def rotamerHMM(predictedProbs):
"""Given rotamer likelihoods for all suites, predict the most likely rotamer string using a Hidden Markov Model
ARGUMENTS:
predictedProbs - the probability for each suite for each rotamer formatted as a list of dictionaries
predictedProbs[suiteNum][rotamer] = probability
RETURNS:
bestPath - a list of the most likely rotamer for each suite
"""
numSuites = len(predictedProbs)
pathProbs = [
{} for i in xrange(numSuites)
] #the log probability of having followed a given path (the delta or phi array)
path = [{} for i in xrange(numSuites)
] #the path followed for $pathProbs (the psi array)
#initialize the pathProbs list
for curRot in rotList:
pathProbs[0][curRot] = ln(predictedProbs[0][curRot])
for curPos in xrange(1, numSuites): #for each suite
for curRot in rotList: #for each rotamer
#figure out what the best previous rotamer is for ending up at the current rotamer
bestPrevRot = max(pathProbs[curPos - 1],
key=lambda prevRot: pathProbs[curPos - 1][
prevRot] + __transitionProb(prevRot, curRot))
path[curPos][curRot] = bestPrevRot
pathProbs[curPos][curRot] = pathProbs[
curPos - 1][bestPrevRot] + __transitionProb(
bestPrevRot, curRot) + ln(predictedProbs[curPos][curRot])
#initialize bestPath to the appropriate length
bestPath = [None] * numSuites
#figure out the best last position
curPos = numSuites - 1
bestPath[curPos] = max(pathProbs[curPos],
key=lambda curRot: pathProbs[curPos][curRot])
#follow the path back to figure out what the best path was
for curPos in xrange(numSuites - 1, 0, -1):
bestPath[curPos - 1] = path[curPos][bestPath[curPos]]
return bestPath
def secondPhos(self, mapNum, curPhos, direction = 3):
"""find the second phosphate in a chain using phosphate distance data
ARGUMENTS:
mapNum - the molecule number of the Coot map to use
curPhos - the coordinates of the first phosphate
OPTIONAL ARGUMENTS:
direction - which direction to trace the chain: 3 implies 5'->3'
5 implies 3'->5'
defaults to 3 (5'->3')
RETURNS:
peakList - a list of potential phosphate peaks
sugarList - a list of potential C1' locations for each phosphate peak
"""
peaks = self.getPeaks(mapNum, curPhos)
#calculate the score for each peak
peakScores = []
for curPeak in peaks:
#exclude any peaks that are within an Angstom of the current phosphate position
#this will exclude the peak corresponding to the current phosphate position
if dist(curPhos, curPeak) >= 1:
#do a sugar search for the current phosphate
if direction == 3:
sugarLocs = self.findSugar(mapNum, curPhos, curPeak)
else: #direction == 5:
sugarLocs = self.findSugar(mapNum, curPeak, curPhos)
densityScore = sugarLocs[0][3] + curPeak[3]
score = ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))) + (SECOND_PHOS_DENSITY_WEIGHT * ln(densityScore))
peakScores.append((curPeak, score, sugarLocs))
#sort the peaks according to score
peakScores.sort(key = lambda x: x[1], reverse = 1)
#return only the coordinates, not the scores
peakList = [x[0] for x in peakScores]
sugarList = [x[2] for x in peakScores]
return (peakList, sugarList)
def secondPhos(self, mapNum, curPhos, direction = 3):
"""find the second phosphate in a chain using phosphate distance data
ARGUMENTS:
mapNum - the molecule number of the Coot map to use
curPhos - the coordinates of the first phosphate
OPTIONAL ARGUMENTS:
direction - which direction to trace the chain: 3 implies 5'->3'
5 implies 3'->5'
defaults to 3 (5'->3')
RETURNS:
peakList - a list of potential phosphate peaks
sugarList - a list of potential C1' locations for each phosphate peak
"""
peaks = self.getPeaks(mapNum, curPhos)
#calculate the score for each peak
peakScores = []
for curPeak in peaks:
#exclude any peaks that are within an Angstom of the current phosphate position
#this will exclude the peak corresponding to the current phosphate position
if dist(curPhos, curPeak) >= 1:
#do a sugar search for the current phosphate
if direction == 3:
sugarLocs = self.findSugar(mapNum, curPhos, curPeak)
else: #direction == 5:
sugarLocs = self.findSugar(mapNum, curPeak, curPhos)
