def get_form():
"""
@return: the body of a form
"""
# define the default nexus string
tree = get_sample_tree()
mixture_model = get_sample_mixture_model()
ncols = 200
seed = 314159
alignment = PhyLikelihood.simulate_alignment(tree, mixture_model, ncols,
seed)
nexus = Nexus.Nexus()
nexus.tree = tree
nexus.alignment = alignment
nexus_string = str(nexus)
# define the form objects
form_objects = [
Form.MultiLine('nexus', 'nexus data', nexus_string),
Form.Integer('ncategories',
'use this many categories',
3,
low=1,
high=5),
Form.CheckGroup('options', 'output options', [
Form.CheckItem('outdebug', 'show debug info'),
Form.CheckItem('outmodel', 'show the model'),
Form.CheckItem('outcheck', 'show the likelihood and rates', True)
])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default nexus string
tree = get_sample_tree()
mixture_model = get_sample_mixture_model()
ncols = 200
seed = 314159
alignment = PhyLikelihood.simulate_alignment(
tree, mixture_model, ncols, seed)
nexus = Nexus.Nexus()
nexus.tree = tree
nexus.alignment = alignment
nexus_string = str(nexus)
# define the form objects
form_objects = [
Form.MultiLine('nexus', 'nexus data', nexus_string),
Form.Integer('ncategories', 'use this many categories',
3, low=1, high=5),
Form.CheckGroup('options', 'output options', [
Form.CheckItem('outdebug', 'show debug info'),
Form.CheckItem('outmodel', 'show the model'),
Form.CheckItem('outcheck', 'show the likelihood and rates',
True)])]
return form_objects
def gen_distance_matrices(self, count, max_steps):
"""
Yield (ordered sequence list, distance matrix) pairs .
The generator will stop if it sees that it cannot meet its goal
in the allotted number of steps.
@param count: the requested number of distance matrices
@param max_steps: an upper bound on the allowed number of steps
"""
# define the jukes cantor rate matrix
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)
model = RateMatrix.RateMatrix(row_major_rate_matrix, ordered_states)
# record the requested number of samples
self.requested_matrix_count = count
# do some rejection sampling
while True:
if self.get_complexity() >= max_steps:
break
if self.accepted_sample_count >= count:
break
# simulate an alignment from the tree
alignment = PhyLikelihood.simulate_alignment(
self.tree, model, self.sequence_length)
# extract the ordered list of sequences from the alignment object
name_to_sequence = dict(zip(alignment.headers,
alignment.sequences))
sequence_list = [
name_to_sequence[name] for name in self.ordered_names
]
# get the estimated distance matrix
distance_matrix = JC69.get_ML_distance_matrix(sequence_list)
# look for degeneracies
has_zero_off_diagonal = False
has_inf_off_diagonal = False
for i, row in enumerate(distance_matrix):
for j, value in enumerate(row):
if i != j:
if value == 0.0:
has_zero_off_diagonal = True
if value == float('inf'):
has_inf_off_diagonal = True
if has_zero_off_diagonal:
self.rejected_zero_sample_count += 1
elif has_inf_off_diagonal:
self.rejected_inf_sample_count += 1
else:
self.accepted_sample_count += 1
yield sequence_list, distance_matrix
def gen_distance_matrices(self, count, max_steps):
"""
Yield (ordered sequence list, distance matrix) pairs .
The generator will stop if it sees that it cannot meet its goal
in the allotted number of steps.
