def RunAlphaGammaTest(chr, organism):
"""
Runs all Alpha, Gamma test calculations.
chr: Current chromosome number.
organism: Organism's name.
"""
print ("ALPHA GAMMA")
# to find C alpha, gamma and P alpha, gamma
seqNames = printAndParseFiles.findSeqNames("geneLocations" + organism + "\GeneLocations%d.txt" % (chr))
seqCagDictAsym = FindCandP.combineSeqMats("SubMatinGenes" + organism[0].upper() + "\SubMatinGenes%d.txt" % (chr), seqNames)
seqCagDictSym = copy.deepcopy(seqCagDictAsym)
printAndParseFiles.printDictionaryListToFile(seqCagDictAsym, "Calculations_" + organism + "\CSeqFamilyMats\CSeqFamilyMats%d.txt" % (chr))
seqPagDictAsym = FindCandP.findPalphaGammaAsymmetric(seqCagDictAsym)
seqPagDictSym = FindCandP.findPalphaGammaSymmetric(seqCagDictSym)
printAndParseFiles.printDictionaryListToFile(seqPagDictAsym, "Calculations_" + organism + "\PSeqFamilyMats\PSeqFamilyMatsAsymmetric%d.txt" % (chr))
printAndParseFiles.printDictionaryListToFile(seqPagDictSym, "Calculations_" + organism + "\PSeqFamilyMats\PSeqFamilyMatsSymmetric%d.txt" % (chr))
# to find R*t alpha, gamma
RagDictAsym = FindR.calculateRag(seqPagDictAsym, str(chr), "Asymmetric", "RAssertionFailuresAsymmetric_" + organism + "/")
RagDictSym = FindR.calculateRag(seqPagDictSym, str(chr), "Symmetric", "RAssertionFailuresSymmetric_" + organism + "/")
for gene, families in RagDictSym.items():
for name, Rmatrix in families.items():
if name not in RagDictAsym[gene]:
print "From Symmetric"
print gene, name
del RagDictSym[gene][name]
for gene, families in RagDictAsym.items():
for name, Rmatrix in families.items():
if name not in RagDictSym[gene]:
print "From Asymmetric"
print gene, name
del RagDictAsym[gene][name]
printAndParseFiles.printDictionaryMatrixToFile(RagDictAsym, "Calculations_" + organism + "\RSeqFamilyMats\RSeqFamilyMatsAsymmetric%d.txt" % (chr))
printAndParseFiles.printDictionaryMatrixToFile(RagDictSym, "Calculations_" + organism + "\RSeqFamilyMats\RSeqFamilyMatsSymmetric%d.txt" % (chr))
# to find Q alpha,gamma and Q gamma
matSize = 4
MtagDictAsym = FindMT.calculateMtalphaGamma(RagDictAsym, matSize)
MtagDictSym = FindMT.calculateMtalphaGamma(RagDictSym, matSize)
printAndParseFiles.printDictionaryofValuesToFile(MtagDictAsym, "Calculations_" + organism + "\MtSeqFamilyMats\MtSeqFamilyMatsAsymmetric%d.txt" % (chr))
printAndParseFiles.printDictionaryofValuesToFile(MtagDictSym, "Calculations_" + organism + "\MtSeqFamilyMats\MtSeqFamilyMatsSymmetric%d.txt" % (chr))
QagDictAsym = FindQ.calculateQag(RagDictAsym, MtagDictAsym, matSize)
QagDictSym = FindQ.calculateQag(RagDictSym, MtagDictSym, matSize)
printAndParseFiles.printDictionaryMatrixToFile(QagDictAsym, "Calculations_" + organism + "\QSeqFamilyMats\QSeqFamilyMatsAsymmetric%d.txt" % (chr))
printAndParseFiles.printDictionaryMatrixToFile(QagDictSym, "Calculations_" + organism + "\QSeqFamilyMats\QSeqFamilyMatsSymmetric%d.txt" % (chr))
QgammaAsym = FindQ.findQgamma(QagDictAsym)
QgammaSym = FindQ.findQgamma(QagDictSym)
printAndParseFiles.printMatrixToFile(QgammaAsym, "Calculations_" + organism + "\Qgamma\QgammaAsymmetric%d.txt" % (chr))
printAndParseFiles.printMatrixToFile(QgammaSym, "Calculations_" + organism + "\Qgamma\QgammaSymmetric%d.txt" % (chr))
print ("DONE WITH CHR %d" % chr)
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" )
