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 loadmotif(infile, trimstart=0, trimend=0):
from TAMO import MotifTools
lines = loadlist(infile)
if lines[0] == "A\tC\tG\tT":
ma = []
for l in lines[1:]:
p = l.split("\t")
ma.append({
'A': float(p[0]),
'C': float(p[1]),
'G': float(p[2]),
'T': float(p[3])
})
if trimend == 0: ma = ma[trimstart:]
else: ma = ma[trimstart:-trimend]
return MotifTools.Motif_from_counts(ma)
elif lines[0][0] in 'ACGT':
if trimend == 0: lines = lines[trimstart:]
else: lines = lines[trimstart:-trimend]
return MotifTools.Motif(lines)
else:
na = []
for line in lines:
na.append(list(map(int, line.split())))
ma = []
for i in range(len(na[0])):
ma.append({
'A': na[0][i],
'C': na[1][i],
'G': na[2][i],
'T': na[3][i]
})
return MotifTools.Motif_from_counts(ma)
def test():
motifs = []
betalist = [0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1.0, 2.0, 4.0]
for beta in [1.0]:
m = MotifTools.Motif()
m.compute_from_text('GGTTTCAT', beta) #STE12 binding site
print m
m._print_ll()
print "Against Ste12:"
match = validate(m, "STE12", 'V', 'T')
print "Against Fkh2:"
fmatch = validate(m, "FKH2", 'V', 'T')
print beta, match, fmatch