def distanceMatrixCorrelation(matrix1, matrix2, weights = None,
collectComponents = False):
"""
:param matrix1:
:param matrix2:
:param weights:
:return: mean, and STD of the Kendal Tau Distances between all rows,
and sorted list of names in the order of better correlations
"""
size = matrix1.getSize()
assert(size == matrix2.getSize())
assert((not weights) or (size == weights.getSize()))
kendallList = [None] * size
weightsAllOnes = [1.0] * size
compDict = DefDict(list)
compSet = set()
if collectComponents:
for vl in matrix1.getArray():
for v in vl:
compSet.add(v)
for i in range(size):
components = DefDict(float)
kendallList[i] = calculateWeightedKendall(matrix1[i],
matrix2[i], weights = weights[i] if weights else None,
components = components if collectComponents else None)
for k in compSet:
compDict[k].append(components[k])
sortedNames = sorted(zip(matrix1.names, kendallList), key =
operator.itemgetter(1))
compList = None
if collectComponents:
compList = map(np.mean, map(operator.itemgetter(1),
sorted(compDict.iteritems(), key = operator.itemgetter(0))))
return (np.mean(kendallList), np.std(kendallList), sortedNames, compList)
def voteRank(sequences, motifs):
poll = {}
for seq in sequences:
poll[seq] = [0.0] * len(sequences[seq])
# perform poll
for tool in motifs:
for motif in motifs[tool]:
for seq in motifs[tool][motif]:
sequence = best(sequences, seq)
for pos in motifs[tool][motif][seq]:
for i in xrange(pos, pos + len(motif)):
try:
# instead of weighting all results the same (1), we
# could bias based on tool or number of results or something like that
poll[sequence][i - 1] += 1
except Exception as e:
print e
print 'It appears a tool has reported finding a motif',\
'outside the bounds of a sequence'
print 'such as finding a motif of length 10 at position',\
'195 in a sequence with length 200'
pdb.set_trace()
# add up votes for each motif
ress = DD(int)
for tool in motifs:
for motif in motifs[tool]:
for seq in motifs[tool][motif]:
for pos in motifs[tool][motif][seq]:
for p in xrange(pos, pos + len(motif)):
ress[motif] += poll[best(sequences, seq)][p-1]
# sort motifs by number of votes
return sorted(map(lambda a: list(a[::-1]), ress.iteritems()))
OUT1.write("%s\t%0.1f\t%0.1f\t%s\t%s\n" %
(transpos, RefMet[transpos], met, "nada", "nada"))
# OUT1.write("%s\t%s\t%0.1f\t%s\t%s\t%s\n" % (transpos, RefMet[transpos], met, x[4], x[5], RefSeq[transpos]) )
FoundMet[transpos] = met
found += 1
else:
# Option for dumping all other 5mC calls . . . . . .
met = 100 * (x[1] / x[2])
# headers = "Pos\tExpMet\tObsMet\tMETscore\tUMTscore\tSeq\n"
OUT2.write("%s\t%0.1f\t%0.1f\t%s\t%s\tnada\n" %
(transpos, RefMet[transpos], met, "nada", "nada"))
IN.close()
OUT1.close()
OUT2.close()
OUT3 = open(results + OUTlost, 'w')
OUT3.write("POS\tpMET\tLOST\n")
lost = 0
for (pos, count) in RefMet.iteritems():
if count > 0:
if FoundMet[pos] < 0:
OUT3.write("%s\t%s\t0\n" % (pos, RefMet[pos]))
lost += 1
OUT3.close()
print " FOUND = ", found, " ; LOST = ", lost
print "\n\n\n * * * * * D O N E * * * * * * \n\n\n"
# EOF ------------------------------------------------------------------------
cogDist = DefDict(dict)
for ordinal, (dir1, cs1) in enumerate(cogDict.iteritems(), start = 1):
print("\r%d. %s" % (ordinal, dir1)),
for dir2, cs2 in cogDict.iteritems():
cogDist[dir1][dir2] = cogDistFunc(cs1, cs2)
print("\nBuilding average distances for TaxaTypes...")
# Genome dir -> dict of {taxaTypes -> avg COG distance to dir}
dirTaxaTypeDictDict = DefDict(lambda: DefDict(list))
for ordinal, dir1 in enumerate(taxaDict.keys(), start = 1):
print("\r%d. %s" % (ordinal, dir1)),
for dir2, taxa in taxaDict.iteritems():
dirTaxaTypeDictDict[dir1][repr(taxa.type)].append(cogDist[dir1][dir2])
print("\nRebuilding dirTaxaTypeDictDict to get UtilNormDistribs...")
for dir, d in dirTaxaTypeDictDict.iteritems():
# Find global weighted STD
std = 0.
totalLen = 0
for taxaTypeStr, distList in d.iteritems():
if len(distList) >= 2:
val = np.std(distList, ddof = 1.)
