def CalcPotentialByEmpSI(predDistMatrix, userRef, largestDistance=20, sequence=None, minPotential=-20., maxPotential=20.):
f=open(userRef, 'rb')
refData = cPickle.load(f)
f.close()
potentials = dict()
for response, prdProb in predDistMatrix.iteritems():
labelName, labelType, _ = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
continue
if not conifg.IsDiscreteLabel(labelType):
continue
refProb = refData[response][0]
potential = - np.log ( predProb / refProb )
rc = largestDistance
cutoff = config.GetCutoffs(response)
lastDistBin = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
lastCol = potential[:, :, lastDistBin]
potential = potential - lastCol
potential[:, :, lastDistBin: ] =0
CheckPotentialValues(potential)
potentials[response] = potential
return potentials
def CalcDistOriPotential(predData, labelNames=['CaCa', 'CbCb', 'NO'] + ['Ca1Cb1Cb2Ca2','N1Ca1Cb1Cb2','Ca1Cb1Cb2'], distPotType='DFIRE', param4Potential=1.61, largestDistance=18, useWeight4Dist=True, useRef4Ori=True, useWeight4Ori=True, minPotential=-30, maxPotential=30):
assert distPotType.upper() in ['DFIRE', 'DOPE']
predProbMatrix, labelWeight, labelDistribution = predData
validDistribution = dict()
validLabelWeight = dict()
validLabelDistribution = dict()
existingLabelNames = []
for response, pred in predProbMatrix.iteritems():
labelName,_, _ = config.ParseResponse(response)
if labelName not in labelNames:
continue
existingLabelNames.append(labelName)
validDistribution[response] = pred
validLabelWeight[response] = labelWeight[response]
validLabelDistribution[response] = labelDistribution[response]
missingLabelNames = list(set(labelNames) - set(existingLabelNames))
if len(missingLabelNames)>0:
print 'WARNING: the predicted probability file does not have information for the following label names: ', missingLabelNames
pairPotential = dict()
validProb = dict()
if distPotType == 'DOPE':
distPotential, distValidProb = CalcPotentialByDOPE(validDistribution, largestDistance=rc, rgScale=param4Potential, useWeight=useWeight4Dist, minPotential=minPotential, maxPotential=maxPotential)
else:
distPotential, distValidProb = CalcPotentialByDFIRE(validDistribution, alpha=param4Potential, largestDistance=largestDistance, useWeight=useWeight4Dist, minPotential=minPotential, maxPotential=maxPotential)
pairPotential.update(distPotential)
validProb.update(distValidProb)
oriPotential, oriValidProb = CalcOrientationPotential(validDistribution, useRef=useRef4Ori, useWeight=useWeight4Ori, labelWeight=validLabelWeight, labelDistribution=validLabelDistribution, minPotential=minPotential, maxPotential=maxPotential)
pairPotential.update(oriPotential)
validProb.update(oriValidProb)
cutoffs = dict()
for response in pairPotential.keys():
cutoffs[response] = config.GetCutoffs(response)
return pairPotential, cutoffs, validProb, distPotential, oriPotential
def CalcPotentialByEmpSD(predDistMatrix, userRef, largestDistance=20, sequence=None, minPotential=-20., maxPotential=20.):
f=open(userRef, 'rb')
refData = cPickle.load(f)
f.close()
potentials = dict()
for response, predProb in predDistMatrix.iteritems():
labelName, labelType, _ = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
continue
if not conifg.IsDiscreteLabel(labelType):
continue
refProbList = refData[response][1]
length = predProb.shape[0]
if length < 400:
refProbs = [ ref for sz, freq, ref in refProbList if sz<=1.3*length and sz>=length/1.3 ]
else:
refProbs = [ ref for sz, freq, ref in refProbList if sz>=350 ]
print '#refProbMatrix: ', len(refProbs), ' for proteins with length= ', length
refProb = np.average(refProbs, axis=0)
potential = - np.log ( predProb / refProb )
rc = largestDistance
cutoff = config.GetCutoffs(response)
lastDistBin = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
lastCol = potential[:, :, lastDistBin]
