def mpat(tr, seqs) :
dseqs = dict(seqs)
for n in getPostOrder(tr) :
data = n.data
if not n.succ :
data.seq = (None,dseqs[n.data.taxon])
else :
s1,s2 = [tr.node(x).data.seq for x in n.succ]
if s1[1] :
if s2[1] :
a = calign.globalAlign(s1[1],s2[1])
data.seq = (calign.createProfile(a),None)
else :
p1,p2 = calign.createProfile(s1[1:]), s2[0]
#assert all([sum(x)==sum(p1[0]) for x in p1])
#assert all([sum(x)==sum(p2[0]) for x in p2])
pa = calign.prof2profAlign(p1,p2)
data.seq = (trimp(pa),None)
#print len(pa)
else :
p1 = s1[0]
if s2[1] :
p2 = calign.createProfile(s2[1:])
else :
p2 = s2[0]
#assert all([sum(x)==sum(p1[0]) for x in p1])
#assert all([sum(x)==sum(p2[0]) for x in p2])
pa = calign.prof2profAlign(p1,p2)
data.seq = (trimp(pa),None)
#print len(pa)
#import pdb; pdb.set_trace()
assert n.id == tr.root
return n.data.seq[0]
def mpa(tr, seqs, scores = defaultMatchScores, trimEnd = None) :
dseqs = dict(seqs)
#scores = (None,None,gapPenalty,feg)
for n in getPostOrder(tr) :
data = n.data
if not n.succ :
data.seq = (None,dseqs[n.data.taxon.strip("'")])
else :
s1,s2 = [tr.node(x).data.seq for x in n.succ]
if s1[1] :
if s2[1] :
a = calign.globalAlign(s1[1],s2[1], scores = scores)
data.seq = (calign.createProfile(a),None)
else :
p1,p2 = calign.createProfile(s1[1:]), s2[0]
pa = calign.prof2profAlign(p1,p2, scores = scores)
data.seq = (trimendsp(pa, trimEnd) if trimEnd is not None else pa,None)
#print len(pa)
else :
p1 = s1[0]
if s2[1] :
p2 = calign.createProfile(s2[1:])
else :
p2 = s2[0]
pa = calign.prof2profAlign(p1,p2, scores = scores)
data.seq = (trimendsp(pa, trimEnd) if trimEnd is not None else pa,None)
#print len(pa)
#import pdb; pdb.set_trace()
assert n.id == tr.root
return n.data.seq[0]
def mpc(seqs, nRefines = 4, gapPenalty = defaultMatchScores.gap) :
al = seqMultiAlign(seqs, scores = defaultMatchScores._replace(gap = gapPenalty))
c0 = stripseq(cons(calign.createProfile(al)))
r = refineSingle(al, gapPenalty = gapPenalty)
c1 = stripseq(cons(calign.createProfile(r)))
cnt = 0
while c0 != c1 and cnt < nRefines:
c0 = c1
r = refineSingle(r, gapPenalty = gapPenalty)
c1 = stripseq(cons(calign.createProfile(r)))
cnt += 1
return c1, r
def refineSingle(al, gapPenalty = defaultMatchScores.gap) :
if not isinstance(al, list) :
al = list(al)
p = calign.createProfile(al)
q = []
for k,s in enumerate(al) :
ps = calign.createProfile([s])
p2 = tuple([[a-b for a,b in zip(x,y)] for x,y in zip(p,ps)])
q.append( calign.profileAlign(s, p2, gapPenalty = gapPenalty) )
return q
def doTheCons(sqs, trh, lengthQuant = 40) :
als = [(lengthQuant*(len(s)//lengthQuant), s) for s in sqs]
als = [x[1] for x in sorted(als, reverse=1)]
scmp = random.sample(sqs, min(5,len(sqs)))
cbest = (None,100000)
for i in range(3) :
al = seqMultiAlign(als)
c = stripseq(cons(calign.createProfile(al)))
# spot check
p = mean(calign.allpairs(c, scmp, report = calign.JCcorrection))/2
if p < cbest[1] :
cbest = (c, p)
if i == 2 or p < trh :
