def checkGCInRegions(sSeq, lCGMap): dGCResults = dict() # Loop that loops over each specified segment for iBegin, iEndBy in lCGMap: sSegPiece = sSeq[iBegin:iEndBy] dGCResults[(iBegin, iEndBy)] = getGCcontent(sSegPiece) return dGCResults
def processCompleteSpecification(dCompleteSpec):
# Setup initial variables
lDNASpecification = dCompleteSpec['Feature Specification']
dForbiddenSeqs = dCompleteSpec['Forbidden Sequences']
lGCMap = dCompleteSpec['GC Optimization Map']
fTargetGC = dCompleteSpec['GC Target Fraction']
iIterations = dCompleteSpec['Optimization Attempts']
# Print info about the job
print('='*100)
print('%s Job Info %s' % ('='*45, '='*45))
print('='*100)
print('Note: DNA specification name: %s' % dCompleteSpec['Specification Name'])
print('Note: Type of job: %s' % 'GVVGCO (Gneration, Verification, Validation and GC Optimization)')
print('Note: Feature map contains %i features:' % len(lDNASpecification))
for iFeature, dFeature in enumerate(lDNASpecification):
print(' %i: %s: ' % (iFeature, dFeature['name']) )
print(' SeqType: %s' % ('Generator' if hasattr(dFeature['seq'], '__call__') else 'Specified'), end='')
if not hasattr(dFeature['seq'], '__call__'): print(', SeqLenght: %i' % len(dFeature['seq']), end='')
print(', Mutable: %s' % dFeature['mutable'])
print(' MayContain:%s' % (' None' if not dFeature['maycontain'] else ''), end='')
sInfront = ''
for sMayContain in dFeature['maycontain']:
print ('%s %s' % (sInfront, sMayContain), end='')
sInfront = ','
print()
print('Note: Forbidden sequences:')
lForbiddenSeqNames = list(dForbiddenSeqs.keys())
lForbiddenSeqNames.sort()
for sFSeqName in lForbiddenSeqNames:
print(' %s: %s' % (sFSeqName, dForbiddenSeqs[sFSeqName]))
print('Note: Target GC contents: %f%%' % (fTargetGC*100))
print('Note: Optimize GC contents of the folowing regions(%i):' % (len(lGCMap)))
for iRegion, (iRegBegin, iRegEndBy) in enumerate(lGCMap):
if not iRegEndBy: iRegEndBy = 0
print(' Region %i @[%i:%i]' % (iRegion, iRegBegin, iRegEndBy))
print('Note: Number of optimization attempts: %i' % iIterations)
# Setup some stuff to catch prints that would normaly happen to early (i know its not nice to do it this way :P)
oStdoutOld = sys.stdout # Store default sdtout pipe
oPrintCatcher = PrintCatcher()
sys.stdout = oPrintCatcher # Start catching print output
# Run the DNA creation, verification and optimization function
tTemp = makeAndGCOptimiseSpecDNA(lDNASpecification, dForbiddenSeqs, lGCMap, fTargetGC, iIterations, bVerbose=False)
# Restore original stdout (and thus stop catching output from the print function)
sys.stdout = oStdoutOld
# If this was a success than display the results
if tTemp:
sBestSequence, fBestAvgGCResult, dBestGCRegionResult, lBestFeatureMap, iBestResultAtIteration = tTemp
print('='*100)
print('%s Result - Success! :D %s' % ('='*39, '='*39))
print('='*100)
print('Note: Best result found at iteration: %i' % iBestResultAtIteration)
print('Note: Optimised GC contents of the folowing regions(%i):' % (len(dBestGCRegionResult)))
for (iRegBegin, iRegEndBy), fResult in dBestGCRegionResult.items():
if not iRegEndBy: iRegEndBy = 0
print(' GC content @[%i:%i]: %f%%' % (iRegBegin, iRegEndBy, fResult*100))
print('Note: Non-weighted regional average CG contents: %f%%' % (fBestAvgGCResult[0]*100))
print('Note: Weighted regional average CG contents: %f%%' % (fBestAvgGCResult[1]*100))
print('Note: Feature map contains features(%i):' % len(lBestFeatureMap))
for iFeature, (iRegBegin, iRegEndBy) in enumerate(lBestFeatureMap):
print(' %i @[%i:%i]: %s (GC: %f%%)' % (iFeature, iRegBegin, iRegEndBy, lDNASpecification[iFeature]['name'], getGCcontent(sBestSequence[iRegBegin:iRegEndBy])))
print('Note: Overall GC contents: %f%%' % getGCcontent(sBestSequence))
print('Note: DNA sequence:')
prettyPrintDNA(sBestSequence, True)
print('Note: See final verification procedure for more information (displayed below)')
print('%s Reverifying Result %s' % ('='*40, '='*40))
makeDNASpecCompliant(sBestSequence, lBestFeatureMap, lDNASpecification, compileForbiddenSeqs(dForbiddenSeqs), bCheckOnly=True)
print('='*100)
# Else it was no success so than display why it resulted in a failure
else:
print('='*100)
print('%s Result - Failure! :( %s' % ('='*39, '='*39))
print('='*100)
print('Note: Procces ended in a warning because the DNA could not possibly be made valid!')
print('Note: See final verification procedure for more information (displayed below)')
print('%s Reverifying Result %s' % ('='*40, '='*40))
print(oPrintCatcher.sContent, end='')
print('='*100)