def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string),
Form.RadioGroup('matrix', 'nodes used for the distance matrix', [
RadioItem('standard', 'tips only', True),
RadioItem('augmented', 'all nodes'),
RadioItem('named', 'all named nodes')
]),
Form.CheckGroup('output_options', 'output options', [
CheckItem('show_split', 'exact criterion partition', True),
CheckItem('show_value', 'exact criterion value', True),
CheckItem('show_value_minus_trace',
'exact criterion value minus trace', True),
CheckItem('show_fiedler_split', 'show the spectral sign partition',
True),
CheckItem('show_fiedler_eigenvector',
'show the eigenvector of interest', True),
CheckItem('show_labels', 'ordered labels', True),
CheckItem('show_distance_matrix', 'distance matrix', True),
CheckItem('show_M_matrix', 'M matrix', True)
])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string and ordered tip labels
tree_string = "(a:1, (b:2, d:5):1, c:4);"
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
labels = list(sorted(tip.name for tip in tree.gen_tips()))
# define the form objects
form_objects = [
Form.MultiLine("tree", "newick tree", formatted_tree_string),
Form.MultiLine("inlabels", "ordered labels", "\n".join(labels)),
Form.Float("strength", "perturbation strength", 0.1, low_inclusive=0),
Form.CheckGroup(
"options",
"output options",
[
CheckItem("perturbed", "a perturbed distance matrix", True),
CheckItem("distance", "the original distance matrix"),
CheckItem("outlabels", "ordered labels"),
],
),
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the tree string
tree_string = '(((a:0.05, b:0.05):0.15, c:0.2):0.8, x:1.0, (((m:0.05, n:0.05):0.15, p:0.2):0.8, y:1.0):1.0);'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the object list
form_objects = [
Form.MultiLine('tree', 'tree',
formatted_tree_string),
Form.Integer('sequence_length', 'use sequences that are this long',
100, low=1),
Form.RadioGroup('assumption', 'distance matrix sampling model', [
RadioItem('infinite_alleles', 'infinite alleles', True),
RadioItem('jukes_cantor', 'Jukes-Cantor model (4 alleles)')]),
Form.RadioGroup('infinity', 'matrices with infinite distances', [
RadioItem('reject_infinity', 'reject these matrices', True),
RadioItem('replace_infinity', 'use 20 instead')]),
Form.RadioGroup('zero', 'matrices with zero distances', [
RadioItem('reject_zero', 'reject these matrices'),
RadioItem('replace_zero', 'use .00001 instead'),
RadioItem('remain_zero', 'use 0 unmodified', True)]),
Form.RadioGroup('criterion', 'tree reconstruction criterion', [
RadioItem('sign', 'spectral sign approximation', True),
RadioItem('nj', 'neighbor joining'),
RadioItem('random', 'random bipartition')])]
# return the object list
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string),
Form.SingleLine('lhs_a', 'the first taxon on one side of the split',
'a'),
Form.SingleLine('lhs_b', 'the second taxon on one side of the split',
'b'),
Form.SingleLine('rhs_a',
'the first taxon on the other side of the split', 'x'),
Form.SingleLine('rhs_b',
'the second taxon on the other side of the split',
'y'),
Form.CheckGroup('options', 'output options', [
Form.CheckItem('show_response',
'show the Laplacian response matrix'),
Form.CheckItem('show_reduced_response', 'show the 2x2 submatrix'),
Form.CheckItem('show_blen',
'show the branch length implied by the split')
])
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
return [Form.MultiLine('tree', 'tree', formatted_tree_string)]
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree',
formatted_tree_string),
Form.Integer('length', 'use sequences that are this long',
100, low=1),
Form.RadioGroup('assumption', 'distance matrix sampling model', [
Form.RadioItem('infinite_alleles', 'infinite alleles', True),
Form.RadioItem('jukes_cantor',
'Jukes-Cantor model (4 alleles)')]),
Form.RadioGroup('infinity', 'infinite distance estimates', [
Form.RadioItem('reject_infinity', 'reject these matrices'),
Form.RadioItem('replace_infinity',
'replace inf with 20', True)]),
Form.RadioGroup('zero', 'distance estimates of zero', [
Form.RadioItem('reject_zero', 'reject these matrices'),
Form.RadioItem('replace_zero', 'use .00001 instead of zero'),
Form.RadioItem('remain_zero', 'use 0 unmodified', True)])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = get_default_original_tree()
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'original tree with branch lengths',
formatted_tree_string),
Form.Integer('iterations', 'reconstruct this many trees',
10, low=1),
Form.Integer('length', 'use sequences that are this long',
100, low=2),
Form.RadioGroup('criterion', 'bipartition function', [
RadioItem('exact', 'exact criterion'),
RadioItem('sign', 'spectral sign approximation', True),
RadioItem('threshold', 'spectral threshold approximation'),
RadioItem('nj', 'neighbor joining criterion'),
RadioItem('random', 'random bipartition')]),
Form.RadioGroup('recourse', 'recourse for degenerate partitions', [
RadioItem('njrecourse', 'neighbor joining', True),
RadioItem('halvingrecourse', 'leaf stem length halving')]),
Form.CheckGroup('output_options', 'extra output option', [
CheckItem('showtrees', 'show reconstructed tree topologies')])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string),
Form.Integer('length', 'use sequences that are this long', 100, low=1),
Form.RadioGroup('assumption', 'distance matrix sampling model', [
Form.RadioItem('infinite_alleles', 'infinite alleles', True),
Form.RadioItem('jukes_cantor', 'Jukes-Cantor model (4 alleles)')
]),
Form.RadioGroup('infinity', 'infinite distance estimates', [
Form.RadioItem('reject_infinity', 'reject these matrices'),
Form.RadioItem('replace_infinity', 'replace inf with 20', True)
]),
Form.RadioGroup('zero', 'distance estimates of zero', [
Form.RadioItem('reject_zero', 'reject these matrices'),
Form.RadioItem('replace_zero', 'use .00001 instead of zero'),
Form.RadioItem('remain_zero', 'use 0 unmodified', True)
])
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
return [Form.MultiLine('tree', 'tree', formatted_tree_string)]
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = get_default_original_tree()
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'original tree with branch lengths',
formatted_tree_string),
Form.Integer('iterations', 'reconstruct this many trees', 10, low=1),
Form.Integer('length', 'use sequences that are this long', 100, low=2),
Form.RadioGroup('criterion', 'bipartition function', [
RadioItem('exact', 'exact criterion'),
RadioItem('sign', 'spectral sign approximation', True),
RadioItem('threshold', 'spectral threshold approximation'),
RadioItem('nj', 'neighbor joining criterion'),
RadioItem('random', 'random bipartition')
]),
Form.RadioGroup('recourse', 'recourse for degenerate partitions', [