potential = potential - lastCol
potential{;, :, lastDistBin: ] = 0
CheckPotentialValues(potential)
potentials[response] = potential
return potentials
def CalcPotentialBySimuRW(predDistMatrix, refFile, largestDistance=20, sequence=None, useWeight=False, minPotential=-30., maxPotential=30.):
f=open(refFile, 'rb')
refData = cPickle.load(f)
f.close()
potentials = dict()
for response in predDistMatrix.keys():
labelName, labelType, _ = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
#print 'WARNING: unsupported response for SimuRW potential: ', response
continue
if not conifg.IsDiscreteLabel(labelType):
continue
predProb = predDistMatrix[response]
## the first row of refProb corresponds to offset=1
refProb = refData[response]
if labelName != 'CbCb':
print 'distance label name not supported yet: ', labelName
exit(1)
if not subType.endswith('34C'):
print 'distance label type not supported yet: ', subType
exit(1)
cutoff = config.GetCutoffs(response)
length = predProb.shape[0]
numLabels = predProb.shape[2]
assert numLabels == refProb.shape[1]
## maxAllowedDist[offset] is the maximum physically feasible distance between two Cb atoms when their sequence separation is equal to offset
maxAllowedDist = [ (offset * 3.8 + 3.06) for offset in range(length) ]
maxAllowedDist[0] = 0
eps = 0.00001
maxAllowedDist[2] = 10.5 - eps
maxAllowedDist[3] = 13.0 - eps
maxAllowedDist[4] = 15.5 - eps
maxAllowedDist[5] = 17.5 - eps
maxAllowedDist[6] = 19.5 - eps
potential = np.zeros_like(predProb)
for i in range(0, length):
for j in range(i+2, length):
offset = j-i
## find the distance bin into which the maxAllowedDist falls
lastDistBin = DistanceUtils.LabelsOfOneDistance(maxAllowedDist[offset], cutoff)
if lastDistBin < (numLabels - 1):
## merge the pred prob and ref prob in the bins from lastDistBin to the end
pred = predProb[i, j, : lastDistBin+1]
ref = refProb[offset-1][:lastDistBin+1]
potential[i, j, :lastDistBin+1] = -np.log( pred / ref )
potential[i, j, lastDistBin+1: ] = maxPotential
else:
## determine the last distance bin
rc = min(cutoff[-1], largestDistance) - 0.001
if (rc<10.0):
print 'ERROR: the largest distance cutoff for SimuRW is too small: ', rc
exit(1)
rc_index = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
refProbLen = refProb.shape[0]
#idx4rc = numLabels - 2
potential[i, j] = -np.log( predProb[i, j] / refProb[min(offset, refProbLen) -1 ] )
potential[i, j] -= potential[i, j, rc_index]
potential[i, j, rc_index + 1: ] = 0
## only valid for symmetric atom pairs
potential[j, i] = potential[i, j]
if useWeigt and subType.endswith('Plus'):
potential *= (1-predProb[:, :, -1])
CheckPotentialValues(potential)
potentials[response] = potential
return potentials
def CalcPotentialByDOPE(predDistMatrix, largestDistance=20, rgScale=1., useWeight=False, minPotential=-30., maxPotential=30.):
potentials = dict()
validProbs = dict()
for response in predDistMatrix.keys():
labelName, labelType, subType = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
#print 'WARNING: unsupported response for DOPE potential: ', response
continue
if not conifg.IsDiscreteLabel(labelType):
continue
cutoff = config.GetCutoffs(response)
## determine the last distance bin
rc = min(cutoff[-1], largestDistance) - 0.001
if (rc<10.0):
print 'ERROR: the largest distance cutoff for DOPE is too small: ', rc
exit(1)
rc_index = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
binwidths = [ d2 - d1 for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
bincenters = [ (d2 + d1)/2. for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
## a is the radius of reference sphere and rg is the estimated radius of gyration
length = predDistMatrix[response].shape[0]
rg = 0.395*length**(3./5)+7.257
a = np.sqrt(5./3) * rg * rgScale
""" calculate n(r,a) defined in the DOPE paper. Below is the original formulation.
