def __call__(self, X_logs):
"""
The vth entry of X corresponds to the log rate of the branch above v.
Return the quantity to be minimized (the neg log likelihood).
@param X: vector of branch rate logs
@return: negative log likelihood
"""
X = [math.exp(x) for x in X_logs]
B_subs = {}
for v_parent, v_child in self.R:
edge = frozenset([v_parent, v_child])
r = X[v_child]
t = self.B[edge]
B_subs[edge] = r * t
newick_string = FtreeIO.RBN_to_newick(self.R, B_subs, self.N_leaves)
tree = Newick.parse(newick_string, Newick.NewickTree)
# define the rate matrix object; horrible
dictionary_rate_matrix = RateMatrix.get_jukes_cantor_rate_matrix()
ordered_states = list('ACGT')
row_major_rate_matrix = MatrixUtil.dict_to_row_major(
dictionary_rate_matrix, ordered_states, ordered_states)
rate_matrix_object = RateMatrix.RateMatrix(
row_major_rate_matrix, ordered_states)
# get the log likelihood
ll = PhyLikelihood.get_log_likelihood(
tree, self.alignment, rate_matrix_object)
return -ll
def test_likelihood_calculation(self):
# get a tree
tree = Newick.parse(sample_tree_string, Newick.NewickTree)
# get a model
input_xml_string = get_sample_xml_string()
model = deserialize_mixture_model(input_xml_string)
# get an alignment
alignment = Fasta.CodonAlignment(StringIO(long_sample_codon_alignment_string))
# get the likelihood
log_likelihood = PhyLikelihood.get_log_likelihood(tree, alignment, model)
def test_likelihood_calculation(self):
# get a tree
tree = Newick.parse(sample_tree_string, Newick.NewickTree)
# get a model
input_xml_string = get_sample_xml_string()
model = deserialize_mixture_model(input_xml_string)
# get an alignment
alignment = Fasta.CodonAlignment(
StringIO(long_sample_codon_alignment_string))
# get the likelihood
log_likelihood = PhyLikelihood.get_log_likelihood(
tree, alignment, model)
def get_response_content(fs):
# get the tree
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
# get the alignment
try:
alignment = Fasta.Alignment(fs.fasta.splitlines())
alignment.force_nucleotide()
except Fasta.AlignmentError as e:
raise HandlingError(e)
# get the log likelihood
dictionary_rate_matrix = RateMatrix.get_jukes_cantor_rate_matrix()
ordered_states = list('ACGT')
row_major_rate_matrix = MatrixUtil.dict_to_row_major(
dictionary_rate_matrix, ordered_states, ordered_states)
rate_matrix_object = RateMatrix.RateMatrix(
row_major_rate_matrix, ordered_states)
log_likelihood = PhyLikelihood.get_log_likelihood(
tree, alignment, rate_matrix_object)
# return the response
return str(log_likelihood) + '\n'
def get_response_content(fs):
# init the response and get the user variables
out = StringIO()
nleaves = fs.nleaves
nvertices = nleaves * 2 - 1
nbranches = nvertices - 1
nsites = fs.nsites
# sample the coalescent tree with timelike branch lengths
R, B = kingman.sample(fs.nleaves)
r = Ftree.R_to_root(R)
# get the leaf vertex names
N = dict(zip(range(nleaves), string.uppercase[:nleaves]))
N_leaves = dict(N)
# get the internal vertex names
v_to_leaves = R_to_v_to_leaves(R)
for v, leaves in sorted(v_to_leaves.items()):
if len(leaves) > 1:
N[v] = ''.join(sorted(N[leaf] for leaf in leaves))
# get vertex ages
v_to_age = kingman.RB_to_v_to_age(R, B)
# sample the rates on the branches
b_to_rate = sample_b_to_rate(R)
xycorr = get_correlation(R, b_to_rate)
# define B_subs in terms of substitutions instead of time
B_subs = dict((p, t * b_to_rate[p]) for p, t in B.items())
# sample the alignment
v_to_seq = sample_v_to_seq(R, B_subs, nsites)