RadioItem('njrecourse', 'neighbor joining', True),
RadioItem('halvingrecourse', 'leaf stem length halving')
]),
Form.CheckGroup(
'output_options', 'extra output option',
[CheckItem('showtrees', 'show reconstructed tree topologies')])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree',
'newick tree with branch lengths', formatted_tree_string),
Form.SingleLine('lhs_a',
'the first taxon on one side of the split', 'a'),
Form.SingleLine('lhs_b',
'the second taxon on one side of the split', 'b'),
Form.SingleLine('rhs_a',
'the first taxon on the other side of the split', 'x'),
Form.SingleLine('rhs_b',
'the second taxon on the other side of the split', 'y'),
Form.CheckGroup('options', 'output options', [
Form.CheckItem('show_response',
'show the full Laplacian matrix'),
Form.CheckItem('show_reduced_response',
'show the 2x2 submatrix'),
Form.CheckItem('show_blen',
'show the branch length implied by the split')])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine("tree", "newick tree", formatted_tree_string),
Form.RadioGroup(
"matrix",
"nodes used for the distance matrix",
[
RadioItem("standard", "tips only", True),
RadioItem("augmented", "all nodes"),
RadioItem("named", "all named nodes"),
],
),
Form.CheckGroup(
"output_options",
"output options",
[
CheckItem("show_split", "exact criterion partition", True),
CheckItem("show_value", "exact criterion value", True),
CheckItem("show_value_minus_trace", "exact criterion value minus trace", True),
CheckItem("show_fiedler_split", "show the spectral sign partition", True),
CheckItem("show_fiedler_eigenvector", "show the eigenvector of interest", True),
CheckItem("show_labels", "ordered labels", True),
CheckItem("show_distance_matrix", "distance matrix", True),
CheckItem("show_M_matrix", "M matrix", True),
],
),
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
form_objects = [Form.MultiLine("tree", "newick tree with branch lengths", formatted_tree_string)]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the formatted tree string
tree = NewickIO.parse(g_tree_data, Newick.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string)]
return form_objects
def get_form():
"""
@return: the body of a form
"""
default_tree = NewickIO.parse(g_tree_data, FelTree.NewickTree)
default_tree_string = NewickIO.get_narrow_newick_string(default_tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', default_tree_string),
Form.MultiLine('annotation', 'SNP annotations', g_annotation_data)
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
tree = NewickIO.parse(g_tree_string, FelTree.NewickTree)
formatted_default_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', formatted_default_tree_string),
Form.ImageFormat()]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
return [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string),
Form.Integer('precision', 'precision', 4, low=2, high=17)]
def get_form():
"""
@return: the body of a form
"""
# define the formatted tree string
tree = NewickIO.parse(g_tree_data, Newick.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string)
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string)]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
tree = NewickIO.parse(g_tree_string, FelTree.NewickTree)
formatted_default_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', formatted_default_tree_string),
Form.ImageFormat()
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
# ordered_labels = ('a', 'b', 'c', 'x', 'm', 'n', 'p', 'y', 'ab', 'abc', 'mn', 'mnp', 'mnpy', 'abcxmnpy')
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
return [
Form.MultiLine("tree", "newick tree with branch lengths", formatted_tree_string),
Form.Integer("precision", "precision", 4, low=2, high=17),
]
def get_form():
"""
@return: a list of form objects
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
return [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string),
Form.Integer('precision', 'precision', 4, low=2, high=17)
]
def get_form():
"""
@return: the body of a form
"""
default_tree = NewickIO.parse(g_tree_data, FelTree.NewickTree)
default_tree_string = NewickIO.get_narrow_newick_string(default_tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree',
default_tree_string),
Form.MultiLine('annotation', 'SNP annotations',
g_annotation_data)]
return form_objects
def get_verbose_summary(self):
"""
@return: a multiline string
"""
# begin the response
out = StringIO()
# show the number of taxa in various domains
print >> out, self._get_name_summary()
print >> out
# show the pruned full tree
formatted_tree_string = NewickIO.get_narrow_newick_string(self.pruned_tree, 120)
print >> out, 'this is the tree that represents all clades but for which redundant nodes have been pruned:'
print >> out, formatted_tree_string
print >> out
# split the distance matrix
D = np.array(self.pruned_tree.get_distance_matrix(self.pruned_names))
L = Euclid.edm_to_laplacian(D)
v = BuildTreeTopology.laplacian_to_fiedler(L)
eigensplit = BuildTreeTopology.eigenvector_to_split(v)
# report the eigendecomposition
print >> out, get_eigendecomposition_report(D)
print >> out
# report the clade intersections of sides of the split
side_names = [set(self.pruned_names[i] for i in side) for side in eigensplit]
print >> out, 'domains represented by each side of the primary split:'
print >> out, 'the left side has:\t', ', '.join(self._get_domains(side_names[0]))
print >> out, 'the right side has:\t', ', '.join(self._get_domains(side_names[1]))
print >> out
# prepare to do the secondary splits
left_indices, right_indices = eigensplit
full_label_sets = [set([i]) for i in range(len(self.pruned_names))]
# do the secondary splits
for index_selection, index_complement in ((left_indices, right_indices), (right_indices, left_indices)):
L_secondary = SchurAlgebra.mmerge(L, index_complement)
next_label_sets = SchurAlgebra.vmerge(full_label_sets, index_complement)
v = BuildTreeTopology.laplacian_to_fiedler(L_secondary)
left_subindices, right_subindices = BuildTreeTopology.eigenvector_to_split(v)
left_sublabels = set()
for i in left_subindices:
left_sublabels.update(next_label_sets[i])
right_sublabels = set()
for i in right_subindices:
right_sublabels.update(next_label_sets[i])
left_subnames = set(self.pruned_names[i] for i in left_sublabels)
right_subnames = set(self.pruned_names[i] for i in right_sublabels)
print >> out, 'domains represented by a subsplit:'
print >> out, 'the left side has:\t', ', '.join(self._get_domains(left_subnames))
print >> out, 'the right side has:\t', ', '.join(self._get_domains(right_subnames))
print >> out
# return the multiline string
return out.getvalue().strip()
def get_form():
"""
@return: the body of a form
"""