## rc is the upper bound of distance between two atoms
rc = bincenters[-1]
if rc <= 2*a:
#nra = 6. * np.square(bincenters * (bincenters - 2*a)) * (bincenters + 4*a) / np.power(rc,3) /(np.power(rc, 3) - 18 * np.square(a)*rc + 32 * np.power(a, 3))
else:
#nra = 3* np.square(bincenters * (bincenters - 2*a)) * (bincenters + 4*a) / 16. / np.power(a, 6)
"""
## calculate n(r,a) described in the DOPE paper. Ignore the constant factor and the denominator since they are same for all distance bins
nra = np.square(bincenters * (bincenters - 2*a)) * (bincenters + 4*a)
def CalcApproxRefPot(idx=0):
points = np.arange(cutoff[idx] + 0.5/2, cutoff[idx+1], 0.5)
values = np.square(points * (points - 2*a)) * (points + 4*a)
tmpNra = np.average(values)
return tmpNra
## get a more accurate estimation of nra for the first several bins if their binwidth is > 0.5
for i in range(len(binwidths)):
if binwidths[i] >= 1:
nra[i] = CalcApproxRefPot(i)
## calculate reference potential defined as log (nra(r)/nra(rc)) + log(\delta r/ \delta rc)
## \delta(r) is equal to binwidths
refPot = np.log( nra / nra[rc_index] * binwidths / binwidths[rc_index] )
## calculate the observed potential defined as log( p(r) /p(rc) ) where p(r) is the predicted distance probability
predProb = predDistMatrix[response]
predProbRC = predProb[:, :, rc_index : rc_index+1]
obsPot = np.log(predProb / predProbRC)
## calculate the final potential, which is the difference between reference and observed potential
potential = np.zeros_like(predDistMatrix[response])
potential[:, :, :rc_index ] = refPot[: rc_index] - obsPot[:, :, :rc_index]
if subType.endswith('Plus'):
validProb = 1 - predProb[:, :, -1]
else:
validProb = np.ones((predProb.shape[0], predProb.shape[1]), dtype=np.float32)
##if useWeight and the prob of disroder exists, adjust potential by prob of not beining in disorder status
if useWeight and subType.endswith('Plus'):
potential *= validProb[:, :, np.newaxis]
## remove the potential for the last distance bin, which corresponds to disorder status
if subType.endswith('Plus'):
potential = potential[:, :, :-1]
CheckPotentialValues(m=potential)
potentials[response] = potential.astype(np.float32)
validProbs[response] = validProb.astype(np.float32)
return potentials, validProbs
def CalcPotentialByDFIRE(predDistMatrix, alpha=1.61, largestDistance=18, useWeight=False, minPotential=-30, maxPotential=30):
potentials = dict()
## validProbs saves the prob of one atom/residue pair likely have valid coordinates
validProbs = dict()
for response in predDistMatrix.keys():
labelName, labelType, subType = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
#print 'WARNING: unsupported response for DFIRE potential: ', response
continue
if not config.IsDiscreteLabel(labelType):
print 'WARNING: the distance label is not discrete: ', response
continue
cutoff = config.GetCutoffs(response)
## determine the last distance bin
rc = min(cutoff[-1], largestDistance) - 0.001
if (rc<10.0):
print 'ERROR: the largest distance cutoff for DFIRE is too small: ', rc
exit(1)
rc_index = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
binwidths = [ d2 - d1 for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
bincenters = [ (d2 + d1)/2. for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
## calculate reference potential defined as alpha*log (r/rc) + log(\delta r/ \delta rc)
## \delta(r) is binwidths and r is the bincenters
refPot = alpha * np.log( bincenters / bincenters[rc_index]) + np.log( binwidths / binwidths[rc_index] )
## idx is the index for a bin
def CalcApproxRefPot(idx=0):
points = np.arange(cutoff[idx] + 0.5/2, cutoff[idx+1], 0.5)
values = np.power(points / bincenters[rc_index], alpha)
avg = np.average(values)
tmpRefPot = np.log(avg) + np.log( binwidths[idx] / binwidths[rc_index] )
return tmpRefPot
## get a more accurate estimation of reference for the bin with a large width
for i in range(len(binwidths)):
if binwidths[i] >= 1:
refPot[i] = CalcApproxRefPot(i)
## calculate the observed potential defined as log( p(r) /p(rc) ) where p(r) is the predicted distance probability
predProb = predDistMatrix[response]
predProbRC = predProb[:, :, rc_index : rc_index+1]
