def outputRates( result, options ):
"""output rates in a grammar."""
trained_model = result.getModel()
pis = trained_model.evaluateTerminalFrequencies()
matrices = trained_model.evaluateRateMatrix()
terminals = pis.keys()
for terminal in terminals:
Q, distance = RateEstimation.getDistanceGTR( pis[terminal], matrices[terminal] )
options.stdout.write("\t%s" % (options.value_format % distance ) )
def runXrate(mali, pairs, options):
from XGram.Generator.Prebuilt import DNA
from XGram.Model import Annotation
import XGram.Run
xgram = XGram.XGram()
if options.xrate_min_increment:
xgram.setMinIncrement(options.xrate_min_increment)
ninput, noutput, nskipped = 0, 0, 0
tempdir = tempfile.mkdtemp()
data = tempdir + "/data"
if options.distance == "K80":
model = DNA.buildModel(substitution_model="k80")
elif options.distance == "JC69":
model = DNA.buildModel(substitution_model="jc69")
elif options.distance == "REV":
model = DNA.buildModel(substitution_model="gtr")
else:
raise "distance %s not implemented for xrate" % (options.distance)
writeModel(model, "input", options)
if options.output_format == "list":
options.stdout.write(
"\t".join(("seq1", "seq2", "distance", "lnL", "alpha", "kappa", "msg")))
if options.with_counts:
options.stdout.write(
"\t%s" % Genomics.SequencePairInfo().getHeader())
options.stdout.write("\n")
for x, y in pairs:
m1 = mali.getSequence(ids[x])
ninput += 1
temp_mali = Mali.Mali()
m2 = mali.getSequence(ids[y])
temp_mali.addSequence(m1.mId, m1.mFrom, m1.mTo, m1.mString)
temp_mali.addSequence(m2.mId, m2.mFrom, m2.mTo, m2.mString)
# if temp_mali.getWidth() < options.min_overlap:
# if options.loglevel >= 1:
# options.stdlog.write("# pair %s-%s: not computed because only %i residues overlap\n" % (mali.getEntry(ids[x]).mId,
# mali.getEntry(ids[y]).mId,
# temp_mali.getWidth()) )
# nskipped += 1
# continue
outfile = open(data, "w")
temp_mali.writeToFile(outfile, format="stockholm",
write_ranges=False,
options=("#=GF NH (%s:1.0)%s;" % tuple(temp_mali.getIdentifiers()),))
outfile.close()
o_alpha, o_kappa = "na", "na"
o_distance = "na"
msg = ""
if options.test_xrate:
for alpha in (0.1, 0.5, 1.0, 1.5):
for beta in (0.1, 0.5, 1.0, 1.5):
model.mGrammar.setParameter("alpha", alpha)
model.mGrammar.setParameter("beta", beta)
result = xgram.train(model, data)
trained_model = result.getModel()
xalpha, xbeta = \
(trained_model.mGrammar.getParameter('alpha'),
trained_model.mGrammar.getParameter('beta'))
# this assumes that the branch length in the input is normalized to 1
# this is the normalization constant
o_distance = options.format % (2 * xbeta + xalpha)
o_kappa = options.format % (xalpha / xbeta)
msg = "alpha=%6.4f, beta=%6.4f" % (xalpha, xbeta)
options.stdout.write("\t".join(("%f" % alpha,
"%f" % beta,
o_distance,
options.format % result.getLogLikelihood(
),
o_alpha,
o_kappa,
msg)))
options.stdout.write("\n")
continue
options.stdout.write("%s\t%s\t" % (m1.mId, m2.mId))
if options.distance in ("K80", ):
result = xgram.train(model, data)
trained_model = result.getModel()
elif options.distance in ("REV", ):
result = xgram.train(model, data)
trained_model = result.getModel()
alpha, beta, gamma, delta, epsilon, theta = \
(trained_model.mGrammar.getParameter('alpha'),
trained_model.mGrammar.getParameter('beta'),
trained_model.mGrammar.getParameter('gamma'),
trained_model.mGrammar.getParameter('delta'),
trained_model.mGrammar.getParameter('epsilon'),
trained_model.mGrammar.getParameter('theta'))
pi = trained_model.evaluateTerminalFrequencies(('A0',))[('A0',)]
matrix = trained_model.evaluateRateMatrix(('A0',))[('A0',)]
q, d = RateEstimation.getDistanceGTR(pi, matrix)
o_distance = options.format % (d)
o_kappa = ""
msg = "alpha=%6.4f, beta=%6.4f, gamma=%6.4f, delta=%6.4f, epsilon=%6.4f, theta=%6.4f" % (
alpha, beta, gamma, delta, epsilon, theta)
elif options.distance in ('JC69', ):
result = xgram.buildTree(model, data)
if options.distance == "K80":
alpha, beta = \
(trained_model.mGrammar.getParameter('alpha'),
trained_model.mGrammar.getParameter('beta'))
# this assumes that the branch length in the input is normalized to 1
# this is the normalization constant
o_distance = options.format % (2 * beta + alpha)
o_kappa = options.format % (alpha / beta)
msg = "alpha=%6.4f, beta=%6.4f" % (alpha, beta)
alpha = "na"
elif options.distance == "JC69":
tree = result.getTree()
# multiply distance by tree, as rates are set to 1 and
# thus the matrix is scaled by a factor of 3
o_distance = options.format % (
3.0 * float(re.search("\(\S+:([0-9.]+)\)", tree).groups()[0]))
o_kappa = "na"
msg = ""
writeModel(result.mModel, "trained", options)
options.stdout.write("\t".join((o_distance,
options.format % result.getLogLikelihood(
),
o_alpha,
o_kappa,
msg)))
if options.with_counts:
