def string_to_networkx(header, sequence, **options):
# defaults
energy_range = options.get('energy_range', 10)
max_num = options.get('max_num', 3)
max_num_subopts = options.get('max_num_subopts', 100)
split_components = options.get('split_components', False)
seq_struct_list, energy_list = rnasubopt_wrapper(sequence, energy_range=energy_range, max_num=max_num, max_num_subopts=max_num_subopts)
if split_components:
for seq_struct, energy in zip(seq_struct_list, energy_list):
G = sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=seq_struct)
G.graph['info'] = 'RNAsubopt energy=%s max_num=%s' % (energy, max_num)
if G.number_of_nodes() < 2:
G = seq_to_networkx(header, sequence, **options)
G.graph['id'] = header
G.graph['sequence'] = sequence
G.graph['structure'] = seq_struct
yield G
else:
G_global = nx.Graph()
G_global.graph['id'] = header
G_global.graph['info'] = 'RNAsubopt energy_range=%s max_num=%s' % (energy_range, max_num)
G_global.graph['sequence'] = sequence
for seq_struct in seq_struct_list:
G = sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=seq_struct)
G_global = nx.disjoint_union(G_global, G)
if G_global.number_of_nodes() < 2:
G_global = seq_to_networkx(header, sequence, **options)
yield G_global
def __init__(self, sequence_name, sequence, vectorizer, structure):
self.sequence_name = sequence_name
self.sequence = sequence
self.vectorizer = vectorizer
self.structure = structure
# create a base_graph , expand
base_graph = conv.sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=structure)
self.base_graph = vectorizer._edge_to_vertex_transform(base_graph)
# get an expanded abstract graph
abstract_graph = forgi.get_abstr_graph(structure)
abstract_graph = vectorizer._edge_to_vertex_transform(abstract_graph)
# connect edges to nodes in the abstract graph
self.abstract_graph = edge_parent_finder(abstract_graph, self.base_graph)
# we are forced to set a label .. for eden reasons
def name_edges(graph, what=''):
for n, d in graph.nodes(data=True):
if 'edge' in d:
d['label'] = what
# in the abstract graph , all the edge nodes need to have a contracted attribute.
# originaly this happens naturally but since we make multiloops into one loop there are some left out
def setset(graph):
for n, d in graph.nodes(data=True):
if 'contracted' not in d:
d['contracted'] = set()
name_edges(self.abstract_graph)
setset(self.abstract_graph)
def transform(self, sequences):
"""
Parameters
----------
sequences : iterable over rna sequences
Returns
-------
list of RnaGraphWrappers
"""
result = []
for sequence in sequences:
structure, energy = self.NNmodel.transform_single(
('fake', sequence))
if structure == None:
result.append(None)
continue
if self.structure_mod:
structure, sequence = fix_structure(structure, sequence)
base_graph = converter.sequence_dotbracket_to_graph(
seq_info=sequence, seq_struct=structure)
base_graph = self.vectorizer._edge_to_vertex_transform(base_graph)
base_graph = expanded_rna_graph_to_digraph(base_graph)
base_graph.graph['energy'] = energy
result.append(
RnaWrapper(sequence,
structure,
base_graph,
self.vectorizer,
self.base_thickness_list,
include_base=self.include_base,
ignore_inserts=self.ignore_inserts))
return result
def transform(self, sequences):
"""
Parameters
----------
sequences : iterable over rna sequences
Returns
-------
list of RnaGraphWrappers
"""
result = []
for sequence in sequences:
if type(sequence) == str:
structure, energy ,sequence = self.NNmodel.transform_single(('fake', sequence))
base_graph = converter.sequence_dotbracket_to_graph(seq_info=sequence, \
seq_struct=structure)
base_graph.graph['sequence']=sequence
base_graph.graph['structure']=structure
abstract_graph = self.make_abstract.abstract(base_graph.copy())
base_graph = self.vectorizer._edge_to_vertex_transform(base_graph)
base_graph = graphlearn.minor.rna.expanded_rna_graph_to_digraph(base_graph)
result.append((sequence,structure,base_graph,abstract_graph))
