def preprocess(self, s):
print('Acor is preprocessing', s.name, 'with refpanel=',
self.params.refpanel)
print(self.params)
annots = [
pa.Annotation(paths.annotations + aname)
for aname in self.params.annot_chr.split(',')
]
for a in annots:
print('preprocessing', a.filestem())
for c in s.chromosomes:
if not os.path.exists(
a.conv_filename(c, full=self.params.fullconv)):
conv_command = [
'python', '-u', paths.code + 'acor/acor.py',
'--annot-chr', a.stem_chr,
'--bfile-chr', self.refpanel.bfile_chr] + \
(['-fullconv'] if self.params.fullconv else []) + \
['conv',
'--chroms', str(c)]
print(' '.join(conv_command))
outfilepath = a.filestem(c) + '.' + \
('full' if self.params.fullconv else '') + \
'convbsub_out'
bsub.submit(
conv_command,
outfilepath,
jobname=self.params.annot_chr.replace('/','_') + \
',conv,chr='+str(c))
def preprocess(self, s):
print('Acor is preprocessing', s.name,
'with refpanel=', self.params.refpanel)
print(self.params)
annots = [pa.Annotation(paths.annotations + aname)
for aname in self.params.annot_chr.split(',')]
for a in annots:
print('preprocessing', a.filestem())
for c in s.chromosomes:
if not os.path.exists(a.conv_filename(c, full=self.params.fullconv)):
conv_command = [
'python', '-u', paths.code + 'acor/acor.py',
'--annot-chr', a.stem_chr,
'--bfile-chr', self.refpanel.bfile_chr] + \
(['-fullconv'] if self.params.fullconv else []) + \
['conv',
'--chroms', str(c)]
print(' '.join(conv_command))
outfilepath = a.filestem(c) + '.' + \
('full' if self.params.fullconv else '') + \
'convbsub_out'
bsub.submit(
conv_command,
outfilepath,
jobname=self.params.annot_chr.replace('/','_') + \
',conv,chr='+str(c))
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 submit_runs(self, s, overwrite=False, debug=False):
def outfile_path(batch_num):
path = s.root_folder() + 'logs/'
fs.makedir(path)
return path + '{}-batch{}.out'.format(self.fsid(), batch_num)
def run_job_name():
return 'run-{}-{}[1-{}]'.format(
self.fsid(), s.name, self.num_batches(s))
if not self.missing_results(s) and not overwrite:
print('submission unnecessary for', str(self), 'on', s.name)
return
if not self.dependencies_satisfied(s):
print('\nERROR:', str(self), 'cannot submit', s.name, '. It needs preprocessing')
return
print('\n' + str(self), 'submitting', s.name)
my_args = ['--method-name', self.method,
'--sim-name', s.name,
'run',
'--batch-num', '$LSB_JOBINDEX'] + \
self.command_line_params()
outfilepath = outfile_path('%I')
bsub.submit(
['python', '-u', paths.code + 'sim/methods/estimator_manager.py'] + my_args,
outfilepath,
jobname=run_job_name(),
memory_GB=8,
debug=debug)
def create_baseline_model(self):
gss = [GenomicSubset(region) for region in LDSC.baseline_model_regions]
# create the annotation file
for chrnum in self.refpanel.chromosomes():
print('creating baseline annot file for chr', chrnum)
d = Dataset(self.params.refpanel, chrnum=chrnum)
sss = [SnpSubset(d, gs.restricted_to_chrom_bedtool(chrnum)) for gs in gss]
SnpSubset.print_subsets(self.baseline_filename(chrnum),
sss, LDSC.baseline_model_regions)
# create the ldscores file
for chrnum in self.refpanel.chromosomes():
d = Dataset(self.params.refpanel, chrnum=chrnum)
