def randomMutation(
self,
pos=None,
n_mut=[1, 1, 1, 1, 2, 2, 2, 2, 3, 4, 5, 6, 20, 30, 50, 100, 200],
mutable_region=None):
if mutable_region == None:
if self.mutable_region == None:
mutable_region = self.solution.mutable_region
else:
mutable_region = self.mutable_region
logger.debug('Mutable region: {}'.format(mutable_region))
new_seq = Functions.randomMutationOperator(
self.solution.sequence,
self.solution.keep_aa,
mutable_region,
self.solution.cds_region,
cai_table=self.solution.cai_table,
pos=pos,
n_mut=n_mut)
return Solution.Solution(sol_id=str(uuid4().int),
sequence=new_seq,
project_dir=self.solution.project_dir,
cds_region=self.solution.cds_region,
keep_aa=self.solution.keep_aa,
mutable_region=self.solution.mutable_region,
parent=self.solution,
design=self.solution.designMethod)
def set_scores(self,
scoring_function=Functions.analyze_duplex_mfe_rnafold):
self.scores.update(
Functions.appendLabelToDict(
scoring_function(filename=self.duplexFile,
project_dir=self.solution.project_dir),
self.label))
def set_scores(self,
scoring_function=Functions.analyze_duplex_structure_rnafold
):
self.scores.update(
Functions.appendLabelToDict(
scoring_function(seq1=self.rnaMolecule1seq,
seq2=self.rnaMolecule2seq,
filename=self.duplexFile,
project_dir=self.solution.project_dir),
self.label))
def set_scores(self, scoring_function=Functions.analyze_duplex_structure):
self.scores.update(
Functions.appendLabelToDict(
scoring_function(self.rnaMolecule1seq, self.rnaMolecule2seq,
self.duplexFile), self.label))
pass
def set_scores(self, scoring_function=Functions.analyze_duplex_mfe):
self.scores.update(
Functions.appendLabelToDict(scoring_function(self.duplexFile),
self.label))
def set_scores(self, scoring_function=Functions.analyze_pwm_score):
self.scores = Functions.appendLabelToDict(
scoring_function(self.sequence, self.pwm), self.label)
def set_scores(self, scoring_function=Functions.analyze_structure_prob):
#compute structure
self.scores.update(
Functions.appendLabelToDict(
scoring_function(self.sequence, self.structurefile,
self.window, self.acc_region), self.label))
def set_scores(self, scoring_function=Functions.analyze_structure_ds):
self.scores.update(
Functions.appendLabelToDict(scoring_function(self.structurefile),
self.label))
def set_scores(self, scoring_function=Functions.analyze_structure_mfe):
self.scores.update(
Functions.appendLabelToDict(
scoring_function(filename=self.structurefile,
project_dir=self.solution.project_dir),
self.label))
def set_scores(self, scoring_function=Functions.analyze_ntcontent):
self.scores = Functions.appendLabelToDict(
scoring_function(self.sequence), self.label)
def validateSolution(self, solution):
'''
Solution validation tests
'''
return True
if solution.sequence == None:
return 0
valid = True
e_type=None
variable_region = solution.sequence[solution.mutable_region[0]:(solution.mutable_region[-1]+1)]
#No Promoters
promoter_putative_region = solution.sequence[(solution.mutable_region[0]-30):(solution.mutable_region[-1]+31)]
(score, position, spacer) = Functions.look_for_promoters(promoter_putative_region)
if score >= 0.3990166: #0.95 percentile for Promoter PWM scores
valid = False
position = (solution.mutable_region[0]-30) + position
e_type = "prom"
sys.stderr.write("SolutionValidator: High Promoter score\n")
#No RBS
rbs_putative_region = solution.sequence[(solution.mutable_region[0]-12):(solution.mutable_region[-1]+11)]
(score, position) = Functions.look_for_RBS(rbs_putative_region)
if score >= 0.820515: #0.95 percentile for RBS PWM scores
valid = False
position = (solution.mutable_region[0]-12) + position
e_type = "rbs"
sys.stderr.write("SolutionValidator: High RBS score: "+str(score)+" - "+str(position)+"\n")
#No Terminator
term_putative_region = solution.sequence[(solution.mutable_region[0]-30):(solution.mutable_region[-1]+31)]
score = Functions.look_for_terminators(term_putative_region)
if score >= 90: #90% confidence from transtermHP
e_type = "term"
valid = False
sys.stderr.write("SolutionValidator: High Terminator score\n")
#No stop codon
for i in range(0,len(variable_region),3):
if codon2aa_table[variable_region[i:i+3]]=='stop':
sys.stderr.write("SolutionValidator: Stop codon found\n")
e_type = "stopcodon"
valid = False
position = solution.mutable_region[0]+i
break
#No restriction enzymes
rsite_putative_region = solution.sequence[(solution.mutable_region[0]-6):(solution.mutable_region[-1])]
if 'ggtacc' in rsite_putative_region:
e_type = "rsite"
sys.stderr.write("SolutionValidator: Restriction enzyme found\n")
position = (solution.mutable_region[0]-6)+rsite_putative_region.index('ggtacc')
valid = False
if 'ggatcc' in rsite_putative_region:
e_type = "rsite"
sys.stderr.write("SolutionValidator: Restriction enzyme found\n")
position = (solution.mutable_region[0]-6)+rsite_putative_region.index('ggatcc')
valid = False
#No bases run of more than 5nt
repeat_putative_region = solution.sequence[(solution.mutable_region[0]-6):(solution.mutable_region[-1]+7)]
for b_run in ('aaaaaa','tttttt','gggggg','cccccc'):
if b_run in repeat_putative_region:
sys.stderr.write("SolutionValidator: Bases run for more than 5 found\n")
valid = False
position = (solution.mutable_region[0]-6) + repeat_putative_region.index(b_run)
e_type = "repeats"
solution.valid = valid
if valid == True:
return (valid,None,None)
else:
return (valid,position,e_type)