def test_probit(self):
logging.info("Leap test_probit")
related_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1.related'))
bed, _ = leapUtils.loadData(self.bedbase, None, self.phen_fn, loadSNPs=False)
keepArr = leapUtils.loadRelatedFile(bed, related_file)
for i in range(1,11):
h2_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1_nochr{0}.h2'.format(i)))
h2 = np.loadtxt(h2_file, usecols=[0])
eigen_file = os.path.abspath(os.path.join(self.tempout_dir, 'dataset1_nochr{}.npz'.format(i)))
eigen = np.load(eigen_file)
ref_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1_nochr{}.liabs'.format(i)))
extractSim = 'dataset1/extracts/nochr{0}_extract.txt'.format(i)
bed, _ = leapUtils.loadData(self.bedbase, extractSim, self.phen_fn, loadSNPs=True)
output_file = os.path.abspath(os.path.join(self.tempout_dir, 'dataset1_nochr{}'.format(i)))
leapMain.probit(bed, self.phen_fn, h2=h2, prev=0.001, eigen=eigen, outFile=output_file, keepArr=keepArr, hess=False)
self.compare_pheno(ref_file, output_file+'.liabs')
def test_gwas(self):
logging.info("Leap test_gwas")
for i in range(1,11):
h2_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1_nochr{0}.h2'.format(i)))
h2 = np.loadtxt(h2_file, usecols=[0])
ref_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1_nochr{}.gwas.out.txt'.format(i)))
extractSim = 'dataset1/extracts/nochr{0}_extract.txt'.format(i)
extract = 'dataset1/extracts/chr{0}_extract.txt'.format(i)
bedSim, phe = leapUtils.loadData(self.bedbase, extractSim, self.phen_fn, loadSNPs=True)
bedTest, phe = leapUtils.loadData(self.bedbase, extract, self.phen_fn, loadSNPs=True)
output_file = os.path.abspath(os.path.join(self.tempout_dir, 'dataset1_nochr{}.gwas.out.txt'.format(i)))
liab_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1_nochr{}.liabs'.format(i)))
eigen_file = os.path.abspath(os.path.join(self.tempout_dir, 'dataset1_nochr{}.npz'.format(i)))
leapMain.leapGwas(bedSim, bedTest, liab_file, h2, output_file, eigenFile=eigen_file)
self.compare_gwas(ref_file, output_file)
def setUpClass(self):
from fastlmm.util.util import create_directory_if_necessary
create_directory_if_necessary(self.tempout_dir, isfile=False)
self.pythonpath = os.path.abspath(os.path.join(os.path.dirname(os.path.realpath(__file__))))
self.bedbase = os.path.join(self.pythonpath, 'dataset1/dataset1')
self.phen_fn = os.path.join(self.pythonpath, 'dataset1/dataset1.phe')
#Create eigendecompositions
logging.info("Creating eigendecomposition files")
for i in range(1,11):
output_file = os.path.abspath(os.path.join(self.tempout_dir, 'dataset1_nochr{}.npz'.format(i)))
extractSim = 'dataset1/extracts/nochr{0}_extract.txt'.format(i)
bed, _ = leapUtils.loadData(self.bedbase, extractSim, self.phen_fn, loadSNPs=True)
leapMain.eigenDecompose(bed, output_file)
def test_calch2(self):
logging.info("Leap test_calch2")
related_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1.related'))
bed, _ = leapUtils.loadData(self.bedbase, None, self.phen_fn, loadSNPs=False)
keepArr = leapUtils.loadRelatedFile(bed, related_file)
for i in range(1,11):
h2_file = os.path.abspath(os.path.join(self.gold_dir, 'dataset1_nochr{0}.h2'.format(i)))
eigen_file = os.path.abspath(os.path.join(self.tempout_dir, 'dataset1_nochr{}.npz'.format(i)))
eigen = np.load(eigen_file)
extractSim = 'dataset1/extracts/nochr{0}_extract.txt'.format(i)
expected_h2 = np.loadtxt(h2_file, usecols=[0])
h2 = leapMain.calcH2(self.phen_fn, 0.001, eigen, keepArr=keepArr, h2coeff=1.0)
assert np.abs(h2-expected_h2)<1e-5, 'Incorrect heritability estimated'
