def showdiffXvert(motif, seq, OVLP_FCN=None, DIFF_FCN=None):
'''
The funtion converts the sequence to a Motif, computes the D
of the best alignment, and prints the alignment that generated
that D.
'''
MSOdiff = minshortestoverhangdiff
if not OVLP_FCN: OVLP_FCN = lambda A, B: min(min(A.width, B.width) - 1, 7)
bg = motif.background
other = MotifTools.Motif_from_text(seq, bg=bg)
ovlp = OVLP_FCN(motif, other)
diff = MSOdiff(motif, other, ovlp, DFUNC=DIFF_FCN)
offset, rcflag = MSOdiff(motif, other, ovlp, 'want_offset', DFUNC=DIFF_FCN)
if rcflag: m = other.revcomp()
else: m = other
print 'MSOdiff: %8.4f %s%s%s' % (diff, ' ' * 15, motif.oneletter, ' ' *
(30 - motif.width))
print ' %8s %s%s%s' % (' ', ' ' *
(15 + offset), m.oneletter, ' ' *
(30 - offset - other.width))
return diff
def main():
fsa_fcn = up_and_no_N
parse()
FID = open(sys.argv[1])
tokss = [x.strip().split(',') for x in FID.readlines()]
FID.close()
D = {}
for expt,motif,score,source in tokss:
print expt,motif
if expt == 'Category': continue
if motif == 'x': continue
motif = MotifTools.Motif_from_text(motif)
motif.kellis = float(score)
motif.source = source
try: D[expt].append(motif)
except: D[expt] = [motif]
for expt,motifs in D.items():
root = expt
ext = 'cons'
if root[0:3] == 'Rnd':
num = re.sub('.*_','',root)
if len(num) == 1:
root = re.sub('_','_00',root)
else:
root = re.sub('_','_0',root)
root = re.sub('Rnd','random_',root)
outname = '%s.t%s'%(root,ext)
print '%-18s --> %s'%(root,outname)
sys.stdout.flush()
motifs2tamo(motifs,outname)
try:
pass
#tamo2tamo(filename,outname)
except:
print "Error: Could not convert %s [[ %s ]]"%(
filename, outname)
def main():
if len(sys.argv) < 2:
print "Usage: %s <fasta_file> [width = None ] [options]"%(re.sub('^.*/','',sys.argv[0]))
print "Options include:"
print ""
print " EM Parameters:"
print " -beta [0.01] Beta for pseudocounts"
print " -seedbeta[0.02] Beta for pseudocounts for seeds from text"
print " -gamma [0.2] Gamma (fraction of sequences)"
print " -delta [0.001] Convergence criteria"
print " "
print " Seeds (not actually proper priors)"
print " -prior Seqences or motifs for seeds (may be repeated)"
print " -top N [0] Include w-mers in top N probes"
print " -gap string sample gapped motifs"
# print " -TF Seed with (all) TRANSFAC PSSMs (buggy)"
print " -kmerseeds Use kmers with best enrichment score as seeds for EM"
print " -pad add NN..NN to seed"
print " "
print " Genome / Background model "
print " -human (250,1000) Use Human Background model"
print " -g genome.fsa Use specicied Fasta file as background (searches first for matching frequency file)"
# print " -Y2K, -Y5C Use Yeast Upstream Intergenic regions (2000, 500)"
# print " -B Use Bacterial Orfs"
print " "
print "Examples:"
print " %s t.fsa 5 -prior GGGTA -prior AAAAAC "%(sys.argv[0].split('/')[-1])
print " will start an EM with 3 seeds: GGGTA, AAAAA, and AAAAC"
print
print " %s t.fsa 5 -info CUP9.info -gamma 0.5 "%(sys.argv[0].split('/')[-1])
print " will start an EM with Enriched seeds in CUP9.info, with"
print " Gamma expectation of 50% of all probes"
print
print " %s t.fsa -prior MCM1_5.tamo:0 "%(sys.argv[0].split('/')[-1])
print " will start an EM with 0th motif of the file MCM1_5.tamo"
print " as a seed"
print
sys.exit(1)
fastafile = sys.argv[1]
#Echo the command line
print "#" + ' '.join(map(lambda x: re.sub(' ','\ ',x), sys.argv))
if sys.argv[2].isdigit():
width = sys.argv[2]
else: width = None
algorithm = ''