#obsPot = np.log(predProb / (sys.float_info.min + predProbRC))
obsPot = np.log(predProb / predProbRC)
## calculate the final potential, which is the difference between reference potential and observed potential
potential = np.zeros_like(predDistMatrix[response])
potential[:, :, :rc_index ] = refPot[: rc_index] - obsPot[:, :, :rc_index]
if subType.endswith('Plus'):
validProb = 1 - predProb[:, :, -1]
else:
validProb = np.ones((predProb.shape[0], predProb.shape[1]), dtype=np.float32)
##if useWeight=True and the prob of being disorder exists, adjust potential by the prob of not being in disorder status
if useWeight and subType.endswith('Plus'):
potential *= validProb[:, :, np.newaxis]
## remove the potential for the last distance bin, which corresponds to disorder status
if subType.endswith('Plus'):
potential = potential[:, :, :-1]
CheckPotentialValues(m=potential)
potentials[response] = potential.astype(np.float32)
validProbs[response] = validProb.astype(np.float32)
return potentials, validProbs
def CalcPotentialByDFIRE(predDistMatrix, alpha=1.61, largestDistance=15, minPotential=-20, maxPotential=20):
potentials = dict()
for response in predDistMatrix.keys():
labelName, labelType, subType = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
print 'WARNING: unsupported response for DFIRE potential: ', response
continue
if not conifg.IsDiscreteLabel(labelType):
continue
cutoff = config.GetCutoffs(response)
## determine the last distance bin
rc = min(cutoff[-1], largestDistance) - 0.001
if (rc<10.0):
print 'ERROR: the largest distance cutoff for DFIRE is too small: ', rc
exit(1)
rc_index = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
binwidths = [ d2 - d1 for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
bincenters = [ (d2 + d1)/2. for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
## calculate reference potential defined as alpha*log (r/rc) + log(\delta r/ \delta rc)
## \delta(r) is binwidths and r is the bincenters
refPot = alpha * np.log( bincenters / bincenters[rc_index]) + np.log( binwidths / binwidths[rc_index] )
## idx is the index for binwidth
def CalcApproxRefPot(idx=0):
points = np.arange(cutoff[idx] + 0.5/2, cutoff[idx+1], 0.5)
values = np.power(points / bincenters[rc_index], alpha)
avg = np.average(values)
tmpRefPot = np.log(avg) + np.log( binwidths[idx] / binwidths[rc_index] )
return tmpRefPot
## get a more accurate estimation of reference for the first bin
[ refPot[i] = CalcApproxRefPot(i) for i in range(len(binwidths)) if binwdiths[i] >= 1 ]
## calculate the observed potential defined as log( p(r) /p(rc) ) where p(r) is the predicted distance probability
predProb = predDistMatrix[response]
predProbRC = predProb[:, :, rc_index : rc_index+1]
obsPot = np.log(predProb / predProbRC)
## calculate the final potential, which is the difference between reference potential and observed potential
potential = np.zeros_like(predDistMatrix[response])
potential[:, :, :rc_index ] = refPot[: rc_index] - obsPot[:, :, :rc_index]
CheckPotentialValues(m=potential)
potentials[response] = potential
return potentials
def CalcPotentialByDOPE(predDistMatrix, largestDistance=20, rgScale=1., minPotential=-20., maxPotential=20.):
potentials = dict()
for response in predDistMatrix.keys():
labelName, labelType, subType = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
print 'WARNING: unsupported response for DOPE potential: ', response
continue
if not conifg.IsDiscreteLabel(labelType):
continue
cutoff = config.GetCutoffs(response)
## determine the last distance bin
rc = min(cutoff[-1], largestDistance) - 0.001
if (rc<10.0):
print 'ERROR: the largest distance cutoff for DOPE is too small: ', rc
exit(1)
rc_index = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
binwidths = [ d2 - d1 for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
bincenters = [ (d2 + d1)/2. for d1, d2 in zip(cutoff[:-1], cutoff[1:]) ]
## a is the radius of reference sphere and rg is the estimated radius of gyration
length = predDistMatrix[response].shape[0]
rg = 0.395*length**(3./5)+7.257
a = np.sqrt(5./3) * rg * rgScale
""" calculate n(r,a) defined in the DOPE paper. Below is the original formulation.