'relatedness cutoff (set to negative value to override relatedness check)'
)
parser.add_argument('--missingPhenotype',
metavar='missingPhenotype',
default='-9',
help='identifier for missing values (default: -9)')
args = parser.parse_args()
if (args.bfilesim is None): raise Exception('--bfilesim must be supplied')
if (args.prev is None): raise Exception('--prev must be supplied')
if (args.pheno is None): raise Exception('--pheno must be supplied')
#Read bfilesim and pheno file for heritability computation
bed, phe = leapUtils.loadData(args.bfilesim,
args.extractSim,
args.pheno,
args.missingPhenotype,
loadSNPs=(args.eigen is None),
standardize=True)
#Read/create eigendecomposition
if (args.eigen is not None): eigen = np.load(args.eigen)
else:
import eigenDecompose
eigen = eigenDecompose.eigenDecompose(bed)
#Compute relatedness
if (args.relCutoff <= 0): keepArr = np.ones(bed.iid.shape[0], dtype=bool)
else:
if (args.related is None):
bed2 = bed
if (args.extractSim is not None or args.eigen is not None):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--bfilesim", metavar="bfilesim", default=None, help="Binary plink file")
parser.add_argument("--extractSim", metavar="extractSim", default=None, help="SNPs subset to use")
parser.add_argument("--out", metavar="out", default=None, help="output file")
parser.add_argument(
"--pheno",
metavar="pheno",
default=None,
help="Phenotypes file (optional), only used for identifying unphenotyped individuals",
)
parser.add_argument(
"--missingPhenotype",
metavar="missingPhenotype",
default="-9",
help="identifier for missing values (default: -9)",
)
args = parser.parse_args()
if args.bfilesim is None:
raise Exception("bfilesim must be supplied")
if args.out is None:
raise Exception("output file name must be supplied")
# Read input files
bed, _ = leapUtils.loadData(args.bfilesim, args.extractSim, args.pheno, args.missingPhenotype, loadSNPs=True)
leapMain.eigenDecompose(bed, args.out)
help='output file')
parser.add_argument(
'--pheno',
metavar='pheno',
default=None,
help=
'Phenotypes file (optional), only used for identifying unphenotyped individuals'
)
parser.add_argument('--missingPhenotype',
metavar='missingPhenotype',
default='-9',
help='identifier for missing values (default: -9)')
args = parser.parse_args()
if (args.bfilesim is None and args.kinship is None):
raise Exception('bfilesim or kinship must be supplied')
if (args.bfilesim is not None and args.kinship is not None):
raise Exception('bfilesim and kinship cannot both be supplied')
if (args.out is None): raise Exception('output file name must be supplied')
if (args.bfilesim is not None):
bed, _ = leapUtils.loadData(args.bfilesim,
args.extractSim,
args.pheno,
args.missingPhenotype,
loadSNPs=True,
standardize=True)
else:
bed = None
leapMain.findRelated(bed, args.out, args.cutoff, args.kinship)
keepArr = leapUtils.findRelated(bed, cutoff, kinshipFile)
if (outFile is not None):
print 'Printing output to', outFile
f = open(outFile, 'w')
for i, (fid,iid) in enumerate(bed.iid):
if (keepArr[i]): f.write(fid + ' ' + iid + ' 0\n')
else: f.write(fid + ' ' + iid + ' 1\n')
f.close()
return keepArr
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--bfilesim', metavar='bfilesim', default=None, help='Binary plink file')
parser.add_argument('--kinship', metavar='kinsip', default=None, help='A kinship matrix represented in a text file. Note that this matrix must correspond exactly to the phenotypes file, unlike the bfilesim file option.')
