def __init__(self,seed_seqs, all_seqs, width = 6, verbose = ''):
self.seed_seqs = seed_seqs #Sequences to be scanned for seeds
self.seqs = all_seqs
self.candidates = []
self.models = [] #Set directly or computed from seed_seqs
self.width = width
self.verbose = verbose
if width:
self.goodwmersT = MotifTools.top_nmers(self.width,self.seed_seqs,1,"")
else:
self.goodwmersT = zip(self.seed_seqs,range(len(self.seed_seqs)))
self.bgprob = {'A': 0.31, 'C': .19, 'G': .19, 'T': .31}
self.beta = 0.001
self.deltamin = 1e-3
self.probes = []
self.method = "ZOOPS" # OOPS or ZOOPS )
self.param = {}
self.gapflank = 0
self.gapweight = 0.2
self.seedbeta = 0.02
self.joint = 1
global theMarkovBackground
if theMarkovBackground:
self.bgprob = theMarkovBackground.zeroth()
'''DELETE
def main():
seqsD = Fasta.load(sys.argv[1])
seqs = seqsD.values()
for w in range(1, 7):
allnmers = permute(w)
nmersT = MotifTools.top_nmers(w, seqs, 'with counts', 'purge Ns')
nmersD = {}
total = 0
for nmer in allnmers:
nmersD[nmer] = 1 #Pseudo count
total = total + 1
for nmer, count in nmersT[:]:
try:
rc = MotifTools.revcomplement(nmer)
nmersD[nmer] = nmersD[nmer] + count
nmersD[rc] = nmersD[rc] + count
total = total + 2 * count
except KeyError:
pass
_t = nmersD.keys()
_t.sort()
print "# freq in %s (total %d with pseudocounts)" % (sys.argv[1],
total)
for nmer in _t:
print "%-7s %20.17f" % (nmer, float(nmersD[nmer]) / total)
sys.stdout.flush()
def main():
seqsD = Fasta.load(sys.argv[1])
seqs = seqsD.values()
for w in range(1,7):
allnmers = permute(w)
nmersT = MotifTools.top_nmers(w,seqs,'with counts','purge Ns')
nmersD = {}
total = 0
for nmer in allnmers:
nmersD[nmer] = 1 #Pseudo count
total = total + 1
for nmer,count in nmersT[:]:
try:
rc = MotifTools.revcomplement(nmer)
nmersD[nmer] = nmersD[nmer] + count
nmersD[rc] = nmersD[rc] + count
total = total + 2*count
except KeyError:
pass
_t = nmersD.keys()
_t.sort()
print "# freq in %s (total %d with pseudocounts)"%(sys.argv[1],total)
for nmer in _t:
print "%-7s %20.17f"%(nmer,float(nmersD[nmer]) / total)
sys.stdout.flush()
def info2seeds(N,infofile,probefile,species='YEAST'):
G = ProbeSet(species)
IDs = G.ids_from_file(probefile)
Q = EM.theMarkovBackground.zeroth()
seqs = Fasta.seqs(infofile)
if not N:
nmers = seqs
else:
nmers= MotifTools.top_nmers(N,seqs)
if len(nmers) > 1000: nmers = nmers[0:1000]
print "Scoring enrichment of %d nmers from %s"%len(nmers,infofile)
sys.stdout.flush()
nmers_scoresT = []
for nmer in nmers:
if nmer.isalpha():
p = G.p_value(nmer,IDs,'') #'verbose'
nmers_scoresT.append((nmer,p))
nmers_scoresT.sort(lambda x,y: cmp(x[1],y[1]))
last = min(20,len(nmers_scoresT))
models = []
for i in range(last):
seq = nmers_scoresT[i][0]
m = MotifTools.Motif('',Q)
m.compute_from_text(seq,0.1)
models.append(m)
for tup in nmers_scoresT[0:40]:
print tup
return(models)
def main(fastafile, outDirectory): # !! 1/2/09 AD added 'fastafile' var and changed 'if __name__' as way to call this from script.