# Define the default tree string with branch lengths
# and named internal nodes.
tree_string = '(a:2, (b:2, c:9)g:4, ((d:1, e:3)i:7, f:2)j:1)h;'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string)]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree
default_tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
default_tree_string = NewickIO.get_narrow_newick_string(default_tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', default_tree_string),
Form.SingleLine('chromosome', 'chromosome', 'chr17'),
Form.Integer('position', 'position', 70360012, low=0),
Form.SingleLine('aminoacid', 'the amino acid of interest', 'P')]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree_string = NewickIO.daylight_example_tree
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string),
Form.MultiLine('selection', 'selected taxa', '\n'.join('ABFG')),
Form.ImageFormat()]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree
default_tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
default_tree_string = NewickIO.get_narrow_newick_string(default_tree, 60)
# Define the default lines
# that tell the amino acids in the column of the alignment.
default_alignment_lines = [
'Hg18 F',
'bosTau3 V',
'canFam2 V',
'danRer5 L',
'galGal3 A',
'mm9 L',
'monDom4 H',
'panTro2 F',
'rheMac2 F',
'rn4 L']
default_alignment_string = '\n'.join(default_alignment_lines)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', default_tree_string),
Form.MultiLine('column',
'amino acid of each taxon', default_alignment_string),
Form.CheckGroup('options',
'show these intermediate values', [
Form.CheckItem('show_raw_pc_table',
'the raw physicochemical property table', True),
Form.CheckItem('show_standardized_pc_table',
'the standardized physicochemical property table', True),
Form.CheckItem('show_pc_correlation_matrix',
'the physicochemical property correlation matrix', True),
Form.CheckItem('show_tree',
'the pruned phylogenetic tree', True),
Form.CheckItem('show_weights',
'the taxon weights', True),
Form.CheckItem('show_aa_distribution',
'the estimated amino acid distribution', True),
Form.CheckItem('show_pc_distribution',
'the estimated physicochemical property distn', True),
Form.CheckItem('show_deviations',
'the aa physicochemical property deviations', True),
Form.CheckItem('show_impact_scores',
'the impact score for each amino acid', True),
Form.CheckItem('show_p_values',
'the p-value for each amino acid', True)])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree
default_tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
default_tree_string = NewickIO.get_narrow_newick_string(default_tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', default_tree_string),
Form.SingleLine('chromosome', 'chromosome', 'chr17'),
Form.Integer('position', 'position', 70360012, low=0),
Form.SingleLine('aminoacid', 'the amino acid of interest', 'P')
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree_string = NewickIO.daylight_example_tree
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string),
Form.MultiLine('selection', 'selected taxa', '\n'.join('ABFG')),
Form.ImageFormat()
]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_default_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', formatted_default_tree_string),
Form.CheckGroup('processing_options', 'processing options', [
Form.CheckItem('internal', 'process internal nodes', True)]),
Form.CheckGroup('visualization_options', 'visualization options', [
Form.CheckItem('axes', 'draw axes', True),
Form.CheckItem('connections', 'draw connections', True)]),
Form.ImageFormat()]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# this counterexample uses symmetric and long branch lengths
unused_counterexample = '(a:2, b:5, (c:5, d:2):1);'
# this counterexample uses asymmetric and shorter branch lengths
counterexample = '(a:.5, b:2.5, (c:2.7, d:.6):.3);'
default_tree_string = counterexample
tree = NewickIO.parse(default_tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string)]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
# this counterexample uses symmetric and long branch lengths
unused_counterexample = '(a:2, b:5, (c:5, d:2):1);'
# this counterexample uses asymmetric and shorter branch lengths
counterexample = '(a:.5, b:2.5, (c:2.7, d:.6):.3);'
default_tree_string = counterexample
tree = NewickIO.parse(default_tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# return the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string)
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string),
Form.CheckGroup('options', 'output options', [
Form.CheckItem('show_direct_d',
'show the directly calculated full distance matrix', True),
Form.CheckItem('show_clever_d',
'show the cleverly calculated full distance matrix', True),
Form.CheckItem('show_closeness',
'show whether or not distance matrices are close', True)])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree
default_tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
default_tree_string = NewickIO.get_narrow_newick_string(default_tree, 60)
# Define the default lines
# that tell the amino acids in the column of the alignment.
default_alignment_lines = [
'Hg18 F', 'bosTau3 V', 'canFam2 V', 'danRer5 L', 'galGal3 A', 'mm9 L',
'monDom4 H', 'panTro2 F', 'rheMac2 F', 'rn4 L'
]
default_alignment_string = '\n'.join(default_alignment_lines)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', default_tree_string),
Form.MultiLine('column', 'amino acid of each taxon',
default_alignment_string),
Form.CheckGroup('options', 'show these intermediate values', [
Form.CheckItem('show_raw_pc_table',
'the raw physicochemical property table', True),
Form.CheckItem('show_standardized_pc_table',
'the standardized physicochemical property table',
True),
Form.CheckItem('show_pc_correlation_matrix',
'the physicochemical property correlation matrix',
True),
Form.CheckItem('show_tree', 'the pruned phylogenetic tree', True),
Form.CheckItem('show_weights', 'the taxon weights', True),
Form.CheckItem('show_aa_distribution',
'the estimated amino acid distribution', True),
Form.CheckItem('show_pc_distribution',
'the estimated physicochemical property distn',
True),
Form.CheckItem('show_deviations',
'the aa physicochemical property deviations', True),
Form.CheckItem('show_impact_scores',
'the impact score for each amino acid', True),
Form.CheckItem('show_p_values', 'the p-value for each amino acid',
True)
])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# Define the default tree string with branch lengths
