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 xrange(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')
#Compute eigendecomposition for the data
eigenFile = 'temp_eigen.npz'
eigen = leapMain.eigenDecompose(bedExclude, outFile=eigenFile)
#compute heritability explained by this data
h2 = leapMain.calcH2(phenoFile,
prevalence,
eigen,
keepArr=indsToKeep,
h2coeff=1.0)
#Compute liabilities explained by this data
liabs = leapMain.probit(bedExclude,
phenoFile,
h2,
prevalence,
eigen,
keepArr=indsToKeep)
#perform GWAS, using the liabilities as the observed phenotypes
results_df = leapMain.leapGwas(bedExclude, bedTest, liabs, h2)
frame_list.append(results_df)
#Join together the results of all chromosomes, and print the top ranking SNPs
frame = pd.concat(frame_list)
frame.sort("PValue", inplace=True)
frame.index = np.arange(len(frame))
print('Top 10 most associated SNPs:')
print(frame.head(n=10))
#Create a bed object excluding SNPs from the current chromosome
bedExclude = leapUtils.getExcludedChromosome(bfile, chrom)
#Create a bed object including only SNPs from the current chromosome
bedTest = leapUtils.getChromosome(bfile, chrom)
#Compute eigendecomposition for the data
eigenFile = 'temp_eigen.npz'
eigen = leapMain.eigenDecompose(bedExclude, outFile=eigenFile)
#compute heritability explained by this data
h2 = leapMain.calcH2(phenoFile, prevalence, eigen, keepArr=indsToKeep)
#Compute liabilities explained by this data
liabs = leapMain.probit(bedExclude, phenoFile, h2, prevalence, eigen, keepArr=indsToKeep)
#perform GWAS, using the liabilities as the observed phenotypes
results_df = leapMain.leapGwas(bedExclude, bedTest, liabs, h2)
frame_list.append(results_df)
#Join together the results of all chromosomes, and print the top ranking SNPs
frame = pd.concat(frame_list)
frame.sort("PValue", inplace=True)
frame.index = np.arange(len(frame))
print 'Top 10 most associated SNPs:'
print frame.head(n=10)