parser.add_argument('--extractSim', metavar='extractSim', default=None, help='extractSim file')
parser.add_argument('--cutoff', metavar='cutoff', type=float, default=0.05, help='Relationship cutoff (default 0.05)')
parser.add_argument('--out', metavar='out', default=None, help='output file')
parser.add_argument('--pheno', metavar='pheno', default=None, help='Phenotypes file (optional), only used for identifying unphenotyped individuals')
parser.add_argument('--missingPhenotype', metavar='missingPhenotype', default='-9', help='identifier for missing values (default: -9)')
args = parser.parse_args()
if (args.bfilesim is None and args.kinship is None): raise Exception('bfilesim or kinship must be supplied')
if (args.bfilesim is not None and args.kinship is not None): raise Exception('bfilesim and kinship cannot both be supplied')
if (args.out is None): raise Exception('output file name must be supplied')
if (args.bfilesim is not None): bed, _ = leapUtils.loadData(args.bfilesim, args.extractSim, args.pheno, args.missingPhenotype, loadSNPs=True, standardize=True)
else: bed=None
leapMain.findRelated(bed, args.out, args.cutoff, args.kinship)
parser.add_argument('--maxFixedIters', metavar='maxFixedIters', type=int, default=100, help='Max number of iterations for fitting of fixed effects')
parser.add_argument('--epsilon', metavar='epsilon', type=float, default=1e-3, help='Convergence cutoff for fitting of fixed effects')
parser.add_argument('--missingPhenotype', metavar='missingPhenotype', default='-9', help='identifier for missing values (default: -9)')
args = parser.parse_args()
if (args.extract is not None and args.bfile is None): raise Exception('--extract cannot be used without --bfile')
if (args.bfile is not None and args.resfile is None): raise Exception('--bfile cannot be used without --resfile')
if (args.bfilesim is None): raise Exception('bfilesim must be supplied')
if (args.pheno is None): raise Exception('phenotype file must be supplied')
if (args.out is None): raise Exception('output file name must be supplied')
if (args.prev is None): raise Exception('prevlence must be supplied')
if (args.h2 is None): raise Exception('heritability must be supplied')
#Read bfilesim and pheno file for heritability computation
bed, phe = leapUtils.loadData(args.bfilesim, args.extractSim, args.pheno, args.missingPhenotype, loadSNPs=(args.eigen is None), standardize=True)
#Read/create eigendecomposition
if (args.eigen is not None): eigen = np.load(args.eigen)
else:
import eigenDecompose
eigen = eigenDecompose.eigenDecompose(bed)
#Compute relatedness
if (args.relCutoff <= 0): keepArr = np.ones(bed.iid.shape[0], dtype=bool)
else:
if (args.related is None):
bed2 = bed
if (args.extractSim is not None or args.eigen is not None): bed2, _ = leapUtils.loadData(args.bfilesim, None, args.pheno, args.missingPhenotype, loadSNPs=True)
keepArr = leapUtils.findRelated(bed2, args.relCutoff)
else:
parser.add_argument('--missingPhenotype',
metavar='missingPhenotype',
default='-9',
help='identifier for missing values (default: -9)')
args = parser.parse_args()
if (args.bfile is None): raise Exception('bfile must be supplied')
if (args.bfilesim is None): raise Exception('bfilesim must be supplied')
if (args.pheno is None): raise Exception('phenotype file must be supplied')
if (args.out is None): raise Exception('output file name must be supplied')
if (args.h2 is None): raise Exception('h2 must be supplied')
#Read bfile and pheno file
bedSim, _ = leapUtils.loadData(args.bfilesim,
args.extractSim,
args.pheno,
args.missingPhenotype,
loadSNPs=True)
bedTest, _ = leapUtils.loadData(args.bfile,
args.extract,
args.pheno,
args.missingPhenotype,
loadSNPs=True)
# #Read covariates
# if (args.covar is not None):
# covar = leapUtils.loadCovars(bedSim, args.covar)
# print 'Read', covar.shape[1], 'covariates from file'
# else: covar = None
leapMain.leapGwas(bedSim,