# and named internal nodes.
tree_string = '(a:2, (b:2, c:9)g:4, ((d:1, e:3)i:7, f:2)j:1)h;'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree',
'newick tree with branch lengths', formatted_tree_string),
Form.Float('scaling_factor',
'show Laplacian matrices scaled by this amount', 13320),
Form.RadioGroup('matrix_format', 'matrix format', [
Form.RadioItem('plain_matrix', 'plain', True),
Form.RadioItem('latex_matrix', 'LaTeX')])]
return form_objects
def get_form():
"""
@return: a list of form objects
"""
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_default_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the list of form objects
form_objects = [
Form.MultiLine('tree', 'tree', formatted_default_tree_string),
Form.CheckGroup(
'processing_options', 'processing options',
[Form.CheckItem('internal', 'process internal nodes', True)]),
Form.CheckGroup('visualization_options', 'visualization options', [
Form.CheckItem('axes', 'draw axes', True),
Form.CheckItem('connections', 'draw connections', True)
]),
Form.ImageFormat()
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string and ordered tip labels
tree_string = '(a:1, (b:2, d:5):1, c:4);'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
labels = list(sorted(tip.name for tip in tree.gen_tips()))
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree', formatted_tree_string),
Form.MultiLine('inlabels', 'ordered labels', '\n'.join(labels)),
Form.Float('strength', 'perturbation strength', 0.1, low_inclusive=0),
Form.CheckGroup('options', 'output options', [
CheckItem('perturbed', 'a perturbed distance matrix', True),
CheckItem('distance', 'the original distance matrix'),
CheckItem('outlabels', 'ordered labels')
])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the ordered labels
ordered_labels = list('abcxmnpy')
# define the form objects
form_objects = [
Form.MultiLine('tree', 'rooted newick tree with branch lengths',
formatted_tree_string),
Form.MultiLine('labels', 'ordered labels',
'\n'.join(ordered_labels)),
Form.Float('epsilon', 'epsilon', '1e-10'),
Form.RadioGroup('matrix_format', 'output matrix format', [
Form.RadioItem('plain_format', 'plain', True),
Form.RadioItem('r_format', 'R'),
Form.RadioItem('matlab_format', 'MATLAB')])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = get_default_original_tree()
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'original tree with branch lengths',
formatted_tree_string),
Form.Integer('iterations', 'reconstruct this many trees', 10),
Form.Integer('length', 'use sequences that are this long', 100),
Form.RadioGroup('criterion', 'bipartition function', [
Form.RadioItem('exact', 'exact criterion'),
Form.RadioItem('sign', 'spectral sign approximation', True),
Form.RadioItem('nj', 'neighbor joining criterion'),
Form.RadioItem('random', 'random bipartition')
])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = NewickIO.parse(g_default_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the ordered labels
ordered_labels = list('abcxmnpy')
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string),
Form.MultiLine('labels', 'ordered labels',
'\n'.join(ordered_labels)),
Form.Float('epsilon', 'epsilon', '1e-10'),
Form.RadioGroup('matrix_format', 'output matrix format', [
Form.RadioItem('plain_format', 'plain', True),
Form.RadioItem('r_format', 'R'),
Form.RadioItem('matlab_format', 'MATLAB')])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# Define the default tree string with branch lengths
# and named internal nodes.
tree_string = '(a:2, (b:2, c:9)g:4, ((d:1, e:3)i:7, f:2)j:1)h;'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine('tree', 'newick tree with branch lengths',
formatted_tree_string),
Form.Float('scaling_factor',
'show Laplacian matrices scaled by this amount', 13320),
Form.RadioGroup('matrix_format', 'matrix format', [
Form.RadioItem('plain_matrix', 'plain', True),
Form.RadioItem('latex_matrix', 'LaTeX')
])
]
return form_objects
def get_response_content(fs):
# read the tree
tree = NewickIO.parse(fs.tree, Newick.NewickTree)
# begin the response
out = StringIO()
# remove the branch length associated with the root
if tree.get_root().blen is not None:
print >> out, 'the root originally had a branch length of', tree.get_root(
).blen
tree.get_root().blen = None
else:
print >> out, 'the root did not originally have a branch length'
# force a trifurcation at the root
if tree.get_root().get_child_count() < 3:
print >> out, 'the original root had', tree.get_root().get_child_count(
), 'children'
max_children, best_child = max(
(child.get_child_count(), child)
for child in tree.get_root().gen_children())
old_root = tree.get_root()
tree.reroot(best_child)
tree.remove_node(old_root)
print >> out, 'the new root has', tree.get_root().get_child_count(
), 'children'
else:
print >> out, 'the root has', tree.get_root().get_child_count(
), 'children'
# remove names of internal nodes
nremoved_names = 0
for node in tree.preorder():
if node.has_children() and node.name is not None:
node.name = None
nremoved_names += 1
print >> out, 'removed', nremoved_names, 'internal node names'
# draw the new formatted newick string after a break
print >> out
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 120)
print >> out, formatted_tree_string
# return the response
return out.getvalue()
def get_form():
"""
@return: the body of a form
"""