ldscores_command = [
'python', '-u', paths.foreign + 'ldsc/ldsc.py',
'--l2',
'--ld-wind-cm', str(self.params.ld_window / 1000.),
'--bfile', d.genotypes_bedfile.filename,
'--annot', self.baseline_filename(chrnum),
'--out', self.baseline_l2_filestem(chrnum)]
print(' '.join(ldscores_command))
outfilepath = self.baseline_l2_filestem(chrnum) + '.bsub_out'
bsub.submit(
ldscores_command,
outfilepath,
jobname='baseline,chr='+str(chrnum))
def submit(args):
my_args = ['main', '--chrom', '$LSB_JOBINDEX']
d = Dataset('UK10Khg19.22')
outfilepath = d.auxfiles_path + '../' + \
'%I/.preprocess.out'
bsub.submit(['python', '-u', paths.code + 'real/preprocess.py'] + my_args,
outfilepath,
jobname='preprocess[1-22]',
memory_GB=16)
def submit(args):
sim = SumstatSimulation(args.sim_name)
my_args = ["--sim_name", args.sim_name, "main", "--beta_num", "$LSB_JOBINDEX"]
outfilepath = sim.path() + ".sim_betas.%I.out"
bsub.submit(
["python", "-u", paths.code + "sim/sim_betas.py"] + my_args,
outfilepath,
jobname="simbetas[1-" + str(sim.num_betas) + "]",
memory_GB=5,
)
def submit(args):
my_args = ['main',
'--chrom', '$LSB_JOBINDEX']
d = Dataset('UK10Khg19.22')
outfilepath = d.auxfiles_path + '../' + \
'%I/.preprocess.out'
bsub.submit(
['python', '-u', paths.code + 'real/preprocess.py'] + my_args,
outfilepath,
jobname='preprocess[1-22]',
memory_GB=16)
def submit(args):
my_args = [
'--annot_stem', args.annot_stem, '--refpanel', args.refpanel, 'main',
'--chrnum', '$LSB_JOBINDEX'
]
outfilepath = \
args.annot_stem + '.maf1p.%I.creation.log'
bsub.submit(['python', '-u', __file__] + my_args,
outfilepath,
jobname='selectrare[1-22]')
def submit(args):
my_args = ['--annot_stem', args.annot_stem,
'main',
'--chrnum', '$LSB_JOBINDEX']
outfilepath = \
args.annot_stem + '.random.%I.creation.log'
bsub.submit(
['python', '-u', paths.code + 'munge/randomize_annot_signs.py'] + my_args,
outfilepath,
jobname='randomize[1-22]', debug=args.debug)
def submit(args):
sim = SumstatSimulation(args.sim_name)
my_args = [
'--sim_name', args.sim_name, 'main', '--beta_num', '$LSB_JOBINDEX'
]
outfilepath = sim.path() + \
'.sim_betas.%I.out'
bsub.submit(['python', '-u', paths.code + 'sim/sim_betas.py'] + my_args,
outfilepath,
jobname='simbetas[1-' + str(sim.num_betas) + ']',
memory_GB=5)
def submit(args):
my_args = [
'--annot_stem', args.annot_stem, '--refpanel', args.refpanel, 'main',
'--chrnum', '$LSB_JOBINDEX'
]
outfilepath = \
args.annot_stem + '.%I.cannot.log'
bsub.submit(['python', '-u', paths.code + 'real/signed_preprocess.py'] +
my_args,
outfilepath,
jobname='preprocess[1-22]')
def submit(args):
my_args = ['--annot_stem', args.annot_stem,
'--refpanel', args.refpanel,
'main',
'--chrnum', '$LSB_JOBINDEX']
outfilepath = \
args.annot_stem + '.maf1p.%I.creation.log'
bsub.submit(
['python', '-u', __file__] + my_args,
outfilepath,
jobname='selectrare[1-22]')
def submit(args):
my_args = ['--annot_stem', args.annot_stem,
'--refpanel', args.refpanel,
'main',
'--chrnum', '$LSB_JOBINDEX']
outfilepath = \
args.annot_stem + '.%I.cannot.log'
bsub.submit(
['python', '-u', paths.code + 'real/signed_preprocess.py'] + my_args,
outfilepath,
jobname='preprocess[1-22]')
def submit(args):
