def forward_lmm_kronecker(snps,phenos,Asnps=None,Acond=None,K1r=None,K1c=None,K2r=None,K2c=None,covs=None,Acovs=None,threshold=5e-8,maxiter=2,qvalues=False, update_covariances = False,verbose=None,**kw_args):
"""
Kronecker fixed effects test with forward selection
Args:
snps: [N x S] np.array of S SNPs for N individuals (test SNPs)
pheno: [N x P] np.array of 1 phenotype for N individuals
K: [N x N] np.array of LMM-covariance/kinship koefficients (optional)
If not provided, then linear regression analysis is performed
covs: [N x D] np.array of D covariates for N individuals
threshold: (float) P-value thrashold for inclusion in forward selection (default 5e-8)
maxiter: (int) maximum number of interaction scans. First scan is
without inclusion, so maxiter-1 inclusions can be performed. (default 2)
qvalues: Use q-value threshold and return q-values in addition (default False)
update_covar: Boolean indicator if covariances should be re-estimated after each forward step (default False)
Returns:
lm: lmix LMMi object
resultStruct with elements:
iadded: array of indices of SNPs included in order of inclusion
pvadded: array of Pvalues obtained by the included SNPs in iteration
before inclusion
pvall: [Nadded x S] np.array of Pvalues for all iterations.
Optional: corresponding q-values
qvadded
qvall
"""
verbose = dlimix.getVerbose(verbose)
#0. checks
N = phenos.shape[0]
P = phenos.shape[1]
if K1r==None:
K1r = np.dot(snps,snps.T)
else:
assert K1r.shape[0]==N, 'K1r: dimensions dismatch'
assert K1r.shape[1]==N, 'K1r: dimensions dismatch'
if K2r==None:
K2r = np.eye(N)
else:
assert K2r.shape[0]==N, 'K2r: dimensions dismatch'
assert K2r.shape[1]==N, 'K2r: dimensions dismatch'
covs,Acovs = _updateKronCovs(covs,Acovs,N,P)
if Asnps is None:
Asnps = [np.ones([1,P])]
if (type(Asnps)!=list):
Asnps = [Asnps]
assert len(Asnps)>0, "need at least one Snp design matrix"
if Acond is None:
Acond = Asnps
if (type(Acond)!=list):
Acond = [Acond]
assert len(Acond)>0, "need at least one Snp design matrix"
#1. run GP model to infer suitable covariance structure
if K1c==None or K2c==None:
vc = _estimateKronCovariances(phenos=phenos, K1r=K1r, K2r=K2r, K1c=K1c, K2c=K2c, covs=covs, Acovs=Acovs, **kw_args)
K1c = vc.getTraitCovar(0)
K2c = vc.getTraitCovar(1)
else:
vc = None
assert K1c.shape[0]==P, 'K1c: dimensions dismatch'
assert K1c.shape[1]==P, 'K1c: dimensions dismatch'
assert K2c.shape[0]==P, 'K2c: dimensions dismatch'
assert K2c.shape[1]==P, 'K2c: dimensions dismatch'
t0 = time.time()
lm,pv = test_lmm_kronecker(snps=snps,phenos=phenos,Asnps=Asnps,K1r=K1r,K2r=K2r,K1c=K1c,K2c=K2c,covs=covs,Acovs=Acovs)
#get pv
#start stuff
iadded = []
pvadded = []
qvadded = []
time_el = []
pvall = []
qvall = None
t1=time.time()
if verbose:
print(("finished GWAS testing in %.2f seconds" %(t1-t0)))
time_el.append(t1-t0)
pvall.append(pv)
imin= np.unravel_index(pv.argmin(),pv.shape)
score=pv[imin].min()
niter = 1
if qvalues:
assert pv.shape[0]==1, "This is untested with the fdr package. pv.shape[0]==1 failed"
qvall = []
qv = FDR.qvalues(pv)
qvall.append(qv)
score=qv[imin]
#loop:
while (score<threshold) and niter<maxiter:
t0=time.time()
pvadded.append(pv[imin])
iadded.append(imin)
if qvalues:
qvadded.append(qv[imin])
if update_covariances and vc is not None:
vc.addFixedTerm(snps[:,imin[1]:(imin[1]+1)],Acond[imin[0]])
