def create_baseline_model(self):
gss = [GenomicSubset(region) for region in LDSC.baseline_model_regions]
# create the annotation file
for chrnum in self.refpanel.chromosomes():
print('creating baseline annot file for chr', chrnum)
d = Dataset(self.params.refpanel, chrnum=chrnum)
sss = [SnpSubset(d, gs.restricted_to_chrom_bedtool(chrnum)) for gs in gss]
SnpSubset.print_subsets(self.baseline_filename(chrnum),
sss, LDSC.baseline_model_regions)
# create the ldscores file
for chrnum in self.refpanel.chromosomes():
d = Dataset(self.params.refpanel, chrnum=chrnum)
ldscores_command = [
'python', '-u', paths.foreign + 'ldsc/ldsc.py',
'--l2',
'--ld-wind-cm', str(self.params.ld_window / 1000.),
'--bfile', d.genotypes_bedfile.filename,
'--annot', self.baseline_filename(chrnum),
'--out', self.baseline_l2_filestem(chrnum)]
print(' '.join(ldscores_command))
outfilepath = self.baseline_l2_filestem(chrnum) + '.bsub_out'
bsub.submit(
ldscores_command,
outfilepath,
jobname='baseline,chr='+str(chrnum))
def preprocess(self):
if self.params.baseline and not self.baseline_preprocessing_in_progress():
print('baseline model not found. creating...')
self.declare_baseline_preprocessing_in_progress()
self.create_baseline_model()
print('submitting ld score jobs for annotation of interest')
gs = GenomicSubset(self.params.region)
# create the annotation file
for chrnum in self.refpanel.chromosomes():
d = Dataset(self.params.refpanel, chrnum=chrnum)
ss = SnpSubset(d, gs.restricted_to_chrom_bedtool(chrnum))
SnpSubset.print_subsets(self.annotation_filename(chrnum),
[ss], [self.params.region], add_other=True)
# create the ldscores file
for chrnum in self.refpanel.chromosomes():
d = Dataset(self.params.refpanel, chrnum=chrnum)
ldscores_command = [
'python', '-u', paths.foreign + 'ldsc/ldsc.py',
'--l2',
'--ld-wind-cm', str(self.params.ld_window / 1000.),
'--bfile', d.genotypes_bedfile.filename,
'--annot', self.annotation_filename(chrnum),
'--out', self.annotation_l2_filestem(chrnum)]
print(' '.join(ldscores_command))
outfilepath = self.annotation_l2_filestem(chrnum) + '.bsub_out'
bsub.submit(
ldscores_command,
outfilepath,
jobname=self.preprocessing_foldername()+',chr='+str(chrnum))
def preprocess(self):
matplotlib.use("Agg")
gs = GenomicSubset(self.params.region)
A = SnpSubset(self.refpanel, bedtool=gs.bedtool)
W = A.expanded_by(self.params.ld_window / 1000.0)
R = BlockDiag.ld_matrix(self.refpanel, W.irs.ranges(), 300, band_units="SNPs")
pickle.dump(R, self.R_file(mode="wb"), 2)
# R.plot(A.irs, filename=self.R_plotfilename())
RA = R.zero_outside_irs(A.irs)
pickle.dump(RA, self.RA_file(mode="wb"), 2)
def create_annot(args):
path = '/'.join(args.bedfile.split('/')[:-1]) + '/'
filename = args.bedfile.split('/')[-1]
if filename[-4:] == '.bed':
name = filename[:-4]
else:
name = filename
gs = GenomicSubset(name, path=path)
for chrnum in range(1,23)[::-1]:
print('creating annot file for chr', chrnum)
d = Dataset(args.refpanel + '.' + str(chrnum))
sss = [SnpSubset(d, gs.restricted_to_chrom_bedtool(chrnum))]
SnpSubset.print_subsets('{}{}.{}.annot.gz'.format(path, name, chrnum),
sss, [name])
def compute_statistic(self, alphahat, R, RA, N, Nref, memoize=False):
Rajd = Nadjust_after = None
if self.params.Radjust == "after":
Nadjust_after = Nref
Radj = R
elif self.params.Radjust == "before":
Nadjust_after = None
Radj = R.adjusted_before_inversion(Nref)
else:
Nadjust_after = None
Radj = R
if self.params.RAreg:
print("regularizing RA")
RA = RA.add_ridge(self.params.Lambda, renormalize=True)
gs = GenomicSubset(self.params.region)
A = SnpSubset(self.refpanel, bedtool=gs.bedtool)
RA.zero_outside_irs(A.irs)
if not memoize or not hasattr(self, "bias"):
print("adding lambda")
Radjreg = Radj.add_ridge(self.params.Lambda, renormalize=True)
print("computing inverse")
self.Radjreginv = Radjreg.inv(Nadjust_after=Nadjust_after)
print("done.computing bias...")
A = SnpSubset(self.refpanel, bedtool=GenomicSubset(self.params.region).bedtool)
W = self.window(A)
if not self.params.avgunbiased:
tr = self.Radjreginv.dot(RA).trace()
self.scaling = 1
else:
tr = RA.dot(self.Radjreginv).dot(R).dot(self.Radjreginv).trace()
Q = R.dot(self.Radjreginv).dot(RA).dot(self.Radjreginv).dot(R)
Q.zero_outside_irs(A.irs)
self.scaling = A.num_snps() / Q.trace()
# self.bias = tr / N + \
# float(self.refpanel.M-len(W.irs))/self.refpanel.M * \
# self.params.sigma2g * tr / self.params.pop_size
self.bias = tr / N + self.params.sigma2g * tr / self.params.pop_size
print("\nbias =", self.bias)
print("scaling =", self.scaling)
betahat = self.Radjreginv.dot(alphahat)
return self.scaling * (betahat.dot(RA.dot(betahat)) - self.bias)
def init(self):
self.Rri = pickle.load(self.Rri_file())
self.R = pickle.load(self.R_file())
self.RA = pickle.load(self.RA_file())
self.A = SnpSubset(self.refpanel,
GenomicSubset(self.params.region).bedtool)
self.ZR = pickle.load(self.biasmatrix_file())
self.Q, self.Z, self.QZ, self.QZR = self.get_variance_matrices()
