gpUtils.py 文件源码

def normalizeSNPs(normMethod, X, y, prev=None, frqFile=None):
    if (normMethod == 'frq'):
        print 'flipping SNPs for standardization...'
        empMean = X.mean(axis=0) / 2.0
        X[:, empMean>0.5] = 2 - X[:, empMean>0.5]       
        mafs = np.loadtxt(frqFile, usecols=[1,2]).mean(axis=1)
        snpsMean = 2*mafs
        snpsStd = np.sqrt(2*mafs*(1-mafs))
    elif (normMethod == 'controls'):
        controls = (y<y.mean())
        cases = ~controls
        snpsMeanControls, snpsStdControls = X[controls, :].mean(axis=0), X[controls, :].std(axis=0)
        snpsMeanCases, snpsStdCases = X[cases, :].mean(axis=0), X[cases, :].std(axis=0)
        snpsMean = (1-prev)*snpsMeanControls + prev*snpsMeanCases
        snpsStd = (1-prev)*snpsStdControls + prev*snpsStdCases
    elif (normMethod is None): snpsMean, snpsStd = X.mean(axis=0), X.std(axis=0)
    else: raise Exception('Unrecognized normalization method: ' + normMethod)

    return snpsMean, snpsStd