info = Genomics.CalculatePairIndices(
mali[ids[x]], mali[ids[y]], with_codons=options.is_codons)
options.stdout.write("\t%s" % (str(info)))
options.stdout.write("\n")
shutil.rmtree(tempdir)
def runXrate(mali, pairs, options):
from XGram.Generator.Prebuilt import DNA
from XGram.Model import Annotation
import XGram.Run
xgram = XGram.XGram()
if options.xrate_min_increment:
xgram.setMinIncrement(options.xrate_min_increment)
ninput, noutput, nskipped = 0, 0, 0
tempdir = tempfile.mkdtemp()
data = tempdir + "/data"
if options.distance == "K80":
model = DNA.buildModel(substitution_model="k80")
elif options.distance == "JC69":
model = DNA.buildModel(substitution_model="jc69")
elif options.distance == "REV":
model = DNA.buildModel(substitution_model="gtr")
else:
raise "distance %s not implemented for xrate" % (options.distance)
writeModel(model, "input", options)
if options.output_format == "list":
options.stdout.write("\t".join(
("seq1", "seq2", "distance", "lnL", "alpha", "kappa", "msg")))
if options.with_counts:
options.stdout.write("\t%s" %
Genomics.SequencePairInfo().getHeader())
options.stdout.write("\n")
for x, y in pairs:
m1 = mali.getSequence(ids[x])
ninput += 1
temp_mali = Mali.Mali()
m2 = mali.getSequence(ids[y])
temp_mali.addSequence(m1.mId, m1.mFrom, m1.mTo, m1.mString)
temp_mali.addSequence(m2.mId, m2.mFrom, m2.mTo, m2.mString)
# if temp_mali.getWidth() < options.min_overlap:
# if options.loglevel >= 1:
# options.stdlog.write("# pair %s-%s: not computed because only %i residues overlap\n" % (mali.getEntry(ids[x]).mId,
# mali.getEntry(ids[y]).mId,
# temp_mali.getWidth()) )
## nskipped += 1
# continue
outfile = open(data, "w")
temp_mali.writeToFile(outfile,
format="stockholm",
write_ranges=False,
options=("#=GF NH (%s:1.0)%s;" %
tuple(temp_mali.getIdentifiers()), ))
outfile.close()
o_alpha, o_kappa = "na", "na"
o_distance = "na"
msg = ""
if options.test_xrate:
for alpha in (0.1, 0.5, 1.0, 1.5):
for beta in (0.1, 0.5, 1.0, 1.5):
model.mGrammar.setParameter("alpha", alpha)
model.mGrammar.setParameter("beta", beta)
result = xgram.train(model, data)
trained_model = result.getModel()
xalpha, xbeta = \
(trained_model.mGrammar.getParameter('alpha'),
trained_model.mGrammar.getParameter('beta'))
# this assumes that the branch length in the input is normalized to 1
# this is the normalization constant
o_distance = options.format % (2 * xbeta + xalpha)
o_kappa = options.format % (xalpha / xbeta)
msg = "alpha=%6.4f, beta=%6.4f" % (xalpha, xbeta)
options.stdout.write("\t".join(
("%f" % alpha, "%f" % beta, o_distance,
options.format % result.getLogLikelihood(), o_alpha,
o_kappa, msg)))
options.stdout.write("\n")
continue
options.stdout.write("%s\t%s\t" % (m1.mId, m2.mId))
if options.distance in ("K80", ):
result = xgram.train(model, data)
trained_model = result.getModel()
elif options.distance in ("REV", ):
result = xgram.train(model, data)
trained_model = result.getModel()
alpha, beta, gamma, delta, epsilon, theta = \
(trained_model.mGrammar.getParameter('alpha'),
trained_model.mGrammar.getParameter('beta'),
trained_model.mGrammar.getParameter('gamma'),
trained_model.mGrammar.getParameter('delta'),
trained_model.mGrammar.getParameter('epsilon'),
trained_model.mGrammar.getParameter('theta'))
pi = trained_model.evaluateTerminalFrequencies(('A0', ))[('A0', )]
matrix = trained_model.evaluateRateMatrix(('A0', ))[('A0', )]
q, d = RateEstimation.getDistanceGTR(pi, matrix)
o_distance = options.format % (d)
o_kappa = ""
msg = "alpha=%6.4f, beta=%6.4f, gamma=%6.4f, delta=%6.4f, epsilon=%6.4f, theta=%6.4f" % (
alpha, beta, gamma, delta, epsilon, theta)
elif options.distance in ('JC69', ):
result = xgram.buildTree(model, data)
if options.distance == "K80":
alpha, beta = \
(trained_model.mGrammar.getParameter('alpha'),
trained_model.mGrammar.getParameter('beta'))
# this assumes that the branch length in the input is normalized to 1
# this is the normalization constant
o_distance = options.format % (2 * beta + alpha)
o_kappa = options.format % (alpha / beta)
msg = "alpha=%6.4f, beta=%6.4f" % (alpha, beta)
alpha = "na"
elif options.distance == "JC69":
tree = result.getTree()
# multiply distance by tree, as rates are set to 1 and
# thus the matrix is scaled by a factor of 3
o_distance = options.format % (
3.0 * float(re.search("\(\S+:([0-9.]+)\)", tree).groups()[0]))
o_kappa = "na"
msg = ""
writeModel(result.mModel, "trained", options)
options.stdout.write("\t".join(
(o_distance, options.format % result.getLogLikelihood(), o_alpha,
o_kappa, msg)))
if options.with_counts:
info = Genomics.CalculatePairIndices(mali[ids[x]],
mali[ids[y]],
with_codons=options.is_codons)
options.stdout.write("\t%s" % (str(info)))
options.stdout.write("\n")
shutil.rmtree(tempdir)