@param count: the requested number of distance matrices
@param max_steps: an upper bound on the allowed number of steps
"""
# define the jukes cantor rate matrix
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)
model = RateMatrix.RateMatrix(row_major_rate_matrix, ordered_states)
# record the requested number of samples
self.requested_matrix_count = count
# do some rejection sampling
while True:
if self.get_complexity() >= max_steps:
break
if self.accepted_sample_count >= count:
break
# simulate an alignment from the tree
alignment = PhyLikelihood.simulate_alignment(
self.tree, model, self.sequence_length)
# extract the ordered list of sequences from the alignment object
name_to_sequence = dict(zip(alignment.headers, alignment.sequences))
sequence_list = [name_to_sequence[name]
for name in self.ordered_names]
# get the estimated distance matrix
distance_matrix = JC69.get_ML_distance_matrix(sequence_list)
# look for degeneracies
has_zero_off_diagonal = False
has_inf_off_diagonal = False
for i, row in enumerate(distance_matrix):
for j, value in enumerate(row):
if i != j:
if value == 0.0:
has_zero_off_diagonal = True
if value == float('inf'):
has_inf_off_diagonal = True
if has_zero_off_diagonal:
self.rejected_zero_sample_count += 1
elif has_inf_off_diagonal:
self.rejected_inf_sample_count += 1
else:
self.accepted_sample_count += 1
yield sequence_list, distance_matrix
def get_response_content(fs):
# get the tree
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
# get the normalized Direct RNA mixture model
mixture_model = DirectRna.deserialize_mixture_model(fs.model)
mixture_model.normalize()
# simulate the alignment
try:
alignment = PhyLikelihood.simulate_alignment(tree, mixture_model,
fs.ncols)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
# return the alignment string
return '\n'.join(arr) + '\n'
def get_response_content(fs):
# get the tree
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
# get the normalized Direct RNA mixture model
mixture_model = DirectRna.deserialize_mixture_model(fs.model)
mixture_model.normalize()
# simulate the alignment
try:
alignment = PhyLikelihood.simulate_alignment(tree,
mixture_model, fs.ncols)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
# return the alignment string
return '\n'.join(arr) + '\n'
def get_response_content(fs):
# get the tree
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
# get the mixture weights
weights = [fs.weight_a, fs.weight_b, fs.weight_c]
# get the matrices
matrices = [fs.matrix_a, fs.matrix_b, fs.matrix_c]
for R in matrices:
if R.shape != (4,4):
msg = 'expected each nucleotide rate matrix to be 4x4'
raise HandlingError(msg)
# create the mixture proportions
weight_sum = sum(weights)
mixture_proportions = [weight / weight_sum for weight in weights]
# create the rate matrix objects
ordered_states = list('ACGT')
rate_matrix_objects = []
for R in matrices:
rate_matrix_object = RateMatrix.RateMatrix(R.tolist(), ordered_states)
rate_matrix_objects.append(rate_matrix_object)
# create the mixture model
mixture_model = SubModel.MixtureModel(mixture_proportions,
rate_matrix_objects)
# normalize the mixture model
mixture_model.normalize()
# simulate the alignment
try:
alignment = PhyLikelihood.simulate_alignment(tree,
mixture_model, fs.ncols)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
# return the alignment string
return '\n'.join(arr) + '\n'
def get_response_content(fs):
# get the tree
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
# get the mixture weights
weights = [fs.weight_a, fs.weight_b, fs.weight_c]
# get the matrices
matrices = [fs.matrix_a, fs.matrix_b, fs.matrix_c]
for R in matrices:
if R.shape != (4, 4):
msg = 'expected each nucleotide rate matrix to be 4x4'
raise HandlingError(msg)
# create the mixture proportions
weight_sum = sum(weights)
mixture_proportions = [weight / weight_sum for weight in weights]
# create the rate matrix objects
ordered_states = list('ACGT')
rate_matrix_objects = []
for R in matrices:
rate_matrix_object = RateMatrix.RateMatrix(R.tolist(), ordered_states)
rate_matrix_objects.append(rate_matrix_object)
# create the mixture model
mixture_model = SubModel.MixtureModel(mixture_proportions,
rate_matrix_objects)
# normalize the mixture model
mixture_model.normalize()
# simulate the alignment
try:
alignment = PhyLikelihood.simulate_alignment(tree, mixture_model,
fs.ncols)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
# return the alignment string
return '\n'.join(arr) + '\n'
def get_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# parse the tree
try:
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
except Newick.NewickSyntaxError as e:
raise HandlingError(str(e))
# get the normalized model
mixture_model = deserialize_mixture_model(fs.model)
# sample the alignment, possibly using a specified seed
try:
alignment = PhyLikelihood.simulate_alignment(tree, mixture_model,
fs.ncols, fs.seed)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the output string
output_string = ''
if fs.fastaformat:
# the output is the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
alignment_string = '\n'.join(arr)
output_string = alignment_string
elif fs.nexusformat:
# the output is the alignment and the tree
nexus = Nexus.Nexus()
nexus.tree = tree
nexus.alignment = alignment