# define the default distance matrix and the ordered labels
# this is from figure two of a paper called why neighbor joining works
D = np.array([[0, 2.7, 2.6, 2.6, 2.6, 4.4, 4.4, 4.4],
[2.7, 0, 4.4, 4.4, 4.4, 2.6, 2.6, 2.6],
[2.6, 4.4, 0, 0.1, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.1, 0, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.4, 0.4, 0, 2.7, 2.7, 2.7],
[4.4, 2.6, 2.7, 2.7, 2.7, 0, 0.1, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.1, 0, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.4, 0.4, 0]])
labels = list('xyabcmnp')
# define the default newick tree string
tree_string = '(((a, b), c), x, (((m, n), p), y));'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.Matrix('matrix', 'perturbed distance matrix', D,
MatrixUtil.assert_predistance),
Form.MultiLine('labels', 'ordered labels', '\n'.join(labels)),
Form.MultiLine('tree', 'original tree (branch lengths optional)',
formatted_tree_string),
Form.RadioGroup('criterion', 'bipartition function', [
RadioItem('exact', 'exact criterion', True),
RadioItem('sign', 'spectral sign approximation'),
RadioItem('threshold', 'spectral threshold approximation'),
RadioItem('nj', 'neighbor joining criterion')
]),
Form.RadioGroup('recourse', 'recourse for degenerate partitions', [
RadioItem('njrecourse', 'neighbor joining', True),
RadioItem('halvingrecourse', 'leaf stem length halving')
])
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default distance matrix and the ordered labels
# this is from figure two of a paper called why neighbor joining works
D = np.array([
[ 0, 2.7, 2.6, 2.6, 2.6, 4.4, 4.4, 4.4],
[2.7, 0, 4.4, 4.4, 4.4, 2.6, 2.6, 2.6],
[2.6, 4.4, 0, 0.1, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.1, 0, 0.4, 2.7, 2.7, 2.7],
[2.6, 4.4, 0.4, 0.4, 0, 2.7, 2.7, 2.7],
[4.4, 2.6, 2.7, 2.7, 2.7, 0, 0.1, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.1, 0, 0.4],
[4.4, 2.6, 2.7, 2.7, 2.7, 0.4, 0.4, 0]])
labels = list('xyabcmnp')
# define the default newick tree string
tree_string = '(((a, b), c), x, (((m, n), p), y));'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.Matrix('matrix', 'perturbed distance matrix',
D, MatrixUtil.assert_predistance),
Form.MultiLine('labels', 'ordered labels',
'\n'.join(labels)),
Form.MultiLine('tree', 'original tree (branch lengths optional)',
formatted_tree_string),
Form.RadioGroup('criterion', 'bipartition function', [
RadioItem('exact', 'exact criterion', True),
RadioItem('sign', 'spectral sign approximation'),
RadioItem('threshold', 'spectral threshold approximation'),
RadioItem('nj', 'neighbor joining criterion')]),
Form.RadioGroup('recourse', 'recourse for degenerate partitions', [
RadioItem('njrecourse', 'neighbor joining', True),
RadioItem('halvingrecourse', 'leaf stem length halving')])]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the default tree string
tree = get_default_original_tree()
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the form objects
form_objects = [
Form.MultiLine("tree", "original tree with branch lengths", formatted_tree_string),
Form.Integer("iterations", "reconstruct this many trees", 10),
Form.Integer("length", "use sequences that are this long", 100),
Form.RadioGroup(
"criterion",
"bipartition function",
[
Form.RadioItem("exact", "exact criterion"),
Form.RadioItem("sign", "spectral sign approximation", True),
Form.RadioItem("nj", "neighbor joining criterion"),
Form.RadioItem("random", "random bipartition"),
],
),
]
return form_objects
def get_form():
"""
@return: the body of a form
"""
# define the tree string
tree_string = '(((a:0.05, b:0.05):0.15, c:0.2):0.8, x:1.0, (((m:0.05, n:0.05):0.15, p:0.2):0.8, y:1.0):1.0);'
tree = NewickIO.parse(tree_string, FelTree.NewickTree)
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 60)
# define the object list
form_objects = [
Form.MultiLine('tree', 'tree', formatted_tree_string),
Form.Integer('sequence_length',
'use sequences that are this long',
100,
low=1),
Form.RadioGroup('assumption', 'distance matrix sampling model', [
RadioItem('infinite_alleles', 'infinite alleles', True),
RadioItem('jukes_cantor', 'Jukes-Cantor model (4 alleles)')
]),
Form.RadioGroup('infinity', 'matrices with infinite distances', [
RadioItem('reject_infinity', 'reject these matrices', True),
RadioItem('replace_infinity', 'use 20 instead')
]),
Form.RadioGroup('zero', 'matrices with zero distances', [
RadioItem('reject_zero', 'reject these matrices'),
RadioItem('replace_zero', 'use .00001 instead'),
RadioItem('remain_zero', 'use 0 unmodified', True)
]),
Form.RadioGroup('criterion', 'tree reconstruction criterion', [
RadioItem('sign', 'spectral sign approximation', True),
RadioItem('nj', 'neighbor joining'),
RadioItem('random', 'random bipartition')
])
]
# return the object list
return form_objects
def get_standard_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# begin the response
out = StringIO()
# show a summary of the original data
print >> out, 'data summary before removing branches with zero length:'
print >> out, len(archaea_names), 'archaea names in the original tree'
print >> out, len(bacteria_names), 'bacteria names in the original tree'
print >> out, len(eukaryota_names), 'eukaryota names in the original tree'
print >> out, len(all_names), 'total names in the original tree'
print >> out
# get the pruned full tree
pruned_full_tree = get_pruned_tree(full_tree)
ordered_names = list(node.get_name() for node in pruned_full_tree.gen_tips())