vc.setScales()#CL: don't know what this does, but findLocalOptima crashes becahuse vc.noisPos=None
vc.findLocalOptima(fast=True)
K1c = vc.getTraitCovar(0)
K2c = vc.getTraitCovar(1)
lm.setK1c(K1c)
lm.setK2c(K2c)
lm.addCovariates(snps[:,imin[1]:(imin[1]+1)],Acond[imin[0]])
for i in range(len(Asnps)):
#add SNP design
lm.setSNPcoldesign(Asnps[i])
lm.process()
pv[i,:] = lm.getPv()[0]
pvall.append(pv.ravel())
imin= np.unravel_index(pv.argmin(),pv.shape)
if qvalues:
qv = FDR.qvalues(pv)
qvall[niter:niter+1,:] = qv
score = qv[imin].min()
else:
score = pv[imin].min()
t1=time.time()
if verbose:
print(("finished GWAS testing in %.2f seconds" %(t1-t0)))
time_el.append(t1-t0)
niter=niter+1
RV = {}
RV['iadded'] = iadded
RV['pvadded'] = pvadded
RV['pvall'] = np.array(pvall)
RV['time_el'] = time_el
if qvalues:
RV['qvall'] = qvall
RV['qvadded'] = qvadded
return lm,RV
def forward_lmm_kronecker(snps,phenos,Asnps=None,Acond=None,K1r=None,K1c=None,K2r=None,K2c=None,covs=None,Acovs=None,threshold=5e-8,maxiter=2,qvalues=False, update_covariances = False,verbose=None,**kw_args):
"""
Kronecker fixed effects test with forward selection
Args:
snps: [N x S] np.array of S SNPs for N individuals (test SNPs)
pheno: [N x P] np.array of 1 phenotype for N individuals
K: [N x N] np.array of LMM-covariance/kinship koefficients (optional)
If not provided, then linear regression analysis is performed
covs: [N x D] np.array of D covariates for N individuals
threshold: (float) P-value thrashold for inclusion in forward selection (default 5e-8)
maxiter: (int) maximum number of interaction scans. First scan is
without inclusion, so maxiter-1 inclusions can be performed. (default 2)
qvalues: Use q-value threshold and return q-values in addition (default False)
update_covar: Boolean indicator if covariances should be re-estimated after each forward step (default False)
Returns:
lm: lmix LMMi object
resultStruct with elements:
iadded: array of indices of SNPs included in order of inclusion
pvadded: array of Pvalues obtained by the included SNPs in iteration
before inclusion
pvall: [Nadded x S] np.array of Pvalues for all iterations.
Optional: corresponding q-values
qvadded
qvall
"""
verbose = limix.getVerbose(verbose)
#0. checks
N = phenos.shape[0]
P = phenos.shape[1]
if K1r==None:
K1r = np.dot(snps,snps.T)
else:
assert K1r.shape[0]==N, 'K1r: dimensions dismatch'
assert K1r.shape[1]==N, 'K1r: dimensions dismatch'
if K2r==None:
K2r = np.eye(N)
else:
assert K2r.shape[0]==N, 'K2r: dimensions dismatch'
assert K2r.shape[1]==N, 'K2r: dimensions dismatch'
covs,Acovs = _updateKronCovs(covs,Acovs,N,P)
if Asnps is None:
Asnps = [np.ones([1,P])]
if (type(Asnps)!=list):
Asnps = [Asnps]
assert len(Asnps)>0, "need at least one Snp design matrix"
if Acond is None:
Acond = Asnps
if (type(Acond)!=list):
Acond = [Acond]
assert len(Acond)>0, "need at least one Snp design matrix"
#1. run GP model to infer suitable covariance structure
if K1c==None or K2c==None:
vc = _estimateKronCovariances(phenos=phenos, K1r=K1r, K2r=K2r, K1c=K1c, K2c=K2c, covs=covs, Acovs=Acovs, **kw_args)
K1c = vc.getTraitCovar(0)
K2c = vc.getTraitCovar(1)
else:
vc = None
assert K1c.shape[0]==P, 'K1c: dimensions dismatch'
assert K1c.shape[1]==P, 'K1c: dimensions dismatch'
assert K2c.shape[0]==P, 'K2c: dimensions dismatch'