# get the log likelihood; this is kind of horrible
pairs = [(N[v], ''.join(v_to_seq[v])) for v in range(nleaves)]
headers, sequences = zip(*pairs)
alignment = Fasta.create_alignment(headers, sequences)
newick_string = FtreeIO.RBN_to_newick(R, B_subs, N_leaves)
tree = Newick.parse(newick_string, Newick.NewickTree)
dictionary_rate_matrix = RateMatrix.get_jukes_cantor_rate_matrix()
ordered_states = list('ACGT')
row_major_rate_matrix = MatrixUtil.dict_to_row_major(
dictionary_rate_matrix, ordered_states, ordered_states)
rate_matrix_object = RateMatrix.RateMatrix(
row_major_rate_matrix, ordered_states)
ll = PhyLikelihood.get_log_likelihood(
tree, alignment, rate_matrix_object)
# get ll when rates are all 1.0
newick_string = FtreeIO.RBN_to_newick(R, B, N_leaves)
tree = Newick.parse(newick_string, Newick.NewickTree)
ll_unity = PhyLikelihood.get_log_likelihood(
tree, alignment, rate_matrix_object)
# get ll when rates are numerically optimized
# TODO incorporate the result into the xml file
# TODO speed up the likelihood evaluation (beagle? C module?)
#f = Opt(R, B, N_leaves, alignment)
#X_logs = [0.0] * nbranches
#result = scipy.optimize.fmin(f, X_logs, full_output=True)
#print result
#
print >> out, '<?xml version="1.0"?>'
print >> out, '<beast>'
print >> out
print >> out, '<!-- actual rate autocorrelation', xycorr, '-->'
print >> out, '<!-- actual root height', v_to_age[r], '-->'
print >> out, '<!-- actual log likelihood', ll, '-->'
print >> out, '<!-- ll if rates were unity', ll_unity, '-->'
print >> out
print >> out, '<!--'
print >> out, 'predefine the taxa as in'
print >> out, 'http://beast.bio.ed.ac.uk/Introduction_to_XML_format'
print >> out, '-->'
print >> out, get_leaf_taxon_defn(list(string.uppercase[:nleaves]))
print >> out
print >> out, '<!--'
print >> out, 'define the alignment as in'
print >> out, 'http://beast.bio.ed.ac.uk/Introduction_to_XML_format'
print >> out, '-->'
print >> out, get_alignment_defn(leaves, N, v_to_seq)
print >> out
print >> out, '<!--'
print >> out, 'specify the starting tree as in'
print >> out, 'http://beast.bio.ed.ac.uk/Tutorial_4'
print >> out, '-->'
print >> out, get_starting_tree_defn(R, B, N_leaves)
print >> out
print >> out, '<!--'
print >> out, 'connect the tree model as in'
print >> out, 'http://beast.bio.ed.ac.uk/Tutorial_4'
print >> out, '-->'
print >> out, g_tree_model_defn
print >> out
print >> out, g_uncorrelated_relaxed_clock_info
print >> out
"""
print >> out, '<!--'
print >> out, 'create a list of taxa for which to constrain the mrca as in'
print >> out, 'http://beast.bio.ed.ac.uk/Tutorial_3.1'
print >> out, '-->'
for v, leaves in sorted(v_to_leaves.items()):
if len(leaves) > 1:
print >> out, get_mrca_subset_defn(N, v, leaves)
print >> out
print >> out, '<!--'
print >> out, 'create a tmrcaStatistic that will record the height as in'
print >> out, 'http://beast.bio.ed.ac.uk/Tutorial_3.1'
print >> out, '-->'
for v, leaves in sorted(v_to_leaves.items()):
if len(leaves) > 1:
print >> out, get_mrca_stat_defn(N[v])
"""
print >> out
print >> out, g_likelihood_info
print >> out
print >> out, '<!--'
print >> out, 'run the mcmc'
print >> out, 'http://beast.bio.ed.ac.uk/Tutorial_3.1'
print >> out, '-->'
print >> out, get_mcmc_defn(v_to_leaves, v_to_age, N)
print >> out
print >> out, '</beast>'
# return the response
return out.getvalue()
def get_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# read the nexus data
