def compute_snp(collect):
snp = collect[0]
id = collect[1]
# result = []
# Check SNPs for missing values
x = snp[keep].reshape((n,1)) # all the SNPs
v = np.isnan(x).reshape((-1,))
if v.sum():
keeps = True - v
xs = x[keeps,:]
if keeps.sum() <= 1 or xs.var() <= 1e-6:
# PS.append(np.nan)
# TS.append(np.nan)
# result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan))
# continue
return formatResult(id,np.nan,np.nan,np.nan,np.nan)
# Its ok to center the genotype - I used options.normalizeGenotype to
# force the removal of missing genotypes as opposed to replacing them with MAF.
if not options.normalizeGenotype:
xs = (xs - xs.mean()) / np.sqrt(xs.var())
Ys = Y[keeps]
X0s = X0[keeps,:]
Ks = K[keeps,:][:,keeps]
if options.kfile2:
K2s = K2[keeps,:][:,keeps]
Ls = LMM_withK2(Ys,Ks,X0=X0s,verbose=options.verbose,K2=K2s)
else:
Ls = LMM(Ys,Ks,X0=X0s,verbose=options.verbose)
if options.refit:
Ls.fit(X=xs,REML=options.REML)
else:
#try:
Ls.fit(REML=options.REML)
#except: pdb.set_trace()
ts,ps,beta,betaVar = Ls.association(xs,REML=options.REML,returnBeta=True)
else:
if x.var() == 0:
# PS.append(np.nan)
# TS.append(np.nan)
# result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan)) # writes nan values
return formatResult(id,np.nan,np.nan,np.nan,np.nan)
# continue
if options.refit:
L.fit(X=x,REML=options.REML)
# This is where it happens
ts,ps,beta,betaVar = L.association(x,REML=options.REML,returnBeta=True)
return formatResult(id,beta,np.sqrt(betaVar).sum(),ts,ps)
def compute_snp(j, snp_ids, q=None):
# print(j,len(snp_ids),"\n")
result = []
for snp_id in snp_ids:
# j,snp_id = collect
snp, id = snp_id
# id = collect[1]
# result = []
# Check SNPs for missing values
x = snp[keep].reshape((n, 1)) # all the SNPs
v = np.isnan(x).reshape((-1, ))
if v.sum():
# NOTE: this code appears to be unreachable!
if options.verbose:
sys.stderr.write("Found missing values in " + str(x))
keeps = True - v
xs = x[keeps, :]
if keeps.sum() <= 1 or xs.var() <= 1e-6:
# PS.append(np.nan)
# TS.append(np.nan)
# result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan))
# continue
result.append(formatResult(id, np.nan, np.nan, np.nan, np.nan))
continue
# Its ok to center the genotype - I used options.normalizeGenotype to
# force the removal of missing genotypes as opposed to replacing them with MAF.
if not options.normalizeGenotype:
xs = (xs - xs.mean()) / np.sqrt(xs.var())
Ys = Y[keeps]
X0s = X0[keeps, :]
Ks = K[keeps, :][:, keeps]
if options.kfile2:
K2s = K2[keeps, :][:, keeps]
Ls = LMM_withK2(Ys,
Ks,
X0=X0s,
verbose=options.verbose,
K2=K2s)
else:
Ls = LMM(Ys, Ks, X0=X0s, verbose=options.verbose)
if options.refit:
Ls.fit(X=xs, REML=options.REML)
else:
#try:
Ls.fit(REML=options.REML)
#except: pdb.set_trace()
ts, ps, beta, betaVar = Ls.association(xs,
REML=options.REML,
returnBeta=True)
else:
if x.var() == 0:
# Note: this code appears to be unreachable!
# PS.append(np.nan)
# TS.append(np.nan)
# result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan)) # writes nan values
result.append(formatResult(id, np.nan, np.nan, np.nan, np.nan))
continue
if options.refit:
L.fit(X=x, REML=options.REML)
# This is where it happens
ts, ps, beta, betaVar = L.association(x,
REML=options.REML,
returnBeta=True)
result.append(formatResult(id, beta, np.sqrt(betaVar).sum(), ts, ps))
# compute_snp.q.put([j,formatResult(id,beta,np.sqrt(betaVar).sum(),ts,ps)])
# print [j,result[0]]," in result queue\n"
if not q:
q = compute_snp.q
q.put([j, result])