seqsD = Fasta.load(fastafile)
seqs = seqsD.values()
output = []
for w in range(1,7):
allnmers = permute(w)
nmersT = MotifTools.top_nmers(w,seqs,'with counts','purge Ns')
nmersD = {}
total = 0
for nmer in allnmers:
nmersD[nmer] = 1 #Pseudo count
total = total + 1
for nmer,count in nmersT[:]:
try:
rc = MotifTools.revcomplement(nmer)
nmersD[nmer] = nmersD[nmer] + count
nmersD[rc] = nmersD[rc] + count
total = total + 2*count
except KeyError:
pass
_t = nmersD.keys()
_t.sort()
output.append("# freq in %s (total %d with pseudocounts)\n"%(fastafile.split('/')[-1],total)) # AD 02-27-09 added a '\n' to make file look right
for nmer in _t:
output.append( "%-7s %20.17f\n"%(nmer,float(nmersD[nmer]) / total)) # AD 02-27-09 added a '\n' to make file look right
# open output file and write out results
outFile = '%s/%s.freq' % (outDirectory, fastafile.split('/')[-1])
outFile = open(outFile, 'w')
for index in output:
outFile.write(index)
def Reduce_Nmers(Info):
print 'COMPUTING Nmers ....'
mseqs = ReduceInfo2seqs(Info,70, lambda L: MotifTools.top_nmers(6,L)[0:3])
print "Combining representative sequences...: "
for i in range(len(mseqs)):
i = i + 1
print '\t%s'%mseqs[i-1],
if (i%5 == 0): print
print
top_seq_pairs = MotifTools.top_nmers(5,mseqs,1)
total_nmers = 0
for (mner,count) in top_seq_pairs:
total_nmers = total_nmers + count
for (nmer,count) in top_seq_pairs[0:8]:
print "RESULT: %s\t%2d (%5.2f%%) occurences: "%(nmer,count,
100*float(count)/total_nmers),
for bsite in Info.query['bsites']:
seq = bsite.cleantxt()
(max,s1,s2) = MotifTools.compare_seqs(nmer,seq)
print ' %s vs %s %4.2f correct'%(s1,s2,max)
def freq_from_seqs_old(self,seqs):
self.highestorder = 4
for depth in range(1,6):
nmersT = MotifTools.top_nmers(depth, seqs, "TUPLES")
self.nmers_by_size[depth] = map(lambda x:x[0],nmersT)
total = 0
for nmer,count in nmersT:
total = total + count
for nmer,count in nmersT:
rc = MotifTools.revcomplement(nmer)
if nmer == rc: #correct top_nmers
f = float(count)/total #palindrome count
else:
f = float(count)/total/2
self.F[nmer] = f
self.F[rc] = f
for depth in range(0): #For debugging
total = 0
for k in self.F.keys():
if len(k) == depth:
total = total + self.F[k]
print k, self.F[k]
print depth,total
def study_seqs(self,seqs):
for depth in range(1,6):
nmersT = MotifTools.top_nmers(depth, seqs, "TUPLES")
total = 0
for nmer,count in nmersT:
total = total + count
rc = MotifTools.revcomplement(nmer)
for nmer,count in nmersT:
f = math.log(float(count)/total)/math.log(2)
f_2 = math.log(0.5 * float(count)/total)/math.log(2)
rc = MotifTools.revcomplement(nmer)
if rc != nmer:
self.D[nmer] = f_2
self.D[rc] = f_2
else:
self.D[nmer] = f
for depth in range(0):
total = 0
for k in self.D.keys():
if len(k) == depth:
total = total + pow(2,self.D[k])
print k, pow(2,self.D[k])
print depth,total
self.highestorder = 5
def freq_from_seqs(self,seqs):
self.highestorder = 6
for w in range(1,7):
allnmers = permute(w)
nmersT = MotifTools.top_nmers(w,seqs,'with counts','purge Ns')
self.nmers_by_size[w] = allnmers[:]
nmersD = {}
total = 0.0
for nmer in allnmers: #Pseudo count
nmersD[nmer] = 1
total = total + 1
for nmer,count in nmersT:
try:
rc = MotifTools.revcomplement(nmer)
nmersD[nmer] = nmersD[nmer] + count
nmersD[rc] = nmersD[rc] + count
total = total + 2*count
except KeyError:
pass
for nmer in nmersD.keys():
rc = MotifTools.revcomplement(nmer)
f = nmersD[nmer]/total
self.F[nmer] = f
self.F[rc] = f