# show a summary of the processed data
print >> out, 'data summary after removing branches with zero length:'
print >> out, len(ordered_names), 'total names in the processed non-degenerate tree'
print >> out
# draw the pruned full tree
print >> out, 'this is the tree that represents all clades but for which redundant nodes have been pruned:'
formatted_tree_string = NewickIO.get_narrow_newick_string(pruned_full_tree, 120)
print >> out, formatted_tree_string
print >> out
# split the distance matrix
D = np.array(pruned_full_tree.get_distance_matrix(ordered_names))
L = Euclid.edm_to_laplacian(D)
v = BuildTreeTopology.laplacian_to_fiedler(L)
eigensplit = BuildTreeTopology.eigenvector_to_split(v)
# report the eigendecomposition
print >> out, get_eigendecomposition_report(D)
# report the clade intersections of sides of the split
side_names = [set(ordered_names[i] for i in side) for side in eigensplit]
clade_name_pairs = ((archaea_names, 'archaea'), (bacteria_names, 'bacteria'), (eukaryota_names, 'eukaryota'))
print >> out, 'clade intersections with each side of the split:'
for side, side_name in zip(side_names, ('left', 'right')):
for clade, clade_name in clade_name_pairs:
if clade & side:
print >> out, 'the', side_name, 'side intersects', clade_name
print >> out
# prepare to do the secondary splits
left_indices, right_indices = eigensplit
full_label_sets = [set([i]) for i in range(len(ordered_names))]
# get a secondary split
for index_selection, index_complement in ((left_indices, right_indices), (right_indices, left_indices)):
L_s1 = SchurAlgebra.mmerge(L, index_complement)
next_label_sets = SchurAlgebra.vmerge(full_label_sets, index_complement)
v = BuildTreeTopology.laplacian_to_fiedler(L_s1)
left_subindices, right_subindices = BuildTreeTopology.eigenvector_to_split(v)
left_sublabels = set()
for i in left_subindices:
left_sublabels.update(next_label_sets[i])
right_sublabels = set()
for i in right_subindices:
right_sublabels.update(next_label_sets[i])
left_subnames = set(ordered_names[i] for i in left_sublabels)
right_subnames = set(ordered_names[i] for i in right_sublabels)
print >> out, 'clade intersections with a subsplit:'
for clade, clade_name in clade_name_pairs:
if clade & left_subnames:
print >> out, 'the left side intersects', clade_name
for clade, clade_name in clade_name_pairs:
if clade & right_subnames:
print >> out, 'the right side intersects', clade_name
print >> out
# show debug info
print >> out, 'archaea names:'
print >> out, '\n'.join(x for x in sorted(archaea_names))
print >> out
print >> out, 'bacteria names:'
print >> out, '\n'.join(x for x in sorted(bacteria_names))
print >> out
print >> out, 'eukaryota names:'
print >> out, '\n'.join(x for x in sorted(eukaryota_names))
print >> out
# return the response
response_text = out.getvalue().strip()
return [('Content-Type', 'text/plain')], response_text
def get_verbose_summary(self):
"""
@return: a multiline string
"""
# begin the response
out = StringIO()
# show the number of taxa in various domains
print >> out, self._get_name_summary()
print >> out
# show the pruned full tree
formatted_tree_string = NewickIO.get_narrow_newick_string(
self.pruned_tree, 120)
print >> out, 'this is the tree that represents all clades but for which redundant nodes have been pruned:'
print >> out, formatted_tree_string
print >> out
# split the distance matrix
D = np.array(self.pruned_tree.get_distance_matrix(self.pruned_names))
L = Euclid.edm_to_laplacian(D)
v = BuildTreeTopology.laplacian_to_fiedler(L)
eigensplit = BuildTreeTopology.eigenvector_to_split(v)
# report the eigendecomposition
print >> out, get_eigendecomposition_report(D)
print >> out
# report the clade intersections of sides of the split
side_names = [
set(self.pruned_names[i] for i in side) for side in eigensplit
]
print >> out, 'domains represented by each side of the primary split:'
print >> out, 'the left side has:\t', ', '.join(
self._get_domains(side_names[0]))
print >> out, 'the right side has:\t', ', '.join(
self._get_domains(side_names[1]))
print >> out
# prepare to do the secondary splits
left_indices, right_indices = eigensplit
full_label_sets = [set([i]) for i in range(len(self.pruned_names))]
# do the secondary splits
for index_selection, index_complement in ((left_indices,
right_indices),
(right_indices,
left_indices)):
L_secondary = SchurAlgebra.mmerge(L, index_complement)
next_label_sets = SchurAlgebra.vmerge(full_label_sets,
index_complement)
v = BuildTreeTopology.laplacian_to_fiedler(L_secondary)
left_subindices, right_subindices = BuildTreeTopology.eigenvector_to_split(
v)
left_sublabels = set()
for i in left_subindices:
left_sublabels.update(next_label_sets[i])
right_sublabels = set()
for i in right_subindices:
right_sublabels.update(next_label_sets[i])
left_subnames = set(self.pruned_names[i] for i in left_sublabels)
right_subnames = set(self.pruned_names[i] for i in right_sublabels)
print >> out, 'domains represented by a subsplit:'
print >> out, 'the left side has:\t', ', '.join(
self._get_domains(left_subnames))
print >> out, 'the right side has:\t', ', '.join(
self._get_domains(right_subnames))
print >> out
# return the multiline string
return out.getvalue().strip()
def get_standard_response(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
# begin the response
out = StringIO()
# show a summary of the original data
print >> out, 'data summary before removing branches with zero length:'
