def bayes_major(self):
self = pickle.load(
open(
"/%s/%s_self_fitting.p" %
(self.output_directory, self.output_prefix), 'rb'))
logging.info('Run the algorithm for the second time ...')
ngene = 0
for (tgid, tginst) in self.allgenedict.iteritems():
#logging.info(tgid)
iteratenbem(tginst,
debug=False,
meanvarmodel=self.mrm,
restart=False,
size_factor=self.size_f,
beta1_prior_var=self.non_PPI_beta_prior_variance)
ngene += 1
for (tgid, tginst) in self.allgenedict.iteritems():
if len(tginst.w_estimate) == 0:
tginst.w_estimate = np.ones(len(tginst.sgrnaid))
pickle.dump(
self,
open(
"/%s/%s_self_bayes_major.p" %
(self.output_directory, self.output_prefix), 'wb'))
def bayes_iteration(self):
logging.info('Iteratioin...')
PPI_choice=[False,True]
for PPI in PPI_choice:
self=pickle.load(open("/%s/%s_self_constant_optimization.p" %(self.output_directory,self.output_prefix),'rb'))
self.PPI_prior=PPI
if self.PPI_diagnosis==False and self.PPI_prior==True:
pass
else:
self.outliers_removal=False
for (tgid,tginst) in self.allgenedict.iteritems():
iteratenbem(tginst,debug=False,meanvarmodel=self.mrm,restart=False,PPI_prior=self.PPI_prior,removeoutliers=self.outliers_removal,size_factor=self.size_f,beta1_prior_var=self.non_PPI_beta_prior_variance)
pickle.dump(self,open("/%s/%s_self_bayes_iteration_PPI_%s_outliers_removal_%s.p" %(self.output_directory,self.output_prefix,self.PPI_prior,self.outliers_removal),'wb'))
#base_index=np.where(~self.design_matrix[:,1:].any(axis=1))[0]
#transform_list=[1 if i in base_index else -1 for i in range(self.design_matrix.shape[0])]
#transform_matrix=np.matrix(transform_list)
for (tgid,tginst) in self.allgenedict.items():
bayes_selection(tginst,log_list=self.log_list,selection_constant=self.selection_constant)
self.outliers_removal=True
for (tgid,tginst) in self.allgenedict.iteritems():
iteratenbem(tginst,debug=False,meanvarmodel=self.mrm,restart=False,PPI_prior=self.PPI_prior,removeoutliers=self.outliers_removal,size_factor=self.size_f,beta1_prior_var=self.non_PPI_beta_prior_variance)
pickle.dump(self,open("/%s/%s_self_bayes_iteration_PPI_%s_outliers_removal_%s.p" %(self.output_directory,self.output_prefix,self.PPI_prior,self.outliers_removal),'wb'))
def bayes_init(self):
maxgene=np.inf
if self.negative_control==None:
self.allgenedict,self.invalid_gRNA_dict=read_gene_from_file(self.count_table,includesamples=self.include_samples,negative_control=self.negative_control)
else:
self.allgenedict,self.invalid_gRNA_dict,self.negative_control_gRNAs=read_gene_from_file(self.count_table,includesamples=self.include_samples,negative_control=self.negative_control)
# calculate the size factor
cttab_sel={}
for (geneid,gk) in self.allgenedict.iteritems():
sgid=gk.sgrnaid
sgreadmat=gk.nb_count.getT().tolist()
for i in range(len(sgid)):
cttab_sel[sgid[i]]=sgreadmat[i]
if hasattr(self,'norm_method'):
if self.norm_method!='none':
self.size_f=normalizeCounts(cttab_sel,method=self.norm_method,returnfactor=True,reversefactor=True,negative_control_gRNAs=self.negative_control_gRNAs)
else:
self.size_f=None
else:
self.size_f=normalizeCounts(cttab_sel,returnfactor=True,reversefactor=True)
logging.info('size factor: '+','.join([str(x) for x in self.size_f]))
#logging.info(self.design_matrix)
desmat=self.design_matrix
for (tgid,tginst) in self.allgenedict.iteritems():
#if tgid=="INO80B":
tginst.design_mat=desmat
iteratenbem(tginst,debug=False,estimateeff=False,alpha_val=0.05,size_factor=self.size_f)
tginst.w_estimate=[]
deviation(self.allgenedict)
self.non_PPI_beta_prior_variance=beta_non_PPI_prior_calculation(self.allgenedict)
pickle.dump(self,open("/%s/%s_self_bayes_init.p" %(self.output_directory,self.output_prefix),'wb'))
def bayes_iteration(self):
logging.info('Iteratioin...')