densityScore = sugarLocs[0][3] + curPeak[3]
score = ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))) + (SECOND_PHOS_DENSITY_WEIGHT * ln(densityScore))
peakScores.append((curPeak, score, sugarLocs))
#sort the peaks according to score
peakScores.sort(key = lambda x: x[1], reverse = 1)
#return only the coordinates, not the scores
peakList = [x[0] for x in peakScores]
sugarList = [x[2] for x in peakScores]
return (peakList, sugarList)
def rotamerHMM(predictedProbs):
"""Given rotamer likelihoods for all suites, predict the most likely rotamer string using a Hidden Markov Model
ARGUMENTS:
predictedProbs - the probability for each suite for each rotamer formatted as a list of dictionaries
predictedProbs[suiteNum][rotamer] = probability
RETURNS:
bestPath - a list of the most likely rotamer for each suite
"""
numSuites = len(predictedProbs)
pathProbs = [{} for i in xrange(numSuites)] #the log probability of having followed a given path (the delta or phi array)
path = [{} for i in xrange(numSuites)] #the path followed for $pathProbs (the psi array)
#initialize the pathProbs list
for curRot in rotList:
pathProbs[0][curRot] = ln(predictedProbs[0][curRot])
for curPos in xrange(1, numSuites): #for each suite
for curRot in rotList: #for each rotamer
#figure out what the best previous rotamer is for ending up at the current rotamer
bestPrevRot = max(pathProbs[curPos-1], key = lambda prevRot: pathProbs[curPos-1][prevRot] + __transitionProb(prevRot, curRot))
path[curPos][curRot] = bestPrevRot
pathProbs[curPos][curRot] = pathProbs[curPos-1][bestPrevRot] + __transitionProb(bestPrevRot, curRot) + ln(predictedProbs[curPos][curRot])
#initialize bestPath to the appropriate length
bestPath = [None] * numSuites
#figure out the best last position
curPos = numSuites - 1
bestPath[curPos] = max(pathProbs[curPos], key = lambda curRot: pathProbs[curPos][curRot])
#follow the path back to figure out what the best path was
for curPos in xrange(numSuites-1, 0, -1):
bestPath[curPos-1] = path[curPos][bestPath[curPos]]
return bestPath
def nextPhos(self, mapNum, curPhos, prevPhos, prevSugar, direction = 3):
"""Find the next phosphate in a chain using phosphate distance and angle data
ARGUMENTS:
mapNum - the molecule number of the Coot map to use
curPhos - the coordinates of the current phosphate
prevPhos - the coordinates of the previous phosphate
prevSugar - the coordinates of the previous C1' atom
OPTIONAL ARGUMENTS:
direction - which direction to trace the chain: 3 implies 5'->3'
5 implies 3'->5'
defaults to 3 (5'->3')
RETURNS:
peakList - a list of potential phosphate peaks
sugarList - a list of potential C1' locations for each phosphate peak
"""
peaks = self.getPeaks(mapNum, curPhos)
#calculate the score for each peak
peakScores = []
for curPeak in peaks:
#exclude any peaks that are within an Angstom of the current phosphate position
#this will exclude the peak corresponding to the current phosphate position
if dist(curPhos, curPeak) >= 1:
#do a sugar search for the current phosphate
if direction == 3:
sugarLocs = self.findSugar(mapNum, curPhos, curPeak)
else:
sugarLocs = self.findSugar(mapNum, curPeak, curPhos)
densityScore = sugarLocs[0][3] + curPeak[3]
score = ((PHOS_DIST_WEIGHT * ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))))
+ ln(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak)))
+ ln(self.__sugarPhosSugarAngleInterp.interp(angle(prevSugar, curPhos, sugarLocs[0][0:3])))
+ (DENSITY_WEIGHT * ln(densityScore))
)
peakScores.append((curPeak, score, sugarLocs))
#FOR DEBUGGING OUTPUT
#peakScores.append((curPeak, score, sugarLocs, ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))), ln(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak))), ln(self.__sugarPhosSugarAngleInterp.interp(angle(prevSugar, prevPhos, sugarLocs[0][0:3]))), sugarLocs[0][3], sugarLocs[0][4], sugarLocs[0][5], sugarLocs[0][6], curPeak[3], sugarLocs[0][7]))