# up: normal preprocessing case, down: hack to avoid overwriting the postprocessor
# needs some changing obviously
else:
result.append(self.re_transform_single(sequence))
return result
def string_to_networkx(header, sequence, **options):
seq_info, seq_struct = RNAfold_wrapper(sequence, **options)
G = sequence_dotbracket_to_graph(seq_info=seq_info, seq_struct=seq_struct)
G.graph['info'] = 'RNAfold'
G.graph['sequence'] = sequence
G.graph['structure'] = seq_struct
G.graph['id'] = header
return G
def string_to_networkx(header, sequence, **options):
seq_info, seq_struct = RNAfold_wrapper(sequence, **options)
G = sequence_dotbracket_to_graph(seq_info=seq_info, seq_struct=seq_struct)
G.graph['info'] = 'RNAfold'
G.graph['sequence'] = sequence
G.graph['structure'] = seq_struct
G.graph['id'] = header
return G
def _seq_to_eden(self, header, sequence, struct, energy):
graph = sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=struct)
if graph.number_of_nodes() < 2:
graph = seq_to_networkx(header, sequence)
graph.graph['id'] = header
graph.graph['info'] = 'muscle+RNAalifold energy=%.3f' % (energy)
graph.graph['energy'] = energy
graph.graph['sequence'] = sequence
return graph
def string_to_networkx(header, sequence, **options):
# defaults
shape_type = options.get('shape_type', 5)
energy_range = options.get('energy_range', 10)
max_num = options.get('max_num', 3)
split_components = options.get('split_components', False)
seq_info, seq_struct_list, struct_list = rnashapes_wrapper(
sequence,
shape_type=shape_type,
energy_range=energy_range,
max_num=max_num,
rnashapes_version=options.get('rnashapes_version', 2))
if split_components:
for seq_struct, struct in zip(seq_struct_list, struct_list):
graph = sequence_dotbracket_to_graph(seq_info=seq_info,
seq_struct=seq_struct)
graph.graph[
'info'] = 'RNAshapes shape_type=%s energy_range=%s max_num=%s' % (
shape_type, energy_range, max_num)
graph.graph['id'] = header + '_' + struct
if graph.number_of_nodes() < 2:
graph = seq_to_networkx(header, sequence, **options)
graph.graph['id'] = header
graph.graph['sequence'] = sequence
graph.graph['structure'] = seq_struct
yield graph
else:
graph_global = nx.Graph()
graph_global.graph['id'] = header
graph_global.graph[
'info'] = 'RNAshapes shape_type=%s energy_range=%s max_num=%s' % (
shape_type, energy_range, max_num)
graph_global.graph['sequence'] = sequence
for seq_struct in seq_struct_list:
graph = sequence_dotbracket_to_graph(seq_info=seq_info,
seq_struct=seq_struct)
graph_global = nx.disjoint_union(graph_global, graph)
if graph_global.number_of_nodes() < 2:
graph_global = seq_to_networkx(header, sequence, **options)
yield graph_global
def string_to_networkx(header, sequence, constraint, **options):
# defaults
energy_range = options.get('energy_range', 10)
max_num = options.get('max_num', 3)
max_num_subopts = options.get('max_num_subopts', 100)
split_components = options.get('split_components', False)
seq_struct_list, energy_list = rnasubopt_wrapper(
sequence,
constraint,
energy_range=energy_range,
max_num=max_num,
max_num_subopts=max_num_subopts)
if split_components:
for seq_struct, energy in zip(seq_struct_list, energy_list):
graph = sequence_dotbracket_to_graph(seq_info=sequence,
seq_struct=seq_struct)
graph.graph['info'] = 'RNAsubopt energy=%s max_num=%s' % (energy,
max_num)
if graph.number_of_nodes() < 2:
graph = seq_to_networkx(header, sequence, **options)
graph.graph['id'] = header
graph.graph['sequence'] = sequence
graph.graph['structure'] = seq_struct
yield graph
else:
graph_global = nx.Graph()
graph_global.graph['id'] = header
graph_global.graph['info'] = 'RNAsubopt energy_range=%s max_num=%s' % (
energy_range, max_num)
graph_global.graph['sequence'] = sequence
for seq_struct in seq_struct_list:
graph = sequence_dotbracket_to_graph(seq_info=sequence,
seq_struct=seq_struct)
graph_global = nx.disjoint_union(graph_global, graph)
if graph_global.number_of_nodes() < 2:
graph_global = seq_to_networkx(header, sequence, **options)
yield graph_global
def string_to_networkx(header, sequence, **options):
