modelILS = build_epoch_seperated_model(
3,
# we start with a,b,c.
[
# merge a and b to '0', c continues as '1'
[0, 0, 1],
# and now '0' and '1' is merged to a new '0'
[0, 0]
],
[1, estates, estates])
nstates = len(modelILS.tree_map)
names = ["bonobo", "pantro2", "hg18"]
init_ILS = (1.0e6 * u, 4.5e6 * u, i_c, i_r)
all_obs = []
total_L = 0
for seq in seqs:
# each sequence creates a new column map extended with any new columns that
# might be seen.
obs, colmap = readObservations(seq, names, COL_MAP)
COL_MAP = colmap
total_L += len(obs)
all_obs.append(obs)
print "%.2fMbp of data in total" % (total_L / 1e6)
L, est = estimate_ILS(modelILS, all_obs, *init_ILS, outfile="/dev/stdout")
print 'Final results:'
print "\t".join(map(str, [L] + est))
def runILSctmc(seqs, **args):
global COL_MAP
NeRef = args["NeRef"]
g = args["g"]
u = args["u"]
i_r = args["r"]
i_N1 = args["N1"]
i_N2 = args["N12"]
i_N3 = args["N123"]
i_c1 = 1.0/(2*g*u*i_N1)
i_c2 = 1.0/(2*g*u*i_N2)
i_c3 = 1.0/(2*g*u*i_N3)
i_t1 = u * args["T12"] / g / (2*NeRef)
i_t2 = u * args["T123"] / g / (2*NeRef)
startvalues = dict( [ (name,eval(name)) for name in ['i_t1', 'i_t2', 'i_c1', 'i_c2', 'i_c3', 'i_r'] ] )
# # generation time and mutation rate
# g = 20
# u = 1e-9
#
# # initial values for recombination rate, population size/coalescence rate and
# # migration rate.
# i_r = 0.4
# i_N = 100e3
# i_c = 1.0/(2*g*u*i_N)
# i_t1 = 3.7e6*u
# i_t2 = 5.95e6*u
estates = 4
print >>sys.stderr, 'running with %d epoch states' % estates
# inst = int(sys.argv[1])
#
# seqs = ["data/x_ils_%i.fa" % inst]
modelILS = build_epoch_seperated_model(3, [[0,0,1], [0,0]], [1,estates,estates])
nstates = len(modelILS.tree_map)
names = ["'1'", "'2'", "'0'"]
#names = ["'0'", "'2'", "'1'"]
all_obs = []
forwarders = []
COL_MAP = dict((v,i) for i,v in enumerate(product('ACGT', repeat=3)))
for seq in seqs:
# each sequence creates a new column map extended with any new columns that
# might be seen.
obs, colmap = readObservations(seq, names, COL_MAP)
all_obs.append(obs)
# print len(COL_MAP)
doEstimate = False
L = None
estimates = list()
if doEstimate:
for obs in all_obs:
print 'next obs:'
ffd, foutname = tempfile.mkstemp()
print ' temp fd/name:', ffd, foutname
fout = os.fdopen(ffd, 'w')
L = len(obs)
for j in xrange(L-1):
o = obs[j]
print >>fout, o,
print >>fout, obs[j]
fout.close()
print ' written, creating forwarder'
f = Forwarder.fromSequence(seqFilename = foutname, alphabetSize = len(COL_MAP))
#f = Forwarder(seqFilename = foutname, nStates = len(modelILS.tree_map), nObservables = len(COL_MAP))
print ' - done.'
forwarders.append(f)
os.system("rm %s" % foutname)
L, estimates = estimate_ILS(modelILS, forwarders, i_t1, i_t2, i_c1, i_c2, i_c3, i_r, outfile="/dev/null")
i_t1, i_t2, i_c1, i_c2, i_c3, i_r = estimates
estimates = dict( [ (name,eval(name)) for name in ['i_t1', 'i_t2', 'i_c1', 'i_c2', 'i_c3', 'i_r'] ] )
#print 'Estimates:'
#print "\t".join(map(str, [L] + est))
if "hook" in args:
args["hook"].run(modelILS, COL_MAP, all_obs, [i_c1, i_c2, i_c3], [i_r]*3, [0]*3, [0, i_t1, i_t2])
return L, estimates, startvalues
3,
# we start with a,b,c.
[
# merge a and b to '0', c continues as '1'
[0,0,1],
# and now '0' and '1' is merged to a new '0'
[0,0]
],
[1,estates,estates])
nstates = len(modelILS.tree_map)
names = ["bonobo", "pantro2", "hg18"]
init_ILS = (1.0e6*u, 4.5e6*u, i_c, i_r)
all_obs = []
total_L = 0
for seq in seqs:
# each sequence creates a new column map extended with any new columns that
# might be seen.
obs, colmap = readObservations(seq, names, COL_MAP)
COL_MAP = colmap
total_L += len(obs)
all_obs.append(obs)
print "%.2fMbp of data in total" % (total_L/1e6)
L, est = estimate_ILS(modelILS, all_obs, *init_ILS, outfile="/dev/stdout")
print 'Final results:'
print "\t".join(map(str, [L] + est))
