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):
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 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 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 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])