assert K2c.shape[1]==P, 'K2c: dimensions dismatch'
t0 = time.time()
lm,pv = test_lmm_kronecker(snps=snps,phenos=phenos,Asnps=Asnps,K1r=K1r,K2r=K2r,K1c=K1c,K2c=K2c,covs=covs,Acovs=Acovs)
#get pv
#start stuff
iadded = []
pvadded = []
qvadded = []
time_el = []
pvall = []
qvall = None
t1=time.time()
if verbose:
print ("finished GWAS testing in %.2f seconds" %(t1-t0))
time_el.append(t1-t0)
pvall.append(pv)
imin= np.unravel_index(pv.argmin(),pv.shape)
score=pv[imin].min()
niter = 1
if qvalues:
assert pv.shape[0]==1, "This is untested with the fdr package. pv.shape[0]==1 failed"
qvall = []
qv = FDR.qvalues(pv)
qvall.append(qv)
score=qv[imin]
#loop:
while (score<threshold) and niter<maxiter:
t0=time.time()
pvadded.append(pv[imin])
iadded.append(imin)
if qvalues:
qvadded.append(qv[imin])
if update_covariances and vc is not None:
vc.addFixedTerm(snps[:,imin[1]:(imin[1]+1)],Acond[imin[0]])
vc.setScales()#CL: don't know what this does, but findLocalOptima crashes becahuse vc.noisPos=None
vc.findLocalOptima(fast=True)
K1c = vc.getTraitCovar(0)
K2c = vc.getTraitCovar(1)
lm.setK1c(K1c)
lm.setK2c(K2c)
lm.addCovariates(snps[:,imin[1]:(imin[1]+1)],Acond[imin[0]])
for i in xrange(len(Asnps)):
#add SNP design
lm.setSNPcoldesign(Asnps[i])
lm.process()
pv[i,:] = lm.getPv()[0]
pvall.append(pv.ravel())
imin= np.unravel_index(pv.argmin(),pv.shape)
if qvalues:
qv = FDR.qvalues(pv)
qvall[niter:niter+1,:] = qv
score = qv[imin].min()
else:
score = pv[imin].min()
t1=time.time()
if verbose:
print ("finished GWAS testing in %.2f seconds" %(t1-t0))
time_el.append(t1-t0)
niter=niter+1
RV = {}
RV['iadded'] = iadded
RV['pvadded'] = pvadded
RV['pvall'] = np.array(pvall)
RV['time_el'] = time_el
if qvalues:
RV['qvall'] = qvall
RV['qvadded'] = qvadded
return lm,RV
def forward_lmm(snps,pheno,K=None,covs=None,qvalues=False,threshold=5e-8,maxiter=2,test='lrt',verbose=None,**kw_args):
"""
univariate fixed effects test with forward selection
Args:
snps: [N x S] np.array of S SNPs for N individuals (test SNPs)
pheno: [N x 1] np.array of 1 phenotype for N individuals
K: [N x N] np.array of LMM-covariance/kinship koefficients (optional)
If not provided, then linear regression analysis is performed
covs: [N x D] np.array of D covariates for N individuals
threshold: (float) P-value thrashold for inclusion in forward selection (default 5e-8)
maxiter: (int) maximum number of interaction scans. First scan is
without inclusion, so maxiter-1 inclusions can be performed. (default 2)
test: 'lrt' for likelihood ratio test (default) or 'f' for F-test
verbose: print verbose output? (False)
Returns:
lm: limix LMM object
RV: dictionary
RV['iadded']: array of indices of SNPs included in order of inclusion
RV['pvadded']: array of Pvalues obtained by the included SNPs in iteration
before inclusion
RV['pvall']: [Nadded x S] np.array of Pvalues for all iterations
"""
verbose = dlimix.getVerbose(verbose)
if K is None:
K=np.eye(snps.shape[0])
if covs is None:
covs = np.ones((snps.shape[0],1))
#assert single trait
assert pheno.shape[1]==1, 'forward_lmm only supports single phenotypes'
lm = test_lmm(snps,pheno,K=K,covs=covs,test=test,**kw_args)
pvall = []
pv = lm.getPv().ravel()
#hack to avoid issues with degenerate pv
pv[sp.isnan(pv)] = 1
pvall.append(pv)
imin= pv.argmin()
niter = 1
#start stuff