PPI_choice = [False, True]
for PPI in PPI_choice:
self = pickle.load(
open(
"/%s/%s_self_constant_optimization.p" %
(self.output_directory, self.output_prefix), 'rb'))
self.PPI_prior = PPI
if self.PPI_diagnosis == False and self.PPI_prior == True:
pass
else:
self.outliers_removal = False
for (tgid, tginst) in self.allgenedict.iteritems():
iteratenbem(
tginst,
debug=False,
meanvarmodel=self.mrm,
restart=False,
PPI_prior=self.PPI_prior,
removeoutliers=self.outliers_removal,
size_factor=self.size_f,
beta1_prior_var=self.non_PPI_beta_prior_variance)
pickle.dump(
self,
open(
"/%s/%s_self_bayes_iteration_PPI_%s_outliers_removal_%s.p"
% (self.output_directory, self.output_prefix,
self.PPI_prior, self.outliers_removal), 'wb'))
#base_index=np.where(~self.design_matrix[:,1:].any(axis=1))[0]
#transform_list=[1 if i in base_index else -1 for i in range(self.design_matrix.shape[0])]
#transform_matrix=np.matrix(transform_list)
for (tgid, tginst) in self.allgenedict.items():
bayes_selection(tginst,
log_list=self.log_list,
selection_constant=self.selection_constant)
self.outliers_removal = True
for (tgid, tginst) in self.allgenedict.iteritems():
iteratenbem(
tginst,
debug=False,
meanvarmodel=self.mrm,
restart=False,
PPI_prior=self.PPI_prior,
removeoutliers=self.outliers_removal,
size_factor=self.size_f,
beta1_prior_var=self.non_PPI_beta_prior_variance)
pickle.dump(
self,
open(
"/%s/%s_self_bayes_iteration_PPI_%s_outliers_removal_%s.p"
% (self.output_directory, self.output_prefix,
self.PPI_prior, self.outliers_removal), 'wb'))
def bayes_init(self):
maxgene = np.inf
if self.negative_control == None:
self.allgenedict, self.invalid_gRNA_dict = read_gene_from_file(
self.count_table,
includesamples=self.include_samples,
negative_control=self.negative_control)
else:
self.allgenedict, self.invalid_gRNA_dict, self.negative_control_gRNAs = read_gene_from_file(
self.count_table,
includesamples=self.include_samples,
negative_control=self.negative_control)
# calculate the size factor
cttab_sel = {}
for (geneid, gk) in self.allgenedict.iteritems():
sgid = gk.sgrnaid
sgreadmat = gk.nb_count.getT().tolist()
for i in range(len(sgid)):
cttab_sel[sgid[i]] = sgreadmat[i]
if hasattr(self, 'norm_method'):
if self.norm_method != 'none':
self.size_f = normalizeCounts(
cttab_sel,
method=self.norm_method,
returnfactor=True,
reversefactor=True,
negative_control_gRNAs=self.negative_control_gRNAs)
else:
self.size_f = None
else:
self.size_f = normalizeCounts(cttab_sel,
returnfactor=True,
reversefactor=True)
logging.info('size factor: ' + ','.join([str(x) for x in self.size_f]))
#logging.info(self.design_matrix)
desmat = self.design_matrix
for (tgid, tginst) in self.allgenedict.iteritems():
#if tgid=="INO80B":
tginst.design_mat = desmat
iteratenbem(tginst,
debug=False,
estimateeff=False,
alpha_val=0.05,
size_factor=self.size_f)
tginst.w_estimate = []
deviation(self.allgenedict)
self.non_PPI_beta_prior_variance = beta_non_PPI_prior_calculation(
self.allgenedict)
pickle.dump(
self,
open(
"/%s/%s_self_bayes_init.p" %
(self.output_directory, self.output_prefix), 'wb'))
def bayes_major(self):
self=pickle.load(open("/%s/%s_self_fitting.p" %(self.output_directory,self.output_prefix),'rb'))
logging.info('Run the algorithm for the second time ...')
ngene=0
for (tgid,tginst) in self.allgenedict.iteritems():
#logging.info(tgid)
iteratenbem(tginst,debug=False,meanvarmodel=self.mrm,restart=False,size_factor=self.size_f,beta1_prior_var=self.non_PPI_beta_prior_variance)
ngene+=1
for (tgid,tginst) in self.allgenedict.iteritems():
if len(tginst.w_estimate)==0:
tginst.w_estimate=np.ones(len(tginst.sgrnaid))
pickle.dump(self,open("/%s/%s_self_bayes_major.p" %(self.output_directory,self.output_prefix),'wb'))