print >> out, len(archaea_names), 'archaea names in the original tree'
print >> out, len(bacteria_names), 'bacteria names in the original tree'
print >> out, len(eukaryota_names), 'eukaryota names in the original tree'
print >> out, len(all_names), 'total names in the original tree'
print >> out
# get the pruned full tree
pruned_full_tree = get_pruned_tree(full_tree)
ordered_names = list(node.get_name()
for node in pruned_full_tree.gen_tips())
# show a summary of the processed data
print >> out, 'data summary after removing branches with zero length:'
print >> out, len(
ordered_names), 'total names in the processed non-degenerate tree'
print >> out
# draw the pruned full tree
print >> out, 'this is the tree that represents all clades but for which redundant nodes have been pruned:'
formatted_tree_string = NewickIO.get_narrow_newick_string(
pruned_full_tree, 120)
print >> out, formatted_tree_string
print >> out
# split the distance matrix
D = np.array(pruned_full_tree.get_distance_matrix(ordered_names))
L = Euclid.edm_to_laplacian(D)
v = BuildTreeTopology.laplacian_to_fiedler(L)
eigensplit = BuildTreeTopology.eigenvector_to_split(v)
# report the eigendecomposition
print >> out, get_eigendecomposition_report(D)
# report the clade intersections of sides of the split
side_names = [set(ordered_names[i] for i in side) for side in eigensplit]
clade_name_pairs = ((archaea_names, 'archaea'),
(bacteria_names, 'bacteria'), (eukaryota_names,
'eukaryota'))
print >> out, 'clade intersections with each side of the split:'
for side, side_name in zip(side_names, ('left', 'right')):
for clade, clade_name in clade_name_pairs:
if clade & side:
print >> out, 'the', side_name, 'side intersects', clade_name
print >> out
# prepare to do the secondary splits
left_indices, right_indices = eigensplit
full_label_sets = [set([i]) for i in range(len(ordered_names))]
# get a secondary split
for index_selection, index_complement in ((left_indices, right_indices),
(right_indices, left_indices)):
L_s1 = SchurAlgebra.mmerge(L, index_complement)
next_label_sets = SchurAlgebra.vmerge(full_label_sets,
index_complement)
v = BuildTreeTopology.laplacian_to_fiedler(L_s1)
left_subindices, right_subindices = BuildTreeTopology.eigenvector_to_split(
v)
left_sublabels = set()
for i in left_subindices:
left_sublabels.update(next_label_sets[i])
right_sublabels = set()
for i in right_subindices:
right_sublabels.update(next_label_sets[i])
left_subnames = set(ordered_names[i] for i in left_sublabels)
right_subnames = set(ordered_names[i] for i in right_sublabels)
print >> out, 'clade intersections with a subsplit:'
for clade, clade_name in clade_name_pairs:
if clade & left_subnames:
print >> out, 'the left side intersects', clade_name
for clade, clade_name in clade_name_pairs:
if clade & right_subnames:
print >> out, 'the right side intersects', clade_name
print >> out
# show debug info
print >> out, 'archaea names:'
print >> out, '\n'.join(x for x in sorted(archaea_names))
print >> out
print >> out, 'bacteria names:'
print >> out, '\n'.join(x for x in sorted(bacteria_names))
print >> out
print >> out, 'eukaryota names:'
print >> out, '\n'.join(x for x in sorted(eukaryota_names))
print >> out
# return the response
response_text = out.getvalue().strip()
return [('Content-Type', 'text/plain')], response_text
def get_response_content(fs):
# start writing the html response
out = StringIO()
print >> out, '<html>'
print >> out, '<body>'
# get the tree and the column sent by the user
pruned_tree, taxon_to_aa_letter = get_tree_and_column(fs)
# get the weights of the taxa
taxon_weight_pairs = LeafWeights.get_stone_weights(pruned_tree)
# show the raw physicochemical property table
if fs.show_raw_pc_table:
print >> out, 'raw physicochemical property table:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = Codon.g_aa_letters
table = MAPP.g_property_array
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the standardized physicochemical property table
standardized_property_array = MAPP.get_standardized_property_array(
MAPP.g_property_array)
# show the standardized physicochemical property table
if fs.show_standardized_pc_table:
print >> out, 'standardized physicochemical property table:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = Codon.g_aa_letters
table = standardized_property_array
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the physicochemical property correlation matrix
correlation_matrix = MAPP.get_property_correlation_matrix(
standardized_property_array)
# show the physicochemical property correlation matrix
if fs.show_pc_correlation_matrix:
print >> out, 'physicochemical property correlation matrix:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = MAPP.g_property_names
table = correlation_matrix
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# show the pruned tree
if fs.show_tree:
tree_string = NewickIO.get_narrow_newick_string(pruned_tree, 80)
lines = StringIO(tree_string).readlines()
lines = [line.rstrip() for line in lines]
print >> out, 'pruned phylogenetic tree in newick format:'
print >> out, '<pre>'
for line in lines:
print >> out, cgi.escape(line)
print >> out, '</pre>'
print >> out, '<br/>'
# show the weights
if fs.show_weights:
taxa, weights = zip(*taxon_weight_pairs)
table = [weights]
row_labels = ['weight']
col_labels = taxa
print >> out, 'taxon weights:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# estimate the amino acid distribution for the column,