beta = ''
seedbeta = ''
deltamin = ''
gamma = 0.2
infofile = ''
seedmodels= []
species = 'YEAST'
valid_tfs = [] #NOT USED
gapped_syl= None
gapflank = 0
gapweight = 0.2
enrichfact= 0.7
pmax = 0 #False
TFSEEDS = 0
TFMids = []
pad = None
bgfile = None
seed_count = 0 #Default: Take the top 0
seed_s = [] #Initialize seq array
'''Parse command-line arguments'''
for tok,i in zip(sys.argv,xrange(len(sys.argv))):
if tok == '-top' : seed_count = int(sys.argv[i+1])
elif tok == '-greedy': algorithm = "GREEDY"
elif tok == '-prior' : seed_s.append(sys.argv[i+1])
elif tok == '-beta' : beta = float(sys.argv[i+1])
elif tok == '-seedbeta': seedbeta = float(sys.argv[i+1])
elif tok == '-gamma' : gamma = float(sys.argv[i+1])
elif tok == '-delta' : deltamin = float(sys.argv[i+1])
elif tok == '-kmerseeds' : infofile = 1
elif tok == '-valid' : valid_tfs.append(sys.argv[i+1]) #NOT USED
elif tok == '-w' : width = sys.argv[i+1]
elif tok == '-width' : width = sys.argv[i+1]
elif tok == '-gap' : gapped_syl = sys.argv[i+1]
elif tok == '-gapflank' :gapflank = int(sys.argv[i+1])
elif tok == '-gapweight':gapweight = float(sys.argv[i+1])
elif tok == '-enrichfact':enrichfact= float(sys.argv[i+1])
elif tok == '-pmax' : pmax = 1
elif tok == '-Y2K' : species = "YEAST_2000_UP"
elif tok == '-Y5C' : species = "YEAST_500_UP"
elif tok == '-B' : species = "BAC_ORF"
elif tok == '-Ch22' : species = "Ch22"
elif tok == '-genome': species = sys.argv[i+1]
elif tok == '-pad' : pad = "TRUE"
elif tok == '-bgfile': bgfile = sys.argv[i+1]
elif tok == '-TF' : #NOT USED (TRANSFAC NOT SUPPLIED WITH DISTRIBUTION)
TFSEEDS = 1
for j in range(i+1,len(sys.argv)):
if re.match('M0',sys.argv[j]):
TFMids.append(sys.argv[j])
else:
break
elif tok == '-human' :
_s = ''
if sys.argv[i+1].isdigit(): _s = '_'+sys.argv[i+1]
else: _s = ''
species = 'HUMAN'+_s
if infofile: infofile = fastafile
if bgfile:
EM.loadMarkovBackground(bgfile)
elif not ('-random_background' in sys.argv or '-nomarkov' in sys.argv):
EM.loadMarkovBackground(species)
else:
EM.theMarkovBackground = EM.Zeroth()
fsaD = Fasta.load(fastafile)
Fasta.delN(fsaD)
seqs = fsaD.values()
probes = fsaD.keys()
all_seqs = seqs
seed_s.extend(seqs[0:min(seed_count,len(seqs))])
if infofile and width=='info':
width = info2width(infofile)
elif width != None:
width = int(width)
#Alternate source of seeds
if infofile:
if 1 or width:
seedmodels.extend(info2seeds(width,infofile,fastafile,species))
else:
print 'Error: need to specify motif width w/ .info file'
#Any -prior pointers to motifs in other files?
(seed_s, motifs) = parse_priors(seed_s)
seedmodels.extend(motifs)
#Should we get seeds from TRANSFAC?
if TFSEEDS: #NOT USED
tf = []
D = tfmats()
if not TFMids:
keys = D.keys()
else:
keys = []
for TFMid in TFMids:
for key in D.keys():
if key[0:6] == TFMid:
keys.append(key)
break
for key in keys:
m = D[key]
m.seednum = int(re.sub('M0*','',key.split()[0]))
m.seedtxt = '%-24s %s'%(m,key)
tf.append(m)
tf.sort(lambda x,y: cmp(x.seednum,y.seednum))
seedmodels.extend(tf)
#seedmodels.append(tf[33])
if gapped_syl:
gapped_priors = gapped_motifs(gapped_syl)
gapped_priors = map(lambda x:'N'+x+'N', gapped_priors)
seed_s.extend(gapped_priors)
if pad:
print '# Padding models with NN-m-NN'
newmodels = []
left = MotifTools.Motif_from_text('@')
right = MotifTools.Motif_from_text('N')
for m in seedmodels:
newmodels.append(left + m + right)
print left + m + right
seedmodels = newmodels
'''
Set everything up and GO!!