nexus = Nexus.Nexus()
try:
nexus.load(StringIO(fs.nexus))
except Nexus.NexusError as e:
raise HandlingError(e)
# move to the data directory
original_directory = os.getcwd()
os.chdir(Config.data_path)
# create the batch file
category_suffixes = [
str(category + 1) for category in range(fs.ncategories)
]
hky_hyphy_model = get_hyphy_model_string(hyphy_nexus, fs.ncategories)
with open(hyphy_bf, 'wt') as fout:
print >> fout, hky_hyphy_model
# create the nexus file
with open(hyphy_nexus, 'wt') as fout:
print >> fout, nexus
# run hyphy
p = subprocess.Popen([Config.hyphy_exe_path, hyphy_bf],
close_fds=True,
stdout=subprocess.PIPE)
hyphy_output = p.stdout.read()
# move back to the original directory
os.chdir(original_directory)
# read the hyphy output
ns = Hyphy.get_hyphy_namespace(StringIO(hyphy_output))
out = StringIO()
if fs.outdebug:
print >> out, get_hyphy_debug_info(hyphy_output)
print >> out, ''
print >> out, ''
if fs.outmodel:
print >> out, 'hyphy model:'
print >> out, '---------------------------------------'
print >> out, hky_hyphy_model
print >> out, '---------------------------------------'
print >> out, ''
print >> out, ''
if True:
print >> out, 'reformatted hyphy output:'
print >> out, '---------------------------------------'
# show the log likelihood
print >> out, 'log likelihood :', ns.lnL
print >> out, ''
# show the kappa value
print >> out, 'kappa :', ns.kappa
print >> out, ''
category_blocks = []
for suffix in category_suffixes:
block = StringIO()
print >> block, 'mixing proportion :', getattr(
ns, 'catFreq' + suffix)
print >> block, 'tree :', getattr(ns, 'tree' +
suffix).get_newick_string()
for nt in list('ACGT'):
print >> block, nt, ':', getattr(ns, 'eqFreq' + nt + suffix)
category_blocks.append(block.getvalue().strip())
print >> out, '\n\n'.join(category_blocks)
print >> out, '---------------------------------------'
print >> out, ''
print >> out, ''
if fs.outcheck:
# get the raw matrices
matrices = []
for suffix in category_suffixes:
nt_dict = {}
for nt in list('ACGT'):
nt_dict[nt] = getattr(ns, 'eqFreq' + nt + suffix)
total = float(sum(nt_dict.values()))
nt_dict = dict((k, v / total) for k, v in nt_dict.items())
matrix = RateMatrix.get_unscaled_hky85_rate_matrix(
nt_dict, ns.kappa)
matrices.append(matrix)
raw_matrix_rates = [matrix.get_expected_rate() for matrix in matrices]
category_weights = []
for suffix in category_suffixes:
category_weights.append(getattr(ns, 'catFreq' + suffix))
total = float(sum(category_weights))
category_distribution = [weight / total for weight in category_weights]
mixture_model = SubModel.MixtureModel(category_distribution, matrices)
raw_mixture_rate = mixture_model.get_expected_rate()
# rescale the mixture model
# 0.75 is the expected rate of the initial model
r1 = 0.75
scaling_factor = r1
mixture_model.rescale(scaling_factor)
recomputed_log_likelihood = PhyLikelihood.get_log_likelihood(
nexus.tree, nexus.alignment, mixture_model)
print >> out, 'recomputed likelihood and rates:'
print >> out, '---------------------------------------'
print >> out, 'log likelihood :', recomputed_log_likelihood
print >> out, ''
print >> out, 'rate :', raw_mixture_rate
print >> out, ''
for rate, suffix in zip(raw_matrix_rates, category_suffixes):
print >> out, 'rate%s : %s' % (suffix, rate)
print >> out, '---------------------------------------'
print >> out, ''
print >> out, ''
# return the response
return out.getvalue()