## rc is the upper bound of distance between two atoms
rc = bincenters[-1]
if rc <= 2*a:
#nra = 6. * np.square(bincenters * (bincenters - 2*a)) * (bincenters + 4*a) / np.power(rc,3) /(np.power(rc, 3) - 18 * np.square(a)*rc + 32 * np.power(a, 3))
else:
#nra = 3* np.square(bincenters * (bincenters - 2*a)) * (bincenters + 4*a) / 16. / np.power(a, 6)
"""
## calculate n(r,a) described in the DOPE paper. Ignore the constant factor and the denominator since they are same for all distance bins
nra = np.square(bincenters * (bincenters - 2*a)) * (bincenters + 4*a)
def CalcApproxRefPot(idx=0):
points = np.arange(cutoff[idx] + 0.5/2, cutoff[idx+1], 0.5)
values = np.square(points * (points - 2*a)) * (points + 4*a)
tmpNra = np.average(values)
return tmpNra
## get a more accurate estimation of nra for the first several bins if their binwidth is > 0.5
[ nra[i] = CalcApproxRefPot(i) for i in range(len(binwidths)) if binwidths[i] >= 1 ]
## calculate reference potential defined as log (nra(r)/nra(rc)) + log(\delta r/ \delta rc)
## \delta(r) is equal to binwidths
refPot = np.log( nra / nra[rc_index] * binwidths / binwidths[rc_index] )
## calculate the observed potential defined as log( p(r) /p(rc) ) where p(r) is the predicted distance probability
predProb = predDistMatrix[response]
predProbRC = predProb[:, :, rc_index : rc_index+1]
obsPot = np.log(predProb / predProbRC)
## calculate the final potential, which is the difference between reference and observed potential
potential = np.zeros_like(predDistMatrix[response])
potential[:, :, :rc_index ] = refPot[: rc_index] - obsPot[:, :, :rc_index]
CheckPotentialValues(m=potential)
potentials[response] = potential
return potentials
def CalcPotentialBySimuRW(predDistMatrix, userRef, largestDistance=20, sequence=None, minPotential=-20., maxPotential=20.):
f=open(userRef, 'rb')
refData = cPickle.load(f)
f.close()
potentials = dict()
for response in predDistMatrix.keys():
labelName, labelType, _ = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
print 'WARNING: unsupported response for SimuRW potential: ', response
continue
if not conifg.IsDiscreteLabel(labelType):
continue
predProb = predDistMatrix[response]
## the first row of refProb corresponds to offset=1
refProb = refData[response]
if labelName != 'CbCb':
print 'distance label name not supported yet: ', labelName
exit(1)
if not subType.endswith('34C'):
print 'distance label type not supported yet: ', subType
exit(1)
cutoff = config.GetCutoffs(response)
length = predProb.shape[0]
numLabels = predProb.shape[2]
assert numLabels == refProb.shape[1]
## maxAllowedDist[offset] is the maximum physically feasible distance between two Cb atoms when their sequence separation is equal to offset
maxAllowedDist = [ (offset * 3.8 + 3.06) for offset in range(length) ]
maxAllowedDist[0] = 0
eps = 0.00001
maxAllowedDist[2] = 10.5 - eps
maxAllowedDist[3] = 13.0 - eps
maxAllowedDist[4] = 15.5 - eps
maxAllowedDist[5] = 17.5 - eps
maxAllowedDist[6] = 19.5 - eps
potential = np.zeros_like(predProb)
for i in range(0, length):
for j in range(i+2, length):
offset = j-i
## find the distance bin into which the maxAllowedDist falls
lastDistBin = DistanceUtils.LabelsOfOneDistance(maxAllowedDist[offset], cutoff)
if lastDistBin < (numLabels - 1):
## merge the pred prob and ref prob in the bins from lastDistBin to the end
pred = predProb[i, j, : lastDistBin+1]
ref = refProb[offset-1][:lastDistBin+1]
potential[i, j, :lastDistBin+1] = -np.log( pred / ref )
potential[i, j, lastDistBin+1: ] = maxPotential
else:
## determine the last distance bin
rc = min(cutoff[-1], largestDistance) - 0.001
if (rc<10.0):
print 'ERROR: the largest distance cutoff for SimuRW is too small: ', rc
exit(1)