# defaults
shape_type = options.get('shape_type', 5)
energy_range = options.get('energy_range', 10)
max_num = options.get('max_num', 3)
split_components = options.get('split_components', False)
seq_info, seq_struct_list, struct_list = rnashapes_wrapper(sequence,
shape_type=shape_type,
energy_range=energy_range,
max_num=max_num,
rnashapes_version=options.get('rnashapes_version', 2))
if split_components:
for seq_struct, struct in zip(seq_struct_list, struct_list):
graph = sequence_dotbracket_to_graph(seq_info=seq_info, seq_struct=seq_struct)
graph.graph['info'] = 'RNAshapes shape_type=%s energy_range=%s max_num=%s' % (shape_type,
energy_range,
max_num)
graph.graph['id'] = header + '_' + struct
if graph.number_of_nodes() < 2:
graph = seq_to_networkx(header, sequence, **options)
graph.graph['id'] = header
graph.graph['sequence'] = sequence
graph.graph['structure'] = seq_struct
yield graph
else:
graph_global = nx.Graph()
graph_global.graph['id'] = header
graph_global.graph['info'] = 'RNAshapes shape_type=%s energy_range=%s max_num=%s' % (shape_type,
energy_range,
max_num)
graph_global.graph['sequence'] = sequence
for seq_struct in seq_struct_list:
graph = sequence_dotbracket_to_graph(seq_info=seq_info, seq_struct=seq_struct)
graph_global = nx.disjoint_union(graph_global, graph)
if graph_global.number_of_nodes() < 2:
graph_global = seq_to_networkx(header, sequence, **options)
yield graph_global
def _sequence_to_base_graph(self, sequence):
'''
Parameters
----------
sequence: rna sequence
Returns
-------
nx.graph
'''
structure,sequence = self.NNmodel.transform_single(sequence)
base_graph = converter.sequence_dotbracket_to_graph(seq_info=sequence, \
seq_struct=structure)
return base_graph
def transform(self, sequences):
"""
Parameters
----------
sequences : iterable over rna sequences
Returns
-------
list of RnaGraphWrappers
"""
result = []
for sequence in sequences:
# if we eat a tupple, it musst be a (name, sequence) type :) we only want a sequence
if type(sequence) == type(()):
logger.warning('YOUR INPUT IS A TUPPLE, GIVE ME A SEQUENCE, SINCERELY -- YOUR RNA PREPROCESSOR')
# get structure
structure, energy, sequence = self.NNmodel.transform_single(('fake', sequence))
# FIXING STRUCTURE
structure, sequence = fix_structure(structure, sequence)
if structure == None:
result.append(None)
continue
# built base_graph
base_graph = converter.sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=structure)
base_graph = self.vectorizer._edge_to_vertex_transform(base_graph)
base_graph = expanded_rna_graph_to_digraph(base_graph)
base_graph.graph['energy'] = energy
base_graph.graph['sequence'] = sequence
base_graph.graph['structure'] = structure
result.append(
(sequence, structure, base_graph, self.abstract_graph(base_graph))
)
return result
def transform(self, sequences):
"""
Parameters
----------
sequences : iterable over rna sequences
Returns
-------
list of RnaGraphWrappers
"""
result = []
for sequence in sequences:
# if we eat a tupple, it musst be a (name, sequence) type :) we only want a sequence
if type(sequence)== type(()):
logger.warning( 'YOUR INPUT IS A TUPPLE, GIVE ME A SEQUENCE, SINCERELY -- YOUR RNA PREPROCESSOR')
# get structure
structure,energy = self.NNmodel.transform_single(('fake',sequence))
if structure==None:
result.append(None)
continue
# the consensus structure is not meant to be used as a folding plan for individual sequences
# so we do the best we can to get a valid structure
if self.structure_mod:
structure,sequence= fix_structure(structure,sequence)
# built base_graph
base_graph = converter.sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=structure)
base_graph = self.vectorizer._edge_to_vertex_transform(base_graph)
base_graph = expanded_rna_graph_to_digraph(base_graph)
base_graph.graph['energy']=energy
result.append(
RnaWrapper(sequence, structure,base_graph, self.vectorizer, self.base_thickness_list,include_base=self.include_base, ignore_inserts=self.ignore_inserts)
)
return result