my_args = [
'--annot_stem', args.annot_stem, 'main', '--chrnum', '$LSB_JOBINDEX'
]
outfilepath = \
args.annot_stem + '.random.%I.creation.log'
bsub.submit(
['python', '-u', paths.code + 'munge/randomize_annot_signs.py'] +
my_args,
outfilepath,
jobname='randomize[1-22]',
debug=args.debug)
def submit(args):
my_args = ['--annot_stems', ' '.join(args.annot_stems),
'--sumstats_stem', args.sumstats_stem,
'--refpanel', args.refpanel,
'main',
'--chrnum', '$LSB_JOBINDEX']
outfilepath = \
results_filename(args.annot_stems, args.sumstats_stem,
chrnum='%I') + '.log'
bsub.submit(
['python', '-u', __file__] + my_args,
outfilepath,
jobname='run[1-22]', debug=args.debug)
def submit(args):
my_args = [
'--annot_stems', ' '.join(args.annot_stems), '--sumstats_stem',
args.sumstats_stem, '--refpanel', args.refpanel, 'main', '--chrnum',
'$LSB_JOBINDEX'
]
outfilepath = \
results_filename(args.annot_stems, args.sumstats_stem,
chrnum='%I') + '.log'
bsub.submit(['python', '-u', __file__] + my_args,
outfilepath,
jobname='run[1-22]',
debug=args.debug)
def submit_preprocess(self):
if not self.preprocess_submitted():
print(str(self), 'pre-processing')
my_args = ['--method_name', self.method(),
'preprocess'] + \
self.command_line_params()
outfilepath = self.path_to_preprocessed_data() + '.preprocessing.out'
bsub.submit(
['python', '-u', paths.code + 'methods/estimator_manager.py'] + my_args,
outfilepath,
jobname=self.preprocess_job_name(),
memory_GB=self.preprocess_memoryreq_GB())
self.declare_preprocess_submitted()
else:
print(str(self), ': pre-processing unnecessary')
def submit_beta(beta_num):
my_args = ['--sim_name', args.sim_name,
'main',
'--beta_num', str(beta_num),
'--sample_num', '$LSB_JOBINDEX']
outfilepath = \
sim.path_to_beta(beta_num) + \
'.sim_sumstats.%I.out'
bsub.submit(
['python', '-u', paths.code + 'sim/sim_sumstats.py'] + my_args,
outfilepath,
jobname='simsumstats' + str(beta_num) + '[1-' + str(sim.num_samples_per_beta) + ']',
# memory_GB=10.5)
memory_GB=13)
def submit_beta(beta_num):
my_args = [
'--sim_name', args.sim_name, 'main', '--beta_num',
str(beta_num), '--sample_num', '$LSB_JOBINDEX'
]
outfilepath = \
sim.path_to_beta(beta_num) + \
'.sim_sumstats.%I.out'
bsub.submit(
['python', '-u', paths.code + 'sim/sim_sumstats.py'] + my_args,
outfilepath,
jobname='simsumstats' + str(beta_num) + '[1-' +
str(sim.num_samples_per_beta) + ']',
# memory_GB=10.5)
memory_GB=13)
def submit(args):
e = sm.Experiment(args.exp_name)
for s in e.sims.values():
if hasattr(s, 'ignore'):
print('ignoring', s.name)
continue
print('submitting', s.name)
my_args = ['--exp-name', args.exp_name] + \
['main',
'--sim-name', s.name,
'--beta-num', '$LSB_JOBINDEX']
outfilename = s.root_folder(create=True) + '.sim_sumstats.%I'
bsub.submit(['python', '-u', __file__] + my_args,
outfilename,
# queue='medium', time_in_hours=40,
queue='short', time_in_hours=12,
jobname=s.name+'.simsumstats[1-{}]'.format(s.num_betas),
debug=args.debug)
def submit_preprocess(self, s, debug=False):
if not self.dependencies_satisfied(s):
print(str(self), 'pre-processing')
my_args = ['--method-name', self.method,
'--sim-name', s.name,
'preprocess'] + \
self.command_line_params()
