAS summary statistics.')
print('Preparing to parse summary statistics')
if p_dict['vbim'] is not None:
bimfile = p_dict['vbim']
elif p_dict['vgf'] is not None:
bimfile = p_dict['vgf'] + '.bim'
elif p_dict['gf'] is not None:
bimfile = p_dict['gf'] + '.bim'
else:
print('Set of validation SNPs is missing! Please specify either a validation PLINK genotype file, ' \
'or a PLINK BIM file with the SNPs of interest.')
if os.path.isfile(p_dict['out']):
print('Output file (%s) already exists! Delete, rename it, or use a different output file.'\
% (p_dict['out']))
raise Exception('Output file already exists!')
h5f = h5py.File(p_dict['out'], 'w')
sum_stats_parsers.parse_sum_stats(h5f, p_dict, bimfile)
check_mafs = p_dict['maf']>0
if not p_dict['vgf'] == None:
coordinate_genotypes_ss_w_ld_ref(genotype_file=p_dict['vgf'], reference_genotype_file=p_dict['gf'],
check_mafs=check_mafs,
hdf5_file=h5f, min_maf=p_dict['maf'], skip_coordination=p_dict['skip_coordination'],
debug=p_dict['debug'])
else:
coordinate_genot_ss(genotype_file=p_dict['gf'], check_mafs=check_mafs,
hdf5_file=h5f, min_maf=p_dict['maf'], skip_coordination=p_dict['skip_coordination'],
debug=p_dict['debug'])
h5f.close()
def test_parse_sum_stats(self):
p_dict = {
'ssf': os.path.join(TEST_DIR, 'test_data/coord_genotypes_ss.txt'),
'ssf_format': 'STANDARD',
'only_hm3': False,
'N': 10000,
'debug': True,
'match_genomic_pos': False,
}
bimfile = os.path.join(TEST_DIR,
'test_data/LDpred_cc_data_p0.001_train_0.bim')
summary_dict = {}
out = '%s_parse_sum_stats.hdf5' % self.tmp_file_prefix
with h5py.File(out, 'w') as h5f:
sum_stats_parsers.parse_sum_stats(h5f, p_dict, bimfile,
summary_dict)
self.assertEqual(len(h5f['sum_stats']['chrom_1']['betas']), 10)