def emit_results(self, betas, rescaled_betas, gold_standard, priors):
"""
Output result report(s) for workflow run.
"""
output_dir = os.path.join(self.input_dir, datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
os.makedirs(output_dir)
self.results_processor = ResultsProcessor(betas, rescaled_betas)
self.results_processor.summarize_network(output_dir, gold_standard, priors)
class BBSR_TFA_Workflow(WorkflowBase):
def run(self):
"""
Execute workflow, after all configuration.
"""
np.random.seed(self.random_seed)
self.mi_clr_driver = mi_R.MIDriver()
self.regression_driver = bbsr_python.BBSR_runner()
self.design_response_driver = design_response_translation.PythonDRDriver() #this is the python switch
self.get_data()
self.compute_common_data()
self.compute_activity()
betas = []
rescaled_betas = []
for idx, bootstrap in enumerate(self.get_bootstraps()):
print('Bootstrap {} of {}'.format((idx + 1), self.num_bootstraps))
X = self.activity.ix[:, bootstrap]
Y = self.response.ix[:, bootstrap]
print('Calculating MI, Background MI, and CLR Matrix')
if 0 == rank:
(self.clr_matrix, self.mi_matrix) = self.mi_clr_driver.run(X, Y)
kvs.put('mi %d'%idx, (self.clr_matrix, self.mi_matrix))
else:
(self.clr_matrix, self.mi_matrix) = kvs.view('mi %d'%idx)
print('Calculating betas using BBSR')
ownCheck = utils.own(kvs, rank, chunk=25)
current_betas,current_rescaled_betas = self.regression_driver.run(X, Y, self.clr_matrix, self.priors_data,kvs,rank,ownCheck)
if rank: continue
betas.append(current_betas)
rescaled_betas.append(current_rescaled_betas)
self.emit_results(betas, rescaled_betas, self.gold_standard, self.priors_data)
def compute_activity(self):
"""
Compute Transcription Factor Activity
"""
print('Computing Transcription Factor Activity ... ')
TFA_calculator = TFA(self.priors_data, self.design, self.half_tau_response)
self.activity = TFA_calculator.compute_transcription_factor_activity()
def emit_results(self, betas, rescaled_betas, gold_standard, priors):
"""
Output result report(s) for workflow run.
"""
if 0 == rank:
output_dir = os.path.join(self.input_dir, datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
os.makedirs(output_dir)
self.results_processor = ResultsProcessor(betas, rescaled_betas)
self.results_processor.summarize_network(output_dir, gold_standard, priors)
class BBSR_TFA_Workflow(WorkflowBase):
def run(self):
"""
Execute workflow, after all configuration.
"""
np.random.seed(self.random_seed)
self.mi_clr_driver = mi_R.MIDriver()
self.regression_driver = bbsr_R.BBSR_driver()
#self.design_response_driver = design_response_R.DRDriver()
self.design_response_driver = design_response_translation.PythonDRDriver(
) #this is the python switch
self.get_data()
self.compute_common_data()
self.compute_activity()
betas = []
rescaled_betas = []
for idx, bootstrap in enumerate(self.get_bootstraps()):
print('Bootstrap {} of {}'.format((idx + 1), self.num_bootstraps))
X = self.activity.ix[:, bootstrap]
Y = self.response.ix[:, bootstrap]
print('Calculating MI, Background MI, and CLR Matrix')
(self.clr_matrix, self.mi_matrix) = self.mi_clr_driver.run(X, Y)
print('Calculating betas using BBSR')
current_betas, current_rescaled_betas = self.regression_driver.run(
X, Y, self.clr_matrix, self.priors_data)
betas.append(current_betas)
rescaled_betas.append(current_rescaled_betas)
self.emit_results(betas, rescaled_betas, self.gold_standard,
self.priors_data)
def compute_activity(self):
"""
Compute Transcription Factor Activity
"""
print('Computing Transcription Factor Activity ... ')
TFA_calculator = TFA(self.priors_data, self.design,
self.half_tau_response)
self.activity = TFA_calculator.compute_transcription_factor_activity()
def emit_results(self, betas, rescaled_betas, gold_standard, priors):
"""
Output result report(s) for workflow run.
"""
output_dir = os.path.join(
self.input_dir,
datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
os.makedirs(output_dir)
self.results_processor = ResultsProcessor(betas, rescaled_betas)
self.results_processor.summarize_network(output_dir, gold_standard,
priors)
def emit_results(self, betas, rescaled_betas, gold_standard, priors):
"""
Output result report(s) for workflow run.
"""
output_dir = os.path.join(self.input_dir, datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S'))
os.makedirs(output_dir)
self.results_processor = ResultsProcessor(betas, rescaled_betas)
self.results_processor.summarize_network(output_dir, gold_standard, priors)
{"tf_seed": 252356, "np_seed": 703889},
{"tf_seed": 343053, "np_seed": 999360},
{"tf_seed": 743746, "np_seed": 67440}
]
# Load experiment specified in system args
exp_file = "base_network.yml"
printt("Running Experiment File: {}".format(exp_file))
f_name = exp_file.split(".")[0] if "." in exp_file else exp_file
exp_specs = yaml.load(open(os.path.join(experiment_directory, exp_file), 'r').read())
# setup output directory
outdir = os.path.join(output_directory, f_name)
if not os.path.exists(outdir):
os.mkdir(outdir)
results_processor = ResultsProcessor()
# create results log
results_log = os.path.join(outdir, "results.csv")
with open(results_log, 'w') as f:
f.write("")
# write experiment specifications to file
with open(os.path.join(outdir, "experiment.yml"), 'w') as f:
f.write("{}\n".format(yaml.dump(exp_specs)))
# pre-process to include residue indices
def preProcessData(data):
num_complex = len(data)
for idx_complex in range(num_complex):