rc_index = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
refProbLen = refProb.shape[0]
#idx4rc = numLabels - 2
potential[i, j] = -np.log( predProb[i, j] / refProb[min(offset, refProbLen) -1 ] )
potential[i, j] -= potential[i, j, rc_index]
potential[i, j, rc_index + 1: ] = 0
## only valid for symmetric atom pairs
potential[j, i] = potential[i, j]
CheckPotentialValues(potential)
potentials[response] = potential
return potentials
def CalcPotentialByEmpSD(predDistMatrix, userRef, largestDistance=20, sequence=None, minPotential=-20., maxPotential=20.):
f=open(userRef, 'rb')
refData = cPickle.load(f)
f.close()
potentials = dict()
for response, predProb in predDistMatrix.iteritems():
labelName, labelType, _ = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
continue
if not conifg.IsDiscreteLabel(labelType):
continue
refProbList = refData[response][1]
length = predProb.shape[0]
if length < 400:
refProbs = [ ref for sz, freq, ref in refProbList if sz<=1.3*length and sz>=length/1.3 ]
else:
refProbs = [ ref for sz, freq, ref in refProbList if sz>=350 ]
print '#refProbMatrix: ', len(refProbs), ' for proteins with length= ', length
refProb = np.average(refProbs, axis=0)
potential = - np.log ( predProb / refProb )
rc = largestDistance
cutoff = config.GetCutoffs(response)
lastDistBin = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
lastCol = potential[:, :, lastDistBin]
potential = potential - lastCol
potential{;, :, lastDistBin: ] = 0
CheckPotentialValues(potential)
potentials[response] = potential
return potentials
def CalcPotentialByEmpSI(predDistMatrix, userRef, largestDistance=20, sequence=None, minPotential=-20., maxPotential=20.):
f=open(userRef, 'rb')
refData = cPickle.load(f)
f.close()
potentials = dict()
for response, prdProb in predDistMatrix.iteritems():
labelName, labelType, _ = config.ParseResponse(response)
if labelName not in config.allAtomPairNames:
continue
if not conifg.IsDiscreteLabel(labelType):
continue
refProb = refData[response][0]
potential = - np.log ( predProb / refProb )
rc = largestDistance
cutoff = config.GetCutoffs(response)
lastDistBin = DistanceUtils.LabelsOfOneDistance(rc, cutoff)
lastCol = potential[:, :, lastDistBin]
potential = potential - lastCol
potential[:, :, lastDistBin: ] =0
CheckPotentialValues(potential)
potentials[response] = potential
return potentials
allRefTypesWithFiles = [ ref.upper() for ref in ['SimuRW', 'EmpSI', 'EmpSD'] ]
allRefTypes = [ 'DFIRE', 'DOPE' ] + allRefTypesWithFiles
def main(argv):
inputFile = None
targetName = None
labelNames = ['CbCb']
potentialFileSuffix = 'pkl'
minPotential = -30.0
maxPotential = 30.0
minSeqSep = 3
minSeqSepStr='3'
## the largest dist cutoff
rc = 18
alpha4DFIRE = 1.61
rgScale4DOPE = 1.
## reference
reference = 'DFIRE'
## refFile
refFile = None
try:
opts, args = getopt.getopt(argv,"i:a:r:l:u:s:f:tn",["input=", "atomPairType=", "refState=", "minPotential=", "maxPotential=", "minSeqSep=", "refFile=", "textFormat=", "nonZero="])
print opts, args
except getopt.GetoptError:
Usage()
exit(1)
if len(opts) < 1:
Usage()
exit(1)
for opt, arg in opts:
if opt in ("-i", "--input"):
inputFile = arg
elif opt in ("-a", "--atomPairType"):
labelNames = config.ParseLabelNames(arg)
elif opt in ("-r", "--refState"):
fields = arg.split('+')
reference = fields[0].upper()
if reference not in allRefTypes:
print 'allowed reference types: ', allRefTypes
exit(1)
if len(fields) > 1:
if reference == 'DFIRE':
rc = np.float32(fields[1])
if len(fields) > 2:
alpha4DFIRE = np.float32(fields[2])
elif reference == 'DOPE':
rc = np.float32(fields[1])
if len(fields) > 2:
rgScale4DOPE = np.float32(fields[2])
elif reference == 'SimuRW'.upper():
rc = np.float32(fields[1])
else:
print 'WARNING: unsupported reference format: ', arg