'''
global theEM
theEM = EM.EM(seed_s,[],width,"VERBOSE")
if beta: theEM.beta = beta
if deltamin: theEM.deltamin = deltamin
if seedbeta: theEM.seedbeta = seedbeta
theEM.param['gamma'] = gamma
theEM.seqs.extend(all_seqs)
theEM.models = seedmodels
theEM.gapflank = gapflank
theEM.gapweight = gapweight
theEM.report()
theEM.EM_Cstart() #GO!!
#print "#Sorting candidates"
#sys.stdout.flush()
#EM.candidates.sort(lambda x,y: cmp(y.MAP,x.MAP))
'''
Compute some metrics
'''
print "#Loading Genome %s"%species ; sys.stdout.flush()
Genome = ProbeSet(species,enrichfact)
ids = Genome.ids_from_file(fastafile)
for C in theEM.candidates:
if not pmax:
C.pssm.pvalue = Genome.p_value(C.pssm,ids,'verbose')
C.pssm.church = Genome.church(C.pssm,ids)
C.pssm.frac = Genome.frac(C.pssm,probes,None,0.7)
else:
(p,frac) = Genome.best_p_value(C.pssm,ids)
C.pssm.pvalue = p
C.pssm.threshold = frac * C.pssm.maxscore
print "Bests:",p,frac
matching = Genome.matching_ids(C.pssm,[],factor=0.7)
matchbound = [x for x in matching if x in probes]
C.pssm.numbound = len(probes)
C.pssm.nummotif = len(matching)
C.pssm.numboundmotif = len(matchbound)
sys.stdout.flush()
'''
Print out all motifs (sorted by Enrichment) in an AlignACE-like form
'''
theEM.candidates.sort(lambda x,y: cmp(x.pssm.pvalue,y.pssm.pvalue))
for C,i in zip(theEM.candidates,range(len(theEM.candidates))):
C.pssm.maxscore = -100 #May have side effects. Recompute when done
if C.pssm.valid: #NOT USED
_t = C.pssm.valid
if not _t[0]:
vstring = "(--- %8.4f %8.4f %s)"%(_t[1],_t[2],_t[3])
else:
vstring = "(HIT %8.4f %8.4f %s)"%(_t[1],_t[2],_t[3])
else:
vstring = ''
C.pssm._maxscore() #Recomputed
MotifTools.print_motif(C.pssm,20,i)
sys.stdout.flush()
continue
#Antiquated stuff -- Remove !!
print "Log-odds matrix for Motif %3d %s"%(i,C)
C.pssm._print_ll()
print "Sequence Logo"
C.pssm._print_bits()
flush()
#print '# %3d matching sequences at 90%%'%len(C.pssm.bestseqs(C.pssm.maxscore * 0.9))
flush()
m = C.pssm
if not m.__dict__.has_key('gamma'): m.gamma = None #Kludge to deal w/ old shelves
if m.seedtxt: print "Seed: %3d %s"%(i,m.seedtxt)
if m.source: print "Source: ",m.source
if m.gamma: print "Gamma: %7.5f"%m.gamma
if m.threshold: print "Threshold: %5.2f"%m.threshold
#if C.pssm.seedtxt:
# print 'Seed %3d %-25s'%(i,C.pssm.seedtxt)
if C.pssm.church != None: vstring = 'ch: %5.2f %s'%(
math.fabs(math.log(C.pssm.church)/math.log(10)), vstring)
print "Motif %3d %-25s nlog(p): %6.3f %s"%(i,C,-math.log(C.pssm.pvalue)/math.log(10),vstring)
if C.pssm.threshold:
print "Threshold: %6.3f %4.1f%%"%(
C.pssm.threshold, 100.0*C.pssm.threshold/C.pssm.maxscore)
C.pssm.maxscore = -1e100 #May have side effects. Recompute when done
for seq in C.wmers:
print seq,i,C.pssm.scan(seq)[2][0]
C.pssm._maxscore() #Recomputed
print '*'*len(seq)
print "MAP Score: %f"%C.MAP
sys.stdout.flush()
sys.stdout.flush()
sys.exit(0) #Avoid ridiculous python cleanup times
# generate PWM for indicated motifs
#module load TAMO (on hpc)
import sys
from TAMO import MotifTools
