def _string_to_networkx(header, sequence, **options):
seq_info, seq_struct = rnafold_wrapper(sequence, **options)
graph = sequence_dotbracket_to_graph(seq_info=seq_info,
seq_struct=seq_struct)
graph.graph['info'] = 'RNAfold'
graph.graph['sequence'] = sequence
graph.graph['structure'] = seq_struct
graph.graph['id'] = header
return graph
def ses_to_graph(ses):
structure, energy, sequence = ses
base_graph = eden_rna.sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=structure)
#base_graph = _edge_to_vertex_transform(base_graph) # this keeps the dict
#base_graph = rna.expanded_rna_graph_to_digraph(base_graph) # i hope this keeps the dict
base_graph.graph['energy'] = energy
base_graph.graph['sequence'] = sequence
base_graph.graph['structure'] = structure
return base_graph
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 seq_to_graph(header, sequence):
"""Fold a sequence in a path graph."""
seq_struct = '.' * len(sequence)
graph = sequence_dotbracket_to_graph(seq_info=sequence,
seq_struct=seq_struct)
graph.graph['info'] = 'sequence'
graph.graph['sequence'] = sequence
graph.graph['structure'] = seq_struct
graph.graph['id'] = header
return graph
def calc(names,data, item,r,d,model=RandomForestRegressor()):
model = make_model(data,names,False,r,d, model)
graph = eden_rna.sequence_dotbracket_to_graph(data[item][1],data[item][2])
res = np.array(predict(model,graph))
other = np.array(data[item][0])
res,other = mask(res,other)
value = corr(res,other)[0]
#print '\t',len(data[item][1]),"\t", value
return value
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 = sequence_fold(header, sequence)
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 = sequence_fold(header, sequence)
yield graph_global
def predict(model, sequence,seq_to_db_function= rnasubopt):
db_list = seq_to_db_function(sequence)
if len(db_list)==1:
graph = eden_rna.sequence_dotbracket_to_graph(sequence, db_list[0])
return model.predict(eg.vertex_vectorize([graph])[0])
# get probability for each structure
struct_proba = probabilities_of_structures(sequence, db_list)
structures, weights = zip(*struct_proba)
# edenize and predict reacticuty
graphs = map(lambda x: getgraph(sequence,x), structures)
vecs = list(eg.vertex_vectorize(graphs,r=3,d=3))
predictions_all_structures = [ model.predict(blob) for blob in vecs ]
# mix reactivity with probabilities
return weighted_average(weights, predictions_all_structures)
def transform(self, sequences):
"""
Parameters
----------
sequences : iterable over rna sequences
Returns
-------
list of RnaGraphWrappers
"""
result = []
for sequence in sequences:
# get structure
structure, energy, sequence = self.NNmodel.transform_single(sequence)
# FIXING STRUCTURE
structure, sequence = fix_structure(structure, sequence)
if structure == None:
result.append(None)
continue
# built base_graph
base_graph = eden_rna.sequence_dotbracket_to_graph(seq_info=sequence, seq_struct=structure)
base_graph = _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
if self.fold_only:
result.append(base_graph)
else:
result.append(self.abstract_graph(base_graph))
# result.append(
# (sequence, structure, base_graph, self.abstract_graph(base_graph))
#)
return result
def getgraph(sequence,structure):
"""returns networkx graph"""
return eden_rna.sequence_dotbracket_to_graph(sequence,structure)