elif opt in ("-f", "--refFile"):
refFile = arg
if not os.path.isfile(refFile):
print 'the provided file for reference state is not valid: ', refFile
exit(1)
elif opt in ("-l", "--minPotential"):
minPotential = np.float32(arg)
elif opt in ("-u", "--maxPotential"):
maxPotential = np.float32(arg)
elif opt in ("-s", "--minSeqSep"):
minSeqSep = np.int32(arg)
minSeqSepStr = arg
if minSeqSep < 1:
print 'ERROR: minSeqSep shall be at least 1'
exit(1)
elif opt in ("-t", "--textFormat"):
potentialFileSuffix = '.txt'
elif opt in ("-n", "--nonZero"):
resetFlag = False
else:
Usage()
exit(1)
if inputFile is None:
print 'Please provide an input file'
exit(1)
if not os.path.isfile(inputFile):
print 'The input file does not exist: ', inputFile
exit(1)
if reference in allRefTypesWithFiles and refFile is None:
print 'The file for user-sepcified reference state is empty'
exit(1)
targetName = os.path.basename(inputFile).split('.')[0]
content = DistanceUtils.LoadRawDistProbFile(inputFile)
assert len(content) >=6
name, sequence, predictedDistProb, predictedContactProb, labelWeight, labelDistribution = content[:6]
assert labelWeight is not None, "labelWeight shall not be empty"
## if needed, add code to here the predicted dist probability
filenames = [ targetName, 'distPotential']
if reference == 'DFIRE':
potential = CalcPotentialByDFIRE(predictedDistProb, alpha=alpha4DFIRE, largestDistance=rc, minPotential=minPotential, maxPotential=maxPotential)
filenames.extend([reference, str(rc), str(alpha4DFIRE), potentialFileSuffix])
elif reference == 'DOPE':
potential = CalcPotentialByDOPE(predictedDistProb, largestDistance=rc, rgScale=rgScale4DOPE, minPotential=minPotential, maxPotential=maxPotential)
filenames.extend([reference, str(rc), str(rgScale4DOPE), potentialFileSuffix])
elif reference == 'SimuRW'.upper():
potential = CalcPotentialBySimuRW(predictedDistProb, refFile, largestDistance=rc, minPotential=minPotential, maxPotential=maxPotential)
filenames.extend([reference, str(rc), potentialFileSuffix])
else:
print 'ERROR: unimplemented reference state: ', reference
exit(1)
potentialFileName = '.'.join(filenames)
## save to PKL file
if potentialFileName.endswith('.pkl'):
fh = open(potentialFileName, 'wb')
potential_new = dict()
distCutoffs = dict()
for response, pot in potential.iteritems():
labelName = config.Response2LabelName(response)
if labelName not in set(labelNames):
continue
potential_new[response] = pot
distCutoffs[response] = config.GetCutoffs(response)
cPickle.dump((name, sequence, potential_new, distCutoffs), fh, protocol=cPickle.HIGHEST_PROTOCOL)
fh.close()
return
## save to text file
potentialFileName = targetName + '.distPotential.s' + minSeqSepStr + potentialFileSuffix
fh = open(potentialFileName, 'w')
fh.write('#TARGET\t' + targetName + '\n')
fh.write('#SEQ\t' + sequence + '\n')
fh.write('#DistanceBinBoundaries\t' + "Please check config.py" + '\n')
for response, pot in potential.iteritems():
labelName, labelType, subType = config.ParseResponse(response)
if labelName not in set(labelNames):
continue
size = pot.shape
for i in xrange(size[0]):
rawPotStrs = []
for j in xrange(i+ minSeqSep, size[1]):
atom1, atom2 = config.SelectAtomPair(sequence, i, j, labelName)
y = pot[i, j]
rawPotStr = ' '.join(['AtomPair', atom1.upper(), str(i+1), atom2.upper(), str(j+1), subType] + [ "{:.4f}".format(e) for e in y ] )
rawPotStrs.append(rawPotStr)
if len(rawPotStrs) >0:
fh.write('\n'.join(rawPotStrs) + '\n')
fh.close()
if __name__ == "__main__":
main(sys.argv[1:])
def main(argv):
inputFile = None
targetName = None
labelNames = ['CbCb']
potentialFileSuffix = 'pkl'
minPotential = -30.0
maxPotential = 30.0
minSeqSep = 3
minSeqSepStr='3'
## the largest dist cutoff
rc = 18
alpha4DFIRE = 1.61
rgScale4DOPE = 1.