def get_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# read the nexus data
nexus = Nexus.Nexus()
try:
nexus.load(StringIO(fs.nexus))
except Nexus.NexusError as e:
raise HandlingError(e)
# move to the data directory
original_directory = os.getcwd()
os.chdir(Config.data_path)
# create the batch file
category_suffixes = [str(category+1) for category in range(fs.ncategories)]
hky_hyphy_model = get_hyphy_model_string(hyphy_nexus, fs.ncategories)
with open(hyphy_bf, 'wt') as fout:
print >> fout, hky_hyphy_model
# create the nexus file
with open(hyphy_nexus, 'wt') as fout:
print >> fout, nexus
# run hyphy
p = subprocess.Popen([Config.hyphy_exe_path, hyphy_bf],
close_fds=True, stdout=subprocess.PIPE)
hyphy_output = p.stdout.read()
# move back to the original directory
os.chdir(original_directory)
# read the hyphy output
ns = Hyphy.get_hyphy_namespace(StringIO(hyphy_output))
out = StringIO()
if fs.outdebug:
print >> out, get_hyphy_debug_info(hyphy_output)
print >> out, ''
print >> out, ''
if fs.outmodel:
print >> out, 'hyphy model:'
print >> out, '---------------------------------------'
print >> out, hky_hyphy_model
print >> out, '---------------------------------------'
print >> out, ''
print >> out, ''
if True:
print >> out, 'reformatted hyphy output:'
print >> out, '---------------------------------------'
# show the log likelihood
print >> out, 'log likelihood :', ns.lnL
print >> out, ''
# show the kappa value
print >> out, 'kappa :', ns.kappa
print >> out, ''
category_blocks = []
for suffix in category_suffixes:
block = StringIO()
print >> block, 'mixing proportion :', getattr(ns, 'catFreq'+suffix)
print >> block, 'tree :', getattr(ns, 'tree'+suffix).get_newick_string()
for nt in list('ACGT'):
print >> block, nt, ':', getattr(ns, 'eqFreq'+nt+suffix)
category_blocks.append(block.getvalue().strip())
print >> out, '\n\n'.join(category_blocks)
print >> out, '---------------------------------------'
print >> out, ''
print >> out, ''
if fs.outcheck:
# get the raw matrices
matrices = []
for suffix in category_suffixes:
nt_dict = {}
for nt in list('ACGT'):
nt_dict[nt] = getattr(ns, 'eqFreq'+nt+suffix)
total = float(sum(nt_dict.values()))
nt_dict = dict((k, v/total) for k, v in nt_dict.items())
matrix = RateMatrix.get_unscaled_hky85_rate_matrix(
nt_dict, ns.kappa)
matrices.append(matrix)
raw_matrix_rates = [matrix.get_expected_rate() for matrix in matrices]
category_weights = []
for suffix in category_suffixes:
category_weights.append(getattr(ns, 'catFreq'+suffix))
total = float(sum(category_weights))
category_distribution = [weight / total for weight in category_weights]
mixture_model = SubModel.MixtureModel(category_distribution, matrices)
raw_mixture_rate = mixture_model.get_expected_rate()
# rescale the mixture model
# 0.75 is the expected rate of the initial model
r1 = 0.75
scaling_factor = r1
mixture_model.rescale(scaling_factor)
recomputed_log_likelihood = PhyLikelihood.get_log_likelihood(
nexus.tree, nexus.alignment, mixture_model)
print >> out, 'recomputed likelihood and rates:'
print >> out, '---------------------------------------'
print >> out, 'log likelihood :', recomputed_log_likelihood
print >> out, ''
print >> out, 'rate :', raw_mixture_rate
print >> out, ''
for rate, suffix in zip(raw_matrix_rates, category_suffixes):
print >> out, 'rate%s : %s' % (suffix, rate)
print >> out, '---------------------------------------'
print >> out, ''
print >> out, ''
# return the response
return out.getvalue()
