def RunGlobalAlphaTest(beginSeqNum, endSeqNum, firstTime, significantRepeatList, organism, prmPrefix, prmDirectory = 'prm_files/'):
"""
Runs all Global Alpha test calculations.
beginSeqNum: Beginning chromosome range.
endSeqNum: Ending chromosome range.
firstTime: Boolean if first time for all calculations.
significantRepeatList: List of significant transposable element family instances.
organism: Organism's name.
prmDirectory: Directory where all of the .prm files are located.
"""
print ("GLOBAL ALPHA")
# to find global alpha values for C and P
if firstTime == True:
AllRepObjs = list(itertools.chain.from_iterable(([unpickleRepeats(prmPrefix + "%d" % chrNum, prmDirectory) for chrNum in range(beginSeqNum, endSeqNum+1)])))
print (len(AllRepObjs))
sigReps = printAndParseFiles.SigTEs(AllRepObjs, significantRepeatList)
print len(sigReps)
CfamilyMats = FindCandP.combineMatrices(sigReps)
print ("done with C")
printAndParseFiles.printListToFile(CfamilyMats, "Calculations_" + organism + "\CFamilyMats.txt")
PfamilyMats = FindCandP.getPSymm(CfamilyMats)
printAndParseFiles.printListToFile(PfamilyMats, "Calculations_" + organism + "\PFamilyMats.txt")
print ("done with P")
else:
PfamilyMats = printAndParseFiles.parsePfamilyFile("Calculations_" + organism + "\PFamilyMats.txt")
# to find global alpha values for R*t
print ("R")
RmatDict = FindR.calculateR(PfamilyMats)
printAndParseFiles.printMatrixToFile(RmatDict, "Calculations_" + organism + "\RFamilyMats.txt" )
# to find global alpha values for m*t
matSize = 4
print ("mt")
mtDict = FindMT.calculateMt(RmatDict, matSize)
printAndParseFiles.printValuesToFile(mtDict, "Calculations_" + organism + "\MTFamilyVals.txt")
# to find global alpha values for Q
print ("Q")
QmatDict = FindQ.calculateQvalues(mtDict, RmatDict, matSize)
printAndParseFiles.printMatrixToFile(QmatDict, "Calculations_" + organism + "\QFamilyMats.txt" )
def RunGammaTest(chr, beginSeqName, globalOrLocalMts, organism):
"""
Runs all Gamma test calculations.
chr: Current chromosome number.
beginSeqName: Beginning of sequence names for query.
globalOrLocalMts: String identifying whether to use global or local Mt values.
organism: Organism's name.
"""
print ("GAMMA")
# to find P gamma
familyListAsym = printAndParseFiles.parsePalphaGamma("Calculations_" + organism + "\RSeqFamilyMats\RSeqFamilyMatsAsymmetric%d.txt" % (chr), beginSeqName)#change this to Rag, should be the final area of filtering
familyListSym = printAndParseFiles.parsePalphaGamma("Calculations_" + organism + "\RSeqFamilyMats\RSeqFamilyMatsSymmetric%d.txt" % (chr), beginSeqName)
QgammaAsym = printAndParseFiles.parseQgammaFile("Calculations_" + organism + "\Qgamma\QgammaAsymmetric%d.txt" % (chr))
QgammaSym = printAndParseFiles.parseQgammaFile("Calculations_" + organism + "\Qgamma\QgammaSymmetric%d.txt" % (chr))
mtDict = {}
if (globalOrLocalMts == "Global"):
mtDict = printAndParseFiles.parseValueFile("Calculations_" + organism + "\MTFamilyVals.txt")
PalphaGammaHatAsym = FindCandP.calculatePalphaGammaHatGlobal(QgammaAsym, familyListAsym, mtDict)
PalphaGammaHatSym = FindCandP.calculatePalphaGammaHatGlobal(QgammaSym, familyListSym, mtDict)
printAndParseFiles.printDictionaryMatrixToFile(PalphaGammaHatAsym, "Calculations_" + organism + "\PalphaGammaHat%s\PalphaGammaHatAsymmetric%d.txt" % (globalOrLocalMts,chr))
printAndParseFiles.printDictionaryMatrixToFile(PalphaGammaHatSym, "Calculations_" + organism + "\PalphaGammaHat%s\PalphaGammaHatSymmetric%d.txt" % (globalOrLocalMts,chr))
CalphaGamma = printAndParseFiles.parseCalphaGammaFile("Calculations_" + organism + "\CSeqFamilyMats\CSeqFamilyMats%d.txt" % (chr), beginSeqName)
# calculate this section's L gamma value
LgammaAsym = FindLg.findLgamma(CalphaGamma, PalphaGammaHatAsym)
LgammaSym = FindLg.findLgamma(CalphaGamma, PalphaGammaHatSym)
printAndParseFiles.printValuesToFile(LgammaAsym, "Calculations_" + organism + "\Lgamma%s\LgammaAsymmetric%d.txt" % (globalOrLocalMts,chr))
printAndParseFiles.printValuesToFile(LgammaSym, "Calculations_" + organism + "\Lgamma%s\LgammaSymmetric%d.txt" % (globalOrLocalMts,chr))
elif (globalOrLocalMts == "Local"):
mtDictAsym = printAndParseFiles.parseMtalphaGammaFile("Calculations_" + organism + "\MtSeqFamilyMats\MtSeqFamilyMatsAsymmetric%d.txt" % chr, beginSeqName) # create dictionary values for asymmetric and symmetric, perform gamma calculations using them
PalphaGammaHatAsym = FindCandP.calculatePalphaGammaHatLocal(QgammaAsym, familyListAsym, mtDictAsym)
mtDictSym = printAndParseFiles.parseMtalphaGammaFile("Calculations_" + organism + "\MtSeqFamilyMats\MtSeqFamilyMatsSymmetric%d.txt" % chr, beginSeqName)
PalphaGammaHatSym = FindCandP.calculatePalphaGammaHatLocal(QgammaSym, familyListSym, mtDictSym)
printAndParseFiles.printDictionaryMatrixToFile(PalphaGammaHatAsym, "Calculations_" + organism + "\PalphaGammaHat%s\PalphaGammaHatAsymmetric%d.txt" % (globalOrLocalMts,chr))
printAndParseFiles.printDictionaryMatrixToFile(PalphaGammaHatSym, "Calculations_" + organism + "\PalphaGammaHat%s\PalphaGammaHatSymmetric%d.txt" % (globalOrLocalMts,chr))
CalphaGamma = printAndParseFiles.parseCalphaGammaFile("Calculations_" + organism + "\CSeqFamilyMats\CSeqFamilyMats%d.txt" % (chr), beginSeqName)
# calculate this section's L gamma value
LgammaAsym = FindLg.findLgamma(CalphaGamma, PalphaGammaHatAsym)
LgammaSym = FindLg.findLgamma(CalphaGamma, PalphaGammaHatSym)
printAndParseFiles.printValuesToFile(LgammaAsym, "Calculations_" + organism + "\Lgamma%s\LgammaAsymmetric%d.txt" % (globalOrLocalMts,chr))
printAndParseFiles.printValuesToFile(LgammaSym, "Calculations_" + organism + "\Lgamma%s\LgammaSymmetric%d.txt" % (globalOrLocalMts,chr))
else:
print "Error with Global or Local choice. Please type 'Global' or 'Local'"
print ("DONE WITH CHR %d" % chr)