outfilepath = self.refpanel.path + '.' + s.name + '.' + self.fsid() + \
'.preprocessing.out'
bsub.submit(
['python', '-u', paths.code + 'sim/methods/estimator_manager.py'] + my_args,
outfilepath,
jobname='preprocess-' + self.fsid() + '-' + s.name,
memory_GB=self.preprocess_memoryreq_GB,
debug=debug)
if not debug:
self.declare_preprocess_submitted(s)
else:
print(str(self), ': pre-processing unnecessary')
def submit(args):
e = sm.Experiment(args.exp_name)
for s in e.sims.values():
if hasattr(s, 'ignore'):
print('ignoring', s.name)
continue
print('submitting', s.name)
my_args = ['--exp-name', args.exp_name] + \
['main',
'--sim-name', s.name,
'--beta-num', '$LSB_JOBINDEX']
outfilename = s.root_folder(create=True) + '.sim_sumstats.%I'
bsub.submit(
['python', '-u', __file__] + my_args,
outfilename,
# queue='medium', time_in_hours=40,
queue='short',
time_in_hours=12,
jobname=s.name + '.simsumstats[1-{}]'.format(s.num_betas),
debug=args.debug)
def preprocess(self, s):
print('TruthRE is preprocessing', s.name,
'with refpanel=', self.params.refpanel)
print(self.params)
print('preprocessing', self.annotation.filestem())
for c in s.chromosomes:
if not os.path.exists(self.annotation.conv_filename(c, full=True)):
conv_command = [
'python', '-u', paths.code + 'acor/acor.py',
'--annot-chr', self.annotation.stem_chr,
'--bfile-chr', self.refpanel.bfile_chr,
'-fullconv',
'conv',
'--chroms', str(c)]
print(' '.join(conv_command))
outfilepath = self.annotation.filestem(c) + '.convbsub_out'
bsub.submit(
conv_command,
outfilepath,
jobname=self.params.annot_chr.replace('/','_') + \
',conv,chr='+str(c))
def submit_runs(self, sim, overwrite=False, debug=False):
#TODO: have it check whether there are more betas or more samples per beta,
# and then have it decide whether to submit the betas in parallel or in groups
# probably its easy to have the actual estimator manager be able to accept groups of
# betas
print('\n' + str(self), 'submitting', sim.name)
my_args = ['--method_name', self.method(),
'run',
'--sim_name', sim.name,
'--batch_num', '$LSB_JOBINDEX'] + \
self.command_line_params()
outfilepath = self.outfile_path(sim, '%I')
if all(os.path.exists(self.results_path_stem(sim, beta_num))
for beta_num in range(1, sim.num_betas+1)) and not overwrite:
print('submission unnecessary for', str(self))
else:
bsub.submit(
['python', '-u', paths.code + 'methods/estimator_manager.py'] + my_args,
outfilepath,
jobname=self.run_job_name(sim),
memory_GB=4,
debug=debug)
def preprocess(self, s):
print('LDSC is preprocessing', s.name, 'with refpanel=',
self.params.refpanel)
print(self.params)
for annot_chr in self.params.annot_chr.split(','):
a = pa.Annotation(paths.annotations + annot_chr)
for c in range(1, 23):
if not os.path.exists(a.ldscores_filename(c)):
ldscores_command = [
'python', '-u', paths.foreign + 'ldsc/ldsc.py', '--l2',
'--ld-wind-cm',
str(self.params.ld_window), '--bfile',
self.refpanel.bfile(c), '--annot',
a.annot_filename(c), '--out',
a.filestem(c)
]
print(' '.join(ldscores_command))
outfilepath = a.filestem(c) + '.ldscoresbsub_out'
bsub.submit(
ldscores_command,
outfilepath,
jobname=self.params.annot_chr.replace('/','_') + \
',ldcores,chr='+str(c))