return j
# Its ok to center the genotype - I used options.normalizeGenotype to
# force the removal of missing genotypes as opposed to replacing them with MAF.
if not options.normalizeGenotype: xs = (xs - xs.mean()) / np.sqrt(xs.var())
Ys = Y[keeps]
X0s = X0[keeps,:]
Ks = K[keeps,:][:,keeps]
if options.kfile2: K2s = K2[keeps,:][:,keeps]
if options.kfile2: Ls = LMM_withK2(Ys,Ks,X0=X0s,verbose=options.verbose,K2=K2s)
else: Ls = LMM(Ys,Ks,X0=X0s,verbose=options.verbose)
if options.refit: Ls.fit(X=xs,REML=options.REML)
else:
#try:
Ls.fit(REML=options.REML)
#except: pdb.set_trace()
ts,ps,beta,betaVar = Ls.association(xs,REML=options.REML,returnBeta=True)
else:
if x.var() == 0:
PS.append(np.nan)
TS.append(np.nan)
outputResult(id,np.nan,np.nan,np.nan,np.nan)
continue
if options.refit: L.fit(X=x,REML=options.REML)
ts,ps,beta,betaVar = L.association(x,REML=options.REML,returnBeta=True)
outputResult(id,beta,np.sqrt(betaVar).sum(),ts,ps)
PS.append(ps)
TS.append(ts)
def compute_snp(j,snp_ids,q = None):
# print(j,len(snp_ids),"\n")
result = []
for snp_id in snp_ids:
# j,snp_id = collect
snp,id = snp_id
# id = collect[1]
# result = []
# Check SNPs for missing values
x = snp[keep].reshape((n,1)) # all the SNPs
v = np.isnan(x).reshape((-1,))
if v.sum():
# NOTE: this code appears to be unreachable!
if options.verbose:
sys.stderr.write("Found missing values in "+str(x))
keeps = True - v
xs = x[keeps,:]
if keeps.sum() <= 1 or xs.var() <= 1e-6:
# PS.append(np.nan)
# TS.append(np.nan)
# result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan))
# continue
result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan))
continue
# Its ok to center the genotype - I used options.normalizeGenotype to
# force the removal of missing genotypes as opposed to replacing them with MAF.
if not options.normalizeGenotype:
xs = (xs - xs.mean()) / np.sqrt(xs.var())
Ys = Y[keeps]
X0s = X0[keeps,:]
Ks = K[keeps,:][:,keeps]
if options.kfile2:
K2s = K2[keeps,:][:,keeps]
Ls = LMM_withK2(Ys,Ks,X0=X0s,verbose=options.verbose,K2=K2s)
else:
Ls = LMM(Ys,Ks,X0=X0s,verbose=options.verbose)
if options.refit:
Ls.fit(X=xs,REML=options.REML)
else:
#try:
Ls.fit(REML=options.REML)
#except: pdb.set_trace()
ts,ps,beta,betaVar = Ls.association(xs,REML=options.REML,returnBeta=True)
else:
if x.var() == 0:
# Note: this code appears to be unreachable!
# PS.append(np.nan)
# TS.append(np.nan)
# result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan)) # writes nan values
result.append(formatResult(id,np.nan,np.nan,np.nan,np.nan))
continue
if options.refit:
L.fit(X=x,REML=options.REML)
# This is where it happens
ts,ps,beta,betaVar = L.association(x,REML=options.REML,returnBeta=True)
result.append(formatResult(id,beta,np.sqrt(betaVar).sum(),ts,ps))
# compute_snp.q.put([j,formatResult(id,beta,np.sqrt(betaVar).sum(),ts,ps)])
# print [j,result[0]]," in result queue\n"
if not q:
q = compute_snp.q
q.put([j,result])
return j
# Its ok to center the genotype - I used options.normalizeGenotype to # force the removal of missing genotypes as opposed to replacing them with MAF. if not options.normalizeGenotype: xs = (xs - xs.mean()) / np.sqrt(xs.var()) Ys = Y[keeps] X0s = X0[keeps,:] Ks = K[keeps,:][:,keeps] if options.kfile2: K2s = K2[keeps,:][:,keeps] if options.kfile2: Ls = LMM_withK2(Ys,Ks,X0=X0s,verbose=options.verbose,K2=K2s) else: Ls = LMM(Ys,Ks,X0=X0s,verbose=options.verbose) if options.refit: Ls.fit(X=xs,REML=options.REML) else: #try: Ls.fit(REML=options.REML) #except: pdb.set_trace() ts,ps,beta,betaVar = Ls.association(xs,REML=options.REML,returnBeta=True) else: if x.var() == 0: PS.append(np.nan) TS.append(np.nan) outputResult(id,np.nan,np.nan,np.nan,np.nan) continue if options.refit: L.fit(X=x,REML=options.REML) ts,ps,beta,betaVar = L.association(x,REML=options.REML,returnBeta=True) outputResult(id,beta,np.sqrt(betaVar).sum(),ts,ps) PS.append(ps) TS.append(ts)