def __constructSolvers__(self, coefFiles):
solvers = {}
for f in coefFiles:
currCatName = AApairwise.__catPattern.search(f).group(1)
currFile = open(f, "r")
currDat = currFile.readlines()
currFile.close()
solvers[currCatName] = aaProbSolver(currDat)
return solvers
def __constructSolvers__(self, coefFiles):
solvers = {}
for f in coefFiles:
currCatName = AApairwise.__catPattern.search(f).group(1)
currFile = open(f, "r")
currDat = currFile.readlines()
currFile.close()
solvers[currCatName] = aaProbSolver(currDat)
return solvers
def __init__(self, pwFile):
#init solvers
## first order solver
fFirstOrder = open(firstOrderCoefFile, "r")
firstOrderCoefs = fFirstOrder.readlines()
fFirstOrder.close()
self.firstOrderSolver = aaProbSolver(firstOrderCoefs)
## second order solvers
### first conditioned on second
self.firstCondSecondSolvers = self.__constructSolvers__(firstCondSecondFiles)
### second conditioned on first
self.secondCondFirstSolvers = self.__constructSolvers__(secondCondFirstFiles)
self.aaDict = dict()
self.saDict = dict()
self.firstPosDict = dict()
self.secondPosDict = dict()
self.pairDict = dict()
self.posList = []
fInput = open(pwFile, "r")
allLines = fInput.readlines()
fInput.close()
for line in allLines:
tmpLine = line.split()
firstAA = tmpLine[4]
secondAA = tmpLine[5]
firstPos = tmpLine[6]
secondPos = tmpLine[7]
firstSA = tmpLine[9]
secondSA = tmpLine[13]
#float
invSD = 1.0/(float(secondPos) - float(firstPos))
invTD = 1.0/float(tmpLine[3])
# fill aaDict and saDict
if firstPos not in self.aaDict.keys():
self.aaDict[firstPos] = firstAA
self.saDict[firstPos] = firstSA
if secondPos not in self.aaDict.keys():
self.aaDict[secondPos] = secondAA
self.saDict[secondPos] = secondSA
# fill pos Dicts
if firstPos not in self.firstPosDict.keys():
self.firstPosDict[firstPos] = []
self.firstPosDict[firstPos].append(secondPos)
else:
if secondPos not in self.firstPosDict[firstPos]:
self.firstPosDict[firstPos].append(secondPos)
if secondPos not in self.secondPosDict.keys():
self.secondPosDict[secondPos] = []
self.secondPosDict[secondPos].append(firstPos)
else:
if firstPos not in self.secondPosDict[secondPos]:
self.secondPosDict[secondPos].append(firstPos)
#fill in pairDict
currPair = (firstPos, secondPos)
self.pairDict[currPair] = map(float, ["1", firstSA, secondSA, invSD, invTD])
self.posList = sorted(map(int, self.aaDict.keys()))
def __init__(self, pwFile):
#init solvers
## first order solver
fFirstOrder = open(firstOrderCoefFile, "r")
firstOrderCoefs = fFirstOrder.readlines()
fFirstOrder.close()
self.firstOrderSolver = aaProbSolver(firstOrderCoefs)
## second order solvers
### first conditioned on second
self.firstCondSecondSolvers = self.__constructSolvers__(
firstCondSecondFiles)
### second conditioned on first
self.secondCondFirstSolvers = self.__constructSolvers__(
secondCondFirstFiles)
self.aaDict = dict()
self.saDict = dict()
self.firstPosDict = dict()
self.secondPosDict = dict()
self.pairDict = dict()
self.posList = []
fInput = open(pwFile, "r")
allLines = fInput.readlines()
fInput.close()
for line in allLines:
tmpLine = line.split()
firstAA = tmpLine[4]
secondAA = tmpLine[5]
firstPos = tmpLine[6]
secondPos = tmpLine[7]
firstSA = tmpLine[9]
secondSA = tmpLine[13]
#float
invSD = 1.0 / (float(secondPos) - float(firstPos))
invTD = 1.0 / float(tmpLine[3])
# fill aaDict and saDict
if firstPos not in self.aaDict.keys():
self.aaDict[firstPos] = firstAA
self.saDict[firstPos] = firstSA
if secondPos not in self.aaDict.keys():
self.aaDict[secondPos] = secondAA
self.saDict[secondPos] = secondSA
# fill pos Dicts
if firstPos not in self.firstPosDict.keys():
self.firstPosDict[firstPos] = []
self.firstPosDict[firstPos].append(secondPos)
else:
if secondPos not in self.firstPosDict[firstPos]:
self.firstPosDict[firstPos].append(secondPos)
if secondPos not in self.secondPosDict.keys():
self.secondPosDict[secondPos] = []
self.secondPosDict[secondPos].append(firstPos)
else:
if firstPos not in self.secondPosDict[secondPos]:
self.secondPosDict[secondPos].append(firstPos)
#fill in pairDict
currPair = (firstPos, secondPos)
self.pairDict[currPair] = map(
float, ["1", firstSA, secondSA, invSD, invTD])
self.posList = sorted(map(int, self.aaDict.keys()))
import glob
import math
#'L' is the reference codon
aaList = ['A','C','D','E','F','G','H','I','K','L','M','N','P','Q','R','S','T','V','W','Y']
#coef file and folders
#on desktop
#firstOrderCoefFile = '/home/kuangyu/workspace/aaCodonProbPred/coefs/aa_sa_coef.txt'
#on mac
firstOrderCoefFile = '/Users/kwang2/Documents/workspace/aaCodonProbPred/coefs/aa_sa_coef.txt'
fFirstOrder = open(firstOrderCoefFile, "r")
firstOrderCoefs = fFirstOrder.readlines()
fFirstOrder.close()
firstOrderSolver = aaProbSolver(firstOrderCoefs)
#sanac range:
#min: 0
#max: 172.4
#generate test data points between min and max
allPoints = range(1,172,2)
fOutput=open("/Users/kwang2/Documents/workspace/aaCodonProbPred/studyHydroResult/aaProb_sa_0_172.csv","w")
for x in allPoints:
aaProbs = []
for aa in aaList:
tmpX = [1, x]
tmpProb = firstOrderSolver.getCatProb(aa, tmpX)
aaProbs.append(tmpProb)
#'L' is the reference codon
aaList = [
'A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R',
'S', 'T', 'V', 'W', 'Y'
]
#coef file and folders
#on desktop
#firstOrderCoefFile = '/home/kuangyu/workspace/aaCodonProbPred/coefs/aa_sa_coef.txt'
#on mac
firstOrderCoefFile = '/Users/kwang2/Documents/workspace/aaCodonProbPred/coefs/aa_sa_coef.txt'
fFirstOrder = open(firstOrderCoefFile, "r")
firstOrderCoefs = fFirstOrder.readlines()
fFirstOrder.close()
firstOrderSolver = aaProbSolver(firstOrderCoefs)
#sanac range:
#min: 0
#max: 172.4
#generate test data points between min and max
allPoints = range(1, 172, 2)
fOutput = open(
"/Users/kwang2/Documents/workspace/aaCodonProbPred/studyHydroResult/aaProb_sa_0_172.csv",
"w")
for x in allPoints:
aaProbs = []
for aa in aaList:
tmpX = [1, x]