iadded = []
pvadded = []
qvadded = []
if qvalues:
assert pv.shape[0]==1, "This is untested with the fdr package. pv.shape[0]==1 failed"
qvall = []
qv = FDR.qvalues(pv)
qvall.append(qv)
score=qv.min()
else:
score=pv.min()
while (score<threshold) and niter<maxiter:
t0=time.time()
iadded.append(imin)
pvadded.append(pv[imin])
if qvalues:
qvadded.append(qv[0,imin])
covs=np.concatenate((covs,snps[:,imin:(imin+1)]),1)
lm.setCovs(covs)
lm.process()
pv = lm.getPv().ravel()
pv[sp.isnan(pv)] = 1
pvall.append(pv)
imin= pv.argmin()
if qvalues:
qv = FDR.qvalues(pv)
qvall[niter:niter+1,:] = qv
score = qv.min()
else:
score = pv.min()
t1=time.time()
if verbose:
print(("finished GWAS testing in %.2f seconds" %(t1-t0)))
niter=niter+1
RV = {}
RV['iadded'] = iadded
RV['pvadded'] = pvadded
RV['pvall'] = np.array(pvall)
if qvalues:
RV['qvall'] = np.array(qvall)
RV['qvadded'] = qvadded
return lm,RV
def forward_lmm(snps,pheno,K=None,covs=None,qvalues=False,threshold=5e-8,maxiter=2,test='lrt',verbose=None,**kw_args):
"""
univariate fixed effects test with forward selection
Args:
snps: [N x S] np.array of S SNPs for N individuals (test SNPs)
pheno: [N x 1] np.array of 1 phenotype for N individuals
K: [N x N] np.array of LMM-covariance/kinship koefficients (optional)
If not provided, then linear regression analysis is performed
covs: [N x D] np.array of D covariates for N individuals
threshold: (float) P-value thrashold for inclusion in forward selection (default 5e-8)
maxiter: (int) maximum number of interaction scans. First scan is
without inclusion, so maxiter-1 inclusions can be performed. (default 2)
test: 'lrt' for likelihood ratio test (default) or 'f' for F-test
verbose: print verbose output? (False)
Returns:
lm: limix LMM object
RV: dictionary
RV['iadded']: array of indices of SNPs included in order of inclusion
RV['pvadded']: array of Pvalues obtained by the included SNPs in iteration
before inclusion
RV['pvall']: [Nadded x S] np.array of Pvalues for all iterations
"""
verbose = limix.getVerbose(verbose)
if K is None:
K=np.eye(snps.shape[0])
if covs is None:
covs = np.ones((snps.shape[0],1))
#assert single trait
assert pheno.shape[1]==1, 'forward_lmm only supports single phenotypes'
lm = test_lmm(snps,pheno,K=K,covs=covs,test=test,**kw_args)
pvall = []
pv = lm.getPv().ravel()
#hack to avoid issues with degenerate pv
pv[sp.isnan(pv)] = 1
pvall.append(pv)
imin= pv.argmin()
niter = 1
#start stuff
iadded = []
pvadded = []
qvadded = []
if qvalues:
assert pv.shape[0]==1, "This is untested with the fdr package. pv.shape[0]==1 failed"
qvall = []
qv = FDR.qvalues(pv)
qvall.append(qv)
score=qv.min()
else:
score=pv.min()
while (score<threshold) and niter<maxiter:
t0=time.time()
iadded.append(imin)
pvadded.append(pv[imin])
if qvalues:
qvadded.append(qv[0,imin])
covs=np.concatenate((covs,snps[:,imin:(imin+1)]),1)
lm.setCovs(covs)
lm.process()
pv = lm.getPv().ravel()
pv[sp.isnan(pv)] = 1
pvall.append(pv)
imin= pv.argmin()
if qvalues:
qv = FDR.qvalues(pv)
qvall[niter:niter+1,:] = qv
score = qv.min()
else:
score = pv.min()
t1=time.time()
if verbose:
print ("finished GWAS testing in %.2f seconds" %(t1-t0))
niter=niter+1
RV = {}
RV['iadded'] = iadded
RV['pvadded'] = pvadded
RV['pvall'] = np.array(pvall)
if qvalues:
RV['qvall'] = np.array(qvall)
RV['qvadded'] = qvadded
return lm,RV