#input file: motif list
input=open(sys.argv[1], 'r')
motif=[]
for line in input:
if line.startswith("#"):
pass
else:
line=line.strip("\n").strip("\r").strip()
motif.append(line)
input.close()
print (motif)
pw=[]
for i in range(0, len(motif)):
m=MotifTools.Motif_from_text(motif[i])
pw.append(m)
MotifTools.save_motifs(pw,sys.argv[1]+'.tamo')
def averagetxts(txts, ovlp=2, VERBOSE=1):
motifs = [MotifTools.Motif_from_text(x.strip()) for x in txts]
return averagemotifs(motifs, ovlp, VERBOSE=VERBOSE)
def testdiff(t1, t2, OVLP_FCN=None, DIFF_FCN=None):
m1 = MotifTools.Motif_from_text(t1, bg=MotifTools.YEAST_BG)
showdiffXvert(m1, t2, OVLP_FCN, DIFF_FCN)
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], "f:m:n:L:t:a:S:", ["help", "output="])
except getopt.GetoptError:
usage()
sys.exit(1)
if not opts:
usage()
sys.exit(1)
print "#" + ' '.join(sys.argv)
fastafile, motiffile, motifnums, labels, thresh = (None, None, [], None, 0.7)
ambigs = []
scale = 50.0 / 1000.0
motifs = []
for opt, value in opts:
#print opt, value
if opt == '-f': fastafile = value
elif opt == '-m': motifs.extend(MotifTools.txt2motifs(value))
elif opt == '-n': motifnums = [int(x) for x in value.split(',')]
elif opt == '-L': labels = list(value)
elif opt == '-t': thresh = float(value)
elif opt == '-a': ambigs.extend(value.split(','))
elif opt == '-S': scale = float(value)
probes = Fasta.load(fastafile)
if motiffile:
motifs.extend(TAMO.tamofile2motifs(motiffile))
if ambigs:
for ambig in ambigs:
motifs.append( MotifTools.Motif_from_text(ambig,0.1) )
if not motifnums: motifnums = range(len(motifs))
print '# %d: %s'%(len(motifs),motifnums)
for i in range(len(motifnums)):
motif = motifs[motifnums[i]]
if labels and i < len(labels):
txt = labels[i]
else:
txt = '%d'%i
print '%-3s : %s %5.2f (%4.2f)'%(txt,motif,thresh*motif.maxscore,thresh)
probehits = {}
for key in probes.keys():
hits_by_motif = []
save_flag = 0
if re.search('[BDHU]',probes[key]): continue
for num in motifnums:
result = motifs[num].scan(probes[key],thresh*motif.maxscore)
if result[0]:
hits_by_motif.append(result)
save_flag = 1
else:
hits_by_motif.append(None)
if save_flag:
probehits[key]=hits_by_motif
#scale = .1
maxw = 40
for key in probehits.keys():
l = len(probes[key])
a = list('-'* int(scale*l) )
a.extend( list(' '*10 ) )
desc = []
matches = probehits[key]
for i in range(len(matches)):
if matches[i]:
subseqs,endpoints,scores = matches[i]
for idx in range(len(subseqs)):
start,stop = endpoints[idx]
subseq = subseqs[idx]
score = scores[idx]
if labels and (i<len(labels)): ID = labels[i]
else : ID = '%d'%i
desc.append('%s %s %d-%d %4.2f '%(ID,subseq,start,stop,score))
start = int(start*scale)
for offset in range(10):
if a[start+offset] == '-':
if labels and (i < len(labels)):
a[start+offset] = labels[i]
else:
a[start+offset] = '%d'%i
break
print '%-14s %s'%(key,''.join(a)),
print ' '*max(0,maxw-len(a)), '| '.join(['%-27s'%x for x in desc])
print
print "Found matches in %d of %d input probes"%(len(probehits),len(probes))