std += val * val * len(distList)
totalLen += len(distList)
if totalLen == 0:
raise ValueError("Cannot calcuate global std for %s" % dir)
std /= totalLen
for taxaTypeStr, distList in d.iteritems():
localStd = np.std(distList)
localStd *= localStd
FILE[i] = FILE[i].rstrip()
fragSeq = ''.join(FILE)
fracGC = fragSeq.count('C') + fragSeq.count('G')
genFragLen = len(fragSeq)
# Generate refMettable to work with. . . . . . . .
index = 0
while (index > -1):
index = fragSeq.find('CCGG', index + 3)
if index > -1 and index < genFragLen - 10:
METtable[index] = random.choice(methylstates)
else:
break
Mettable = open(refMetTable, 'w')
for pos, pcnt in METtable.iteritems():
Mettable.write("%s\t%0.2f\n" % (pos + 1, pcnt))
Mettable.close()
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# . . . Process differentially methylated copies . . . .
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if (ReadGenFile == 0):
# Assign target quantitative state to each CCGG site in the sample . . . .
fracGC = 100 * float(fracGC) / float(genFragLen)
countCCGG = 0
index = 7
while (index > -1):
index = fragSeq.find('CCGG', index + 3)
if index > -1 and index < genFragLen - 10:
count += 1
if count % 1000 == 0:
print count,
print
print k,"Done!!"
## Print Dict
print "Printing Dictionary"
for i,j in contextDict.iteritems():
frequenciesFile.write(i[0]+"\t"+i[1]+"\t"+str(j)+"\n")
frequenciesFile.close()
## Print Test, Indices
print "printing PureTrainFile"
for i in trainIndices:
pureTrainFile.write(word_tag(enLines[i]))
pureTrainFile.write(word_tag(frLines[i]))
pureTrainFile.close()
print "Printing Testfile"
def voteRefine(sequences, motifs):
#get probabilities
lets = "ACGT"
probability = DD(int)
for seq in sequences:
for let in sequences[seq]:
probability[let] += 1
s = sum(probability.values())
for let in lets:
probability[let] = probability[let] / float(s)
#conductPoll
poll = {}
maxV = 0
maxL = 0
for seq in sequences:
poll[seq] = [0.0] * len(sequences[seq])
if len(sequences[seq]) > maxL:
maxL = len(sequences[seq])
for tool in motifs:
for motif in motifs[tool]:
for seq in motifs[tool][motif]:
sequence = best(sequences, seq)
for pos in motifs[tool][motif][seq]:
for i in xrange(pos, pos + len(motif)):
try:
# instead of weighting all results the same (1), we
# could bias based on tool or number of results or something like that
#poll[sequence][i - 1] += 1
if tool == "CMF":
poll[sequence][i - 1] += 1
if tool == "Weeder":
poll[sequence][i - 1] += 1
if tool == "MEME":
poll[sequence][i - 1] += 1
if tool == "DECOD":
poll[sequence][i - 1] += 1
if tool == "BioProspector":
poll[sequence][i - 1] += 1
if tool == "XXmotif":
poll[sequence][i - 1] += 1
except Exception as e:
print e
print 'It appears a tool has reported finding a motif',\
'outside the bounds of a sequence'
print 'such as finding a motif of length 10 at position',\
'195 in a sequence with length 200'
pdb.set_trace()
if poll[sequence][i - 1] > maxV:
maxV = poll[sequence][i - 1]
#inspectPoll
ress = []
THRESH = 3.7
maxInsts = 0
MLEN = MOTIF_LEN
for seq in poll:
for i in xrange(len(poll[seq]) - MLEN):
if sum(poll[seq][i:i + MLEN]) >= MLEN * THRESH:
curr = sequences[seq][i:i + MLEN]
bestPWM = None
bestMatching = 0
for PWM in ress:
matching = compMotifPWM(curr, PWM)
if matching > bestMatching and matching > MLEN / 2:
bestMatching = matching
bestPWM = PWM
if bestPWM == None:
bestPWM = [[0, 0, 0, 0] for x in xrange(MLEN)]
ress.append(bestPWM)
for c, col in zip(curr, bestPWM):
col[ALPH[c]] += 1
insts = sum(bestPWM[0])
if insts > maxInsts:
maxInsts = insts
votedRess = DD(int)
for PWM in ress:
l = len(PWM)
cons = PWMconsensus(PWM)
for seq in sequences:
for spos in xrange(0, len(sequences[seq]) - l):
# .75% thresh
if compMotifPWM(sequences[seq][spos:spos + l], PWM) >= .75 * l:
for pos in xrange(spos, spos + l):
votedRess[cons] += poll[seq][pos]
return sorted(votedRess.iteritems(), key=lambda a: a[::-1])