# taking into account the tree and a uniform prior.
weights = []
aa_indices = []
for taxon, weight in taxon_weight_pairs:
weights.append(weight)
aa_indices.append(aa_letter_to_aa_index(taxon_to_aa_letter[taxon]))
aa_distribution = MAPP.estimate_aa_distribution(weights, aa_indices)
# show the estimated amino acid distribution
if fs.show_aa_distribution:
table = [aa_distribution]
row_labels = ['weight']
col_labels = Codon.g_aa_letters
print >> out, 'estimated amino acid distribution:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# estimate the mean and variance of each physicochemical property
est_pc_means = MAPP.estimate_property_means(
standardized_property_array, aa_distribution)
est_pc_variances = MAPP.estimate_property_variances(
standardized_property_array, aa_distribution)
# show the estimated mean and variance of each physicochemical property
if fs.show_pc_distribution:
table = [est_pc_means, est_pc_variances]
row_labels = ['mean', 'variance']
col_labels = MAPP.g_property_names
print >> out, 'estimated physicochemical property moments:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the deviation from each property mean
# for each possible amino acid
deviations = MAPP.get_deviations(
est_pc_means, est_pc_variances, standardized_property_array)
# show the deviation from each property mean for each possible amino acid
if fs.show_deviations:
print >> out, 'deviations of amino acids from the normal distribution'
print >> out, 'estimated for each property:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = Codon.g_aa_letters
table = deviations
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the impact scores
impact_scores = MAPP.get_impact_scores(correlation_matrix, deviations)
# show the impact scores
if fs.show_impact_scores:
table = [impact_scores]
row_labels = ['impact']
col_labels = Codon.g_aa_letters
print >> out, 'impact scores:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the p-values
p_values = []
for score in impact_scores:
ntaxa = len(taxon_weight_pairs)
p_values.append(MAPP.get_p_value(score, ntaxa))
# show the p-values
if fs.show_p_values:
table = [p_values]
row_labels = ['p-value']
col_labels = Codon.g_aa_letters
print >> out, 'p-values:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# write the html footer
print >> out, '</body>'
print >> out, '</html>'
# return the response
return out.getvalue()
def get_response_content(fs):
# start writing the html response
out = StringIO()
print >> out, '<html>'
print >> out, '<body>'
# get the tree and the column sent by the user
pruned_tree, taxon_to_aa_letter = get_tree_and_column(fs)
# get the weights of the taxa
taxon_weight_pairs = LeafWeights.get_stone_weights(pruned_tree)
# show the raw physicochemical property table
if fs.show_raw_pc_table:
print >> out, 'raw physicochemical property table:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = Codon.g_aa_letters
table = MAPP.g_property_array
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the standardized physicochemical property table
standardized_property_array = MAPP.get_standardized_property_array(
MAPP.g_property_array)
# show the standardized physicochemical property table
if fs.show_standardized_pc_table:
print >> out, 'standardized physicochemical property table:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = Codon.g_aa_letters
table = standardized_property_array
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the physicochemical property correlation matrix
correlation_matrix = MAPP.get_property_correlation_matrix(
standardized_property_array)
# show the physicochemical property correlation matrix
if fs.show_pc_correlation_matrix:
print >> out, 'physicochemical property correlation matrix:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = MAPP.g_property_names
table = correlation_matrix
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# show the pruned tree
if fs.show_tree:
tree_string = NewickIO.get_narrow_newick_string(pruned_tree, 80)
lines = StringIO(tree_string).readlines()
lines = [line.rstrip() for line in lines]
print >> out, 'pruned phylogenetic tree in newick format:'
print >> out, '<pre>'
for line in lines:
print >> out, cgi.escape(line)
print >> out, '</pre>'
print >> out, '<br/>'
# show the weights
if fs.show_weights:
taxa, weights = zip(*taxon_weight_pairs)
table = [weights]
row_labels = ['weight']
col_labels = taxa
print >> out, 'taxon weights:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# estimate the amino acid distribution for the column,
# taking into account the tree and a uniform prior.
weights = []
aa_indices = []
for taxon, weight in taxon_weight_pairs:
weights.append(weight)
aa_indices.append(aa_letter_to_aa_index(taxon_to_aa_letter[taxon]))
aa_distribution = MAPP.estimate_aa_distribution(weights, aa_indices)
# show the estimated amino acid distribution
if fs.show_aa_distribution:
table = [aa_distribution]
row_labels = ['weight']
col_labels = Codon.g_aa_letters
print >> out, 'estimated amino acid distribution:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# estimate the mean and variance of each physicochemical property
est_pc_means = MAPP.estimate_property_means(standardized_property_array,
aa_distribution)
est_pc_variances = MAPP.estimate_property_variances(
standardized_property_array, aa_distribution)
# show the estimated mean and variance of each physicochemical property
if fs.show_pc_distribution:
table = [est_pc_means, est_pc_variances]
row_labels = ['mean', 'variance']
col_labels = MAPP.g_property_names
print >> out, 'estimated physicochemical property moments:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the deviation from each property mean
# for each possible amino acid
deviations = MAPP.get_deviations(est_pc_means, est_pc_variances,
standardized_property_array)
# show the deviation from each property mean for each possible amino acid
if fs.show_deviations:
print >> out, 'deviations of amino acids from the normal distribution'
print >> out, 'estimated for each property:'
print >> out, '<br/>'
col_labels = MAPP.g_property_names
row_labels = Codon.g_aa_letters
table = deviations
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the impact scores
impact_scores = MAPP.get_impact_scores(correlation_matrix, deviations)
# show the impact scores
if fs.show_impact_scores:
table = [impact_scores]
row_labels = ['impact']
col_labels = Codon.g_aa_letters
print >> out, 'impact scores:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# calculate the p-values
p_values = []
for score in impact_scores:
ntaxa = len(taxon_weight_pairs)
p_values.append(MAPP.get_p_value(score, ntaxa))
# show the p-values
if fs.show_p_values:
table = [p_values]
row_labels = ['p-value']
col_labels = Codon.g_aa_letters
print >> out, 'p-values:'
print >> out, '<br/>'
print >> out, HtmlTable.get_labeled_table_string(
col_labels, row_labels, table)
print >> out, '<br/><br/>'
# write the html footer
print >> out, '</body>'
print >> out, '</html>'
# return the response
return out.getvalue()
def get_response_content(fs):
# read the tree
tree = NewickIO.parse(fs.tree, Newick.NewickTree)
# begin the response
out = StringIO()
# remove the branch length associated with the root
if tree.get_root().blen is not None:
print >> out, 'the root originally had a branch length of', tree.get_root().blen
tree.get_root().blen = None
else:
print >> out, 'the root did not originally have a branch length'
# force a trifurcation at the root
if tree.get_root().get_child_count() < 3:
print >> out, 'the original root had', tree.get_root().get_child_count(), 'children'
max_children, best_child = max((child.get_child_count(), child) for child in tree.get_root().gen_children())
old_root = tree.get_root()
tree.reroot(best_child)
tree.remove_node(old_root)
print >> out, 'the new root has', tree.get_root().get_child_count(), 'children'
else:
print >> out, 'the root has', tree.get_root().get_child_count(), 'children'
# remove names of internal nodes
nremoved_names = 0
for node in tree.preorder():
if node.has_children() and node.name is not None:
node.name = None
nremoved_names += 1
print >> out, 'removed', nremoved_names, 'internal node names'
# draw the new formatted newick string after a break
print >> out
formatted_tree_string = NewickIO.get_narrow_newick_string(tree, 120)
print >> out, formatted_tree_string
# return the response
return out.getvalue()