## reference
reference = 'DFIRE'
## refFile
refFile = None
try:
opts, args = getopt.getopt(argv,"i:a:r:l:u:s:f:tn",["input=", "atomPairType=", "refState=", "minPotential=", "maxPotential=", "minSeqSep=", "refFile=", "textFormat=", "nonZero="])
print opts, args
except getopt.GetoptError:
Usage()
exit(1)
if len(opts) < 1:
Usage()
exit(1)
for opt, arg in opts:
if opt in ("-i", "--input"):
inputFile = arg
elif opt in ("-a", "--atomPairType"):
labelNames = config.ParseLabelNames(arg)
elif opt in ("-r", "--refState"):
fields = arg.split('+')
reference = fields[0].upper()
if reference not in allRefTypes:
print 'allowed reference types: ', allRefTypes
exit(1)
if len(fields) > 1:
if reference == 'DFIRE':
rc = np.float32(fields[1])
if len(fields) > 2:
alpha4DFIRE = np.float32(fields[2])
elif reference == 'DOPE':
rc = np.float32(fields[1])
if len(fields) > 2:
rgScale4DOPE = np.float32(fields[2])
elif reference == 'SimuRW'.upper():
rc = np.float32(fields[1])
else:
print 'WARNING: unsupported reference format: ', arg
elif opt in ("-f", "--refFile"):
refFile = arg
if not os.path.isfile(refFile):
print 'the provided file for reference state is not valid: ', refFile
exit(1)
elif opt in ("-l", "--minPotential"):
minPotential = np.float32(arg)
elif opt in ("-u", "--maxPotential"):
maxPotential = np.float32(arg)
elif opt in ("-s", "--minSeqSep"):
minSeqSep = np.int32(arg)
minSeqSepStr = arg
if minSeqSep < 1:
print 'ERROR: minSeqSep shall be at least 1'
exit(1)
elif opt in ("-t", "--textFormat"):
potentialFileSuffix = '.txt'
elif opt in ("-n", "--nonZero"):
resetFlag = False
else:
Usage()
exit(1)
if inputFile is None:
print 'Please provide an input file'
exit(1)
if not os.path.isfile(inputFile):
print 'The input file does not exist: ', inputFile
exit(1)
if reference in allRefTypesWithFiles and refFile is None:
print 'The file for user-sepcified reference state is empty'
exit(1)
targetName = os.path.basename(inputFile).split('.')[0]
content = DistanceUtils.LoadRawDistProbFile(inputFile)
assert len(content) >=6
name, sequence, predictedDistProb, predictedContactProb, labelWeight, labelDistribution = content[:6]
assert labelWeight is not None, "labelWeight shall not be empty"
## if needed, add code to here the predicted dist probability
filenames = [ targetName, 'distPotential']
if reference == 'DFIRE':
potential = CalcPotentialByDFIRE(predictedDistProb, alpha=alpha4DFIRE, largestDistance=rc, minPotential=minPotential, maxPotential=maxPotential)
filenames.extend([reference, str(rc), str(alpha4DFIRE), potentialFileSuffix])
elif reference == 'DOPE':
potential = CalcPotentialByDOPE(predictedDistProb, largestDistance=rc, rgScale=rgScale4DOPE, minPotential=minPotential, maxPotential=maxPotential)
filenames.extend([reference, str(rc), str(rgScale4DOPE), potentialFileSuffix])
elif reference == 'SimuRW'.upper():
potential = CalcPotentialBySimuRW(predictedDistProb, refFile, largestDistance=rc, minPotential=minPotential, maxPotential=maxPotential)
filenames.extend([reference, str(rc), potentialFileSuffix])
else:
print 'ERROR: unimplemented reference state: ', reference
exit(1)
potentialFileName = '.'.join(filenames)
## save to PKL file
if potentialFileName.endswith('.pkl'):
fh = open(potentialFileName, 'wb')
potential_new = dict()
distCutoffs = dict()
for response, pot in potential.iteritems():
labelName = config.Response2LabelName(response)
if labelName not in set(labelNames):
continue
potential_new[response] = pot
distCutoffs[response] = config.GetCutoffs(response)
cPickle.dump((name, sequence, potential_new, distCutoffs), fh, protocol=cPickle.HIGHEST_PROTOCOL)
fh.close()
return
## save to text file
potentialFileName = targetName + '.distPotential.s' + minSeqSepStr + potentialFileSuffix
fh = open(potentialFileName, 'w')
fh.write('#TARGET\t' + targetName + '\n')
fh.write('#SEQ\t' + sequence + '\n')
fh.write('#DistanceBinBoundaries\t' + "Please check config.py" + '\n')
for response, pot in potential.iteritems():
labelName, labelType, subType = config.ParseResponse(response)
if labelName not in set(labelNames):
continue
size = pot.shape
for i in xrange(size[0]):
rawPotStrs = []
for j in xrange(i+ minSeqSep, size[1]):
atom1, atom2 = config.SelectAtomPair(sequence, i, j, labelName)
y = pot[i, j]
rawPotStr = ' '.join(['AtomPair', atom1.upper(), str(i+1), atom2.upper(), str(j+1), subType] + [ "{:.4f}".format(e) for e in y ] )
rawPotStrs.append(rawPotStr)
if len(rawPotStrs) >0:
fh.write('\n'.join(rawPotStrs) + '\n')
fh.close()