break
if i == 0 :
# try original order
als = sqs
elif i == 1 :
# try random order
als = list(sqs)
random.shuffle(als)
return cbest[0]
def refineAlignment(al, ci = [0], drop = False, mx = -1, rev = False, verbose = False) :
if not isinstance(al, list) :
al = list(al)
p = calign.createProfile(al)
if rev:
can = [(k,s) for k,s in enumerate(al) if all([s[x] == '-' for x in ci])]
else :
can = [(k,s) for k,s in enumerate(al) if any([s[x] != '-' for x in ci])]
if verbose:
print len(al[0]), len(can)
import sys
sys.stdout.flush()
if mx > 0 and len(can) > mx:
return
changed = 0
if len(can) :
pr = calign.createProfile([s for n,s in can])
p2 = tuple([[a-b for a,b in zip(x,y)] for x,y in zip(p,pr)])
if drop:
p2,rx = removeColumns(p2, ci)
for n,s in can:
if len(s.replace('-','')) <= len(p2) :
ra = calign.profileAlign(s, p2)
if drop :
ra = restoreColumns(list(ra),rx, calign.GAP)
al[n] = iton(ra)
if tuple(ra) != sasn(s) :
changed += 1
if changed :
p = calign.createProfile(al)
r = [k for k,i in enumerate(p) if i[calign.GAP] == len(al)]
r1 = toRanges(r)
if r1 :
for a,b in r1[::-1] :
for k in range(len(al)) :
x = al[k]
al[k] = x[:a] + x[b:]
return al,len(al[0]), changed
def seqMultiAlign(seqs, scores = defaultMatchScores, report=False) :
if len(seqs) < 2:
return seqs
a = calign.globalAlign(seqs[0], seqs[1], scores=scores)
ns = 2
p = calign.createProfile(a)
a = tuple(iton(x) for x in a)
for kk,s2 in enumerate(seqs[2:]) :
#print ns
# assert p == calign.createProfile(a)
assert len(a[0]) == len(p) and \
p[0][calign.GAP] != ns and p[-1][calign.GAP] != ns
pad = 20
if len(p)+2*pad < len(s2) :
# enough for sequences start to align
pad = (len(s2) - len(p)) ; assert len(p)+2*pad >= len(s2)
pa,extendLeft,extendRight = calign.profileAlign(s2, p, pad=pad, chop=True,
gapPenalty=defaultMatchScores.gap)
if extendLeft > 0 or extendRight > 0 :
gapProfile = [0,0,0,0,0,ns]
p1 = tuple((list(gapProfile) for k in range(extendLeft))) + p \
+ tuple((list(gapProfile) for k in range(extendRight)))
else :
p1 = p
for k,n in enumerate(pa) :
p1[k][n] += 1
p = p1
if extendLeft > 0 or extendRight > 0 :
fr = '-'*extendLeft
bk = '-'*extendRight
a = tuple((fr + x + bk for x in a))
a = a + (iton(pa),)
ns += 1
if report and (kk+1) % 1000 == 0 :
import sys
print kk+1, len(a[0]),
sys.stdout.flush()
if report: print
return a
def sortByEntropy(seqs) :
alen = len(seqs[0])
trans = not (seqs[0][0] in range(6))
#print "sorting,"
counts = calign.createProfile(seqs)
#print "stage 1,"
cc = [sum([log(x) * x for x in c if x > 0])/len(seqs) - log(len(seqs))
for c in counts]
scc = sorted(zip(cc, count()), reverse=0)
occ = [x[1] for x in scc]
#print "stage 2,"
if trans :
sx = sorted(zip([[ngtoi(x[k]) for k in occ] for x in seqs], count()))
else :
sx = sorted(zip([[x[k] for k in occ] for x in seqs], count()))
#print "stage 3,"
seqsSorted = [k for s,k in sx]
#print "sorted"
return seqsSorted
def createProfile(seqs) : return calign.createProfile(seqs)