output_string = str(nexus)
# print the results
response_headers = [('Content-Type', 'text/plain')]
return response_headers, output_string
def get_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# parse the tree
try:
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
except Newick.NewickSyntaxError as e:
raise HandlingError(str(e))
# get the normalized model
mixture_model = deserialize_mixture_model(fs.model)
# sample the alignment, possibly using a specified seed
try:
alignment = PhyLikelihood.simulate_alignment(tree, mixture_model, fs.ncols, fs.seed)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the output string
output_string = ""
if fs.fastaformat:
# the output is the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
alignment_string = "\n".join(arr)
output_string = alignment_string
elif fs.nexusformat:
# the output is the alignment and the tree
nexus = Nexus.Nexus()
nexus.tree = tree
nexus.alignment = alignment
output_string = str(nexus)
# print the results
response_headers = [("Content-Type", "text/plain")]
return response_headers, output_string
def get_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# parse the tree
try:
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
except Newick.NewickSyntaxError as e:
raise HandlingError(str(e))
# get the mixture weights
mixture_weights = [fs.weight_a, fs.weight_b]
# get the kappa values
kappa_values = [fs.kappa_a, fs.kappa_b]
# get the nucleotide distributions
frequency_strings = (fs.frequency_a, fs.frequency_b)
nucleotide_distributions = []
for nt_string in frequency_strings:
d = SnippetUtil.get_distribution(nt_string, 'nucleotide', list('ACGT'))
nucleotide_distributions.append(d)
# create the nucleotide HKY rate matrix objects
rate_matrix_objects = []
for nt_distribution, kappa in zip(nucleotide_distributions, kappa_values):
rate_matrix_object = RateMatrix.get_unscaled_hky85_rate_matrix(
nt_distribution, kappa)
rate_matrix_objects.append(rate_matrix_object)
# create the mixture proportions
weight_sum = sum(mixture_weights)
mixture_proportions = [weight / weight_sum for weight in mixture_weights]
# create the mixture model
mixture_model = SubModel.MixtureModel(mixture_proportions,
rate_matrix_objects)
# normalize the mixture model
mixture_model.normalize()
# simulate the alignment
try:
alignment = PhyLikelihood.simulate_alignment(tree, mixture_model,
fs.ncols)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the output string
output_string = ''
if fs.fasta:
# the output is the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
alignment_string = '\n'.join(arr)
output_string = alignment_string
elif fs.nex:
# the output is the alignment and the tree
nexus = Nexus.Nexus()
nexus.tree = tree
nexus.alignment = alignment
for i in range(2):
arr = []
arr.append('weight: %s' % mixture_weights[i])
arr.append('kappa: %s' % kappa_values[i])
nexus.add_comment('category %d: %s' % (i + 1, ', '.join(arr)))
output_string = str(nexus)
# define the filename
if fs.fasta:
filename_extension = 'fasta'
elif fs.nex:
filename_extension = 'nex'
filename = 'sample.' + fs.fmt
#TODO use the correct filename extension in the output
return output_string
def get_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# parse the tree
try:
tree = Newick.parse(fs.tree, Newick.NewickTree)
tree.assert_valid()
except Newick.NewickSyntaxError as e:
raise HandlingError(str(e))
# get the mixture weights
mixture_weights = [fs.weight_a, fs.weight_b]
# get the kappa values
kappa_values = [fs.kappa_a, fs.kappa_b]
# get the nucleotide distributions
frequency_strings = (fs.frequency_a, fs.frequency_b)
nucleotide_distributions = []
for nt_string in frequency_strings:
d = SnippetUtil.get_distribution(nt_string, 'nucleotide', list('ACGT'))
nucleotide_distributions.append(d)
# create the nucleotide HKY rate matrix objects
rate_matrix_objects = []
for nt_distribution, kappa in zip(nucleotide_distributions, kappa_values):
rate_matrix_object = RateMatrix.get_unscaled_hky85_rate_matrix(
nt_distribution, kappa)
rate_matrix_objects.append(rate_matrix_object)
# create the mixture proportions
weight_sum = sum(mixture_weights)
mixture_proportions = [weight / weight_sum for weight in mixture_weights]
# create the mixture model
mixture_model = SubModel.MixtureModel(
mixture_proportions, rate_matrix_objects)
# normalize the mixture model
mixture_model.normalize()
# simulate the alignment
try:
alignment = PhyLikelihood.simulate_alignment(
tree, mixture_model, fs.ncols)
except PhyLikelihood.SimulationError as e:
raise HandlingError(e)
# get the output string
output_string = ''
if fs.fasta:
# the output is the alignment
arr = []
for node in tree.gen_tips():
arr.append(alignment.get_fasta_sequence(node.name))
alignment_string = '\n'.join(arr)
output_string = alignment_string
elif fs.nex:
# the output is the alignment and the tree
nexus = Nexus.Nexus()
nexus.tree = tree
nexus.alignment = alignment
for i in range(2):
arr = []
arr.append('weight: %s' % mixture_weights[i])
arr.append('kappa: %s' % kappa_values[i])
nexus.add_comment('category %d: %s' % (i+1, ', '.join(arr)))
output_string = str(nexus)
# define the filename
if fs.fasta:
filename_extension = 'fasta'
elif fs.nex:
filename_extension = 'nex'
filename = 'sample.' + fs.fmt
#TODO use the correct filename extension in the output
return output_string
