def find_vstructures(bfile, pfile, gfile, cisfile, assoc0file, window, vfile,
startTraitIdx, nTraits):
"""
running association scan
input:
pfile : phenotype file
cfile : covariance file
ffile : fixed effects file
cisfile : file containing cis anchors
assoc0file : file containing the results from the initial association scan
vfile : file containing v-structures
"""
preader = phenoReader.PhenoReaderFile(pfile)
greader = bedReader.BedReader(bfile)
model = gnetlmm.GNetLMM(preader, greader, window=window)
genecorr_reader = reader.FileReader(gfile + '.pv')
model.set_genecorr_reader(genecorr_reader)
assoc0Reader = reader.FileReader(assoc0file + '.pv')
model.set_assoc0_reader(assoc0Reader)
model.load_cis_anchors(cisfile)
model.find_vstructures(startTraitIdx, nTraits)
model.save_vstructures(vfile + '.csv')
def scan(bfile, pfile, cfile, ffile, vfile, assocfile, startTraitIdx, nTraits):
"""
running association scan
input:
bfile : basefilename of plink file
pfile : phenotype file
cfile : covariance file
ffile : fixed effects file
vfile : file containing vstructures
assocfile : file for saving results
"""
K = None
if cfile is not None:
K = np.loadtxt(cfile)
Covs = None
if ffile is not None:
Covs = np.loadtxt(ffile)
preader = phenoReader.PhenoReaderFile(pfile)
greader = bedReader.BedReader(bfile)
model = gnetlmm.GNetLMM(preader, greader, Covs=Covs, K=K)
model.load_vstructures(vfile + ".csv")
model.update_associations(startTraitIdx, nTraits)
model.save_updates(assocfile)
def plot_power(bfile, pfile, assoc0file, assocfile, plotfile, window):
# reading out p-values
score = {}
assoc0Reader = reader.FileReader(assoc0file + '.pv')
score['LMM'] = -np.log10(assoc0Reader.getMatrix())
assocReader = reader.FileReader(assocfile + '.pv')
score['GNetLMM'] = -np.log10(assocReader.getMatrix())
# get network
Agene = np.loadtxt(pfile + '.Agene')
# gene info
preader = phenoReader.PhenoReaderFile(pfile)
gene_start = preader.getGeneStart()
gene_end = preader.getGeneEnd()
gene_chrom = preader.getGeneChrom()
# snp info
breader = bedReader.BedReader(bfile)
snp_pos = breader.getSnpPos()
snp_chrom = breader.getSnpChrom()
P_cis, P_trans = get_groundtruth(Agene, snp_pos, snp_chrom, gene_start,
gene_chrom, window)
# delete cis-associations
for key in score.keys():
score[key][P_cis] = 0
# compute receiver operator characteristics
FPR = {}
TPR = {}
for key in score.keys():
FPR[key], TPR[key] = roc.roc(P_trans, score[key])
# plotting results
plotting.plotROCcurve(['LMM', 'GNetLMM'],
TPR,
FPR,
xlim=(0, 0.05),
ylim=(0, 0.42),
fn=plotfile)
def gene_has_cis_anchor(bfile, pfile, assoc0, cis_thresh, cis_window, cisfile):
"""
tests if a gene has a cis anchor
input:
bfile : binary bed file (bfile.bed, bfile.bim and bfile.fam are required)
pfile : phenotype file
assoc0file : basefilename of initial association scan
cis_thresh : thrshold for cis-association
cis_window : maximal distance between cis-snp and gene
cis_file : filename for saving cis assocaitions
"""
preader = phenoReader.PhenoReaderFile(pfile)
greader = bedReader.BedReader(bfile)
model = gnetlmm.GNetLMM(preader, greader, window=cis_window)
assoc0Reader = reader.FileReader(assoc0 + '.pv')
model.set_assoc0_reader(assoc0Reader)
model.gene_has_cis_anchor(cis_thresh)
model.save_cis_anchors(cisfile)
def marginal_genecorr(bfile, pfile, gfile):
"""
running marginal gene-gene correlations
Input:
bfile : binary bed file (bfile.bed, bfile.bim and bfile.fam are required)
pfile : phenotype file
cfile : covariance matrix file
ffile : covariates file
gfile : basename of output file
"""
preader = phenoReader.PhenoReaderFile(pfile)
greader = bedReader.BedReader(bfile)
model = gnetlmm.GNetLMM(preader, greader)
corr, pv = model.marginal_gene_correlations()
write = writer.Writer(gfile + '.pv')
write.writeMatrix(pv, fmt='%.4e')
write = writer.Writer(gfile + '.corr')
write.writeMatrix(corr, fmt='%.4f')
def initial_scan(bfile,
pfile,
cfile,
ffile,
assoc0file,
startSnpIdx=0,
nSnps=np.inf,
memory_efficient=False):
"""
running initial scan using a standard linear mixed model
Input:
bfile : binary bed file (bfile.bed, bfile.bim and bfile.fam are required)
pfile : phenotype file
cfile : covariance matrix file
ffile : covariates file
assoc0file : basename of output file
"""
K = None
if cfile is not None:
K = np.loadtxt(cfile)
Covs = None
if ffile is not None:
Covs = np.loadtxt(ffile)
preader = phenoReader.PhenoReaderFile(pfile)
greader = bedReader.BedReader(bfile)
model = gnetlmm.GNetLMM(preader, greader, K=K, Covs=Covs)
beta0, pv0 = model.initial_scan(startSnpIdx, nSnps, memory_efficient)
write = writer.Writer(assoc0file + '.pv')
write.writeMatrix(pv0, fmt='%.4e')
write = writer.Writer(assoc0file + '.beta')
write.writeMatrix(beta0, fmt='%.4f')