#peakScores.append((curPeak, score, sugarLocs, ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))), ln(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak))), ln(self.__sugarPhosSugarAngleInterp.interp(angle(prevSugar, curPhos, sugarLocs[0][0:3]))), ln(densityScore), DENSITY_WEIGHT * ln(densityScore), sugarLocs[0][3], curPeak[3]))
#print "Score for peak %(curPeak)s is %(score)f" % vars()
#print "\tDist: " + str(dist(curPhos, curPeak)) + "\t" + str(self.__phosDistInterp.interp(dist(curPhos, curPeak)))
#print "\tAngle: " + str(angle(prevPhos, curPhos, curPeak)) + "\t" + str(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak)))
#sort the peaks according to score
peakScores.sort(key = lambda x: x[1], reverse = 1)
#return only the coordinates, not the scores
peakList = [x[0] for x in peakScores]
sugarList = [x[2] for x in peakScores]
#FOR DEBUGGING OUTPUT
#print "Current scores:"
#print "overall\t\tphosDist\tphosAngle\tsPsAngle\tdensity score\tw. den score\tsugar score\tphos score"
#for x in peakScores:
# #print "SCORE: %f\tSUGAR SCORE: %f" % (x[1], x[2][0][3])
# print "\t".join(map(str, (x[1],) + x[3:]))
return (peakList, sugarList)
def nextPhos(self, mapNum, curPhos, prevPhos, prevSugar, direction = 3):
"""Find the next phosphate in a chain using phosphate distance and angle data
ARGUMENTS:
mapNum - the molecule number of the Coot map to use
curPhos - the coordinates of the current phosphate
prevPhos - the coordinates of the previous phosphate
prevSugar - the coordinates of the previous C1' atom
OPTIONAL ARGUMENTS:
direction - which direction to trace the chain: 3 implies 5'->3'
5 implies 3'->5'
defaults to 3 (5'->3')
RETURNS:
peakList - a list of potential phosphate peaks
sugarList - a list of potential C1' locations for each phosphate peak
"""
peaks = self.getPeaks(mapNum, curPhos)
#calculate the score for each peak
peakScores = []
for curPeak in peaks:
#exclude any peaks that are within an Angstom of the current phosphate position
#this will exclude the peak corresponding to the current phosphate position
if dist(curPhos, curPeak) >= 1:
#do a sugar search for the current phosphate
if direction == 3:
sugarLocs = self.findSugar(mapNum, curPhos, curPeak)
else:
sugarLocs = self.findSugar(mapNum, curPeak, curPhos)
densityScore = sugarLocs[0][3] + curPeak[3]
score = ((PHOS_DIST_WEIGHT * ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))))
+ ln(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak)))
+ ln(self.__sugarPhosSugarAngleInterp.interp(angle(prevSugar, curPhos, sugarLocs[0][0:3])))
+ (DENSITY_WEIGHT * ln(densityScore))
)
peakScores.append((curPeak, score, sugarLocs))
#FOR DEBUGGING OUTPUT
#peakScores.append((curPeak, score, sugarLocs, ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))), ln(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak))), ln(self.__sugarPhosSugarAngleInterp.interp(angle(prevSugar, prevPhos, sugarLocs[0][0:3]))), sugarLocs[0][3], sugarLocs[0][4], sugarLocs[0][5], sugarLocs[0][6], curPeak[3], sugarLocs[0][7]))
#peakScores.append((curPeak, score, sugarLocs, ln(self.__phosDistInterp.interp(dist(curPhos, curPeak))), ln(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak))), ln(self.__sugarPhosSugarAngleInterp.interp(angle(prevSugar, curPhos, sugarLocs[0][0:3]))), ln(densityScore), DENSITY_WEIGHT * ln(densityScore), sugarLocs[0][3], curPeak[3]))
#print "Score for peak %(curPeak)s is %(score)f" % vars()
#print "\tDist: " + str(dist(curPhos, curPeak)) + "\t" + str(self.__phosDistInterp.interp(dist(curPhos, curPeak)))
#print "\tAngle: " + str(angle(prevPhos, curPhos, curPeak)) + "\t" + str(self.__phosAngleInterp.interp(angle(prevPhos, curPhos, curPeak)))
#sort the peaks according to score
peakScores.sort(key = lambda x: x[1], reverse = 1)
#return only the coordinates, not the scores
peakList = [x[0] for x in peakScores]
sugarList = [x[2] for x in peakScores]
#FOR DEBUGGING OUTPUT
#print "Current scores:"
#print "overall\t\tphosDist\tphosAngle\tsPsAngle\tdensity score\tw. den score\tsugar score\tphos score"
#for x in peakScores:
# #print "SCORE: %f\tSUGAR SCORE: %f" % (x[1], x[2][0][3])
# print "\t".join(map(str, (x[1],) + x[3:]))
return (peakList, sugarList)
