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 _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 rnafold_to_eden(iterable=None, **options):
assert (is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
G = string_to_networkx(header, seq, **options)
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
G = seq_to_networkx(header, seq, **options)
yield G
def rnafold_to_eden(iterable=None, **options):
assert(is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
G = string_to_networkx(header, seq, **options)
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
G = seq_to_networkx(header, seq, **options)
yield G
def rnashapes_struct_to_eden(iterable, **options):
assert(is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
for G in string_to_networkx(header, seq, **options):
yield G
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s %s' % (header, seq)
G = seq_to_networkx(header, seq, **options)
yield G
def rnasubopt_to_eden(iterable, **options):
assert(is_iterable(iterable)), 'Not iterable'
for header, seq, const in iterable:
try:
for G in string_to_networkx(header, seq, const, **options):
yield G
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
G = seq_to_networkx(header, seq, **options)
yield G
def rnashapes_struct_to_eden(iterable, **options):
assert(is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
for G in string_to_networkx(header, seq, **options):
yield G
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s %s' % (header, seq)
graph = seq_to_networkx(header, seq, **options)
yield graph
def rnasubopt_to_eden(iterable, **options):
assert (is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
for graph in string_to_networkx(header, seq, **options):
yield graph
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
graph = seq_to_networkx(header, seq, **options)
yield 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 rnaplfold_to_eden(iterable, **options):
assert(is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
graph = string_to_networkx(header, seq, **options)
except Exception as e:
print
print '-' * 80
# print e.__doc__
print e.message
print 'Error in: %s %s' % (header, seq)
print 'Reverting to path graph from sequence'
graph = seq_to_networkx(header, seq, **options)
yield graph
def rnaplfold_to_eden(iterable, **options):
assert (is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
graph = string_to_networkx(header, seq, **options)
except Exception as e:
print
print '-' * 80
# print e.__doc__
print e.message
print 'Error in: %s %s' % (header, seq)
print 'Reverting to path graph from sequence'
graph = seq_to_networkx(header, seq, **options)
yield 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)
shape = options.get('shape', False)
energy = options.get('energy', False)
dotbracket = options.get('dotbracket', True)
split_components = options.get('split_components', False)
seq_info, seq_struct_list = rnashapes_wrapper(sequence, shape_type=shape_type, energy_range=energy_range, max_num=max_num)
if split_components:
for shape_str, energy_str, dotbracket_str in seq_struct_list:
graph = nx.Graph()
if shape:
graph_shape = seq_to_networkx('', shape_str)
graph = nx.disjoint_union(graph, graph_shape)
if energy:
graph_energy = seq_to_networkx('', energy_str)
graph = nx.disjoint_union(graph, graph_energy)
if dotbracket:
graph_dotbracket = seq_to_networkx('', dotbracket_str)
graph = nx.disjoint_union(graph, graph_dotbracket)
graph.graph['id'] = header + '_' + shape_str
graph.graph['info'] = 'RNAshapes shape_type=%s energy_range=%s max_num=%s shape=%s energy=%s dotbracket=%s' % (
shape_type, energy_range, max_num, shape, energy, dotbracket)
graph.graph['sequence'] = sequence
yield graph
else:
graph_global = nx.Graph()
for shape_str, energy_str, dotbracket_str in seq_struct_list:
graph = nx.Graph()
if shape:
graph_shape = seq_to_networkx('', shape_str)
graph = nx.disjoint_union(graph, graph_shape)
if energy:
graph_energy = seq_to_networkx('', energy_str)
graph = nx.disjoint_union(graph, graph_energy)
if dotbracket:
graph_dotbracket = seq_to_networkx('', dotbracket_str)
graph = nx.disjoint_union(graph, graph_dotbracket)
graph_global = nx.disjoint_union(graph_global, graph)
graph_global.graph['id'] = header
graph_global.graph['info'] = 'RNAshapes shape_type=%s energy_range=%s max_num=%s shape=%s energy=%s dotbracket=%s' % (
shape_type, energy_range, max_num, shape, energy, dotbracket)
graph_global.graph['sequence'] = sequence
yield graph_global
def rnafold_to_eden(iterable=None, **options):
'''
Parameters
----------
iterable: over (header_string, sequence_string)
options
Returns
-------
nx.graph generator
'''
assert (is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
graph = string_to_networkx(header, seq, **options)
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
graph = seq_to_networkx(header, seq, **options)
yield graph
def rnafold_to_eden(iterable=None, **options):
'''
Parameters
----------
iterable: over (header_string, sequence_string)
options
Returns
-------
nx.graph generator
'''
assert (is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
graph = string_to_networkx(header, seq, **options)
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
graph = seq_to_networkx(header, seq, **options)
yield graph
def rnashapes_to_eden(iterable, **options):
"""Transforms sequences to graphs that encode secondary structure information
according to the RNAShapes algorithm.
Parameters
----------
sequences : iterable
iterable pairs of header and sequence strings
rnashapes_version : int (default 2)
The version of RNAshapes that is in the path.
2 e.g. RNAshapes version 2.1.6
3 e.g. RNAshapes version 3.3.0
shape_type : int (default 5)
Is the level of abstraction or dissimilarity which defines a different shape.
In general, helical regions are depicted by a pair of opening and closing brackets
and unpaired regions are represented as a single underscore. The differences of the
shape types are due to whether a structural element (bulge loop, internal loop, multiloop,
hairpin loop, stacking region and external loop) contributes to the shape representation:
Five types are implemented.
1 Most accurate - all loops and all unpaired [_[_[]]_[_[]_]]_
2 Nesting pattern for all loop types and unpaired regions in external loop
and multiloop [[_[]][_[]_]]
3 Nesting pattern for all loop types but no unpaired regions [[[]][[]]]
4 Helix nesting pattern in external loop and multiloop [[][[]]]
5 Most abstract - helix nesting pattern and no unpaired regions [[][]]
energy_range : float (default 10)
Sets the energy range as percentage value of the minimum free energy.
For example, when relative deviation is specified as 5.0, and the minimum free energy
is -10.0 kcal/mol, the energy range is set to -9.5 to -10.0 kcal/mol.
Relative deviation must be a positive floating point number; by default it is set to to 10 %.
max_num : int (default 3)
Is the maximum number of structures that are generated.
split_components : bool (default False)
If True each structure is yielded as an independent graph. Otherwise all structures
are part of the same graph that has therefore several disconnectd components.
example: transform a simple sequence using RNAshapes version 3+
>>> graphs = rnashapes_to_eden([("ID", "CCCCCGGGGG")], rnashapes_version=3)
>>> g = graphs.next()
>>> # extract sequence from graph nodes
>>> "".join([ value["label"] for (key, value) in g.nodes(data=True)])
'CCCCCGGGGG'
>>> # get vertice types
>>> [(start, end, g.edge[start][end]["type"]) for start, end in g.edges()]
[(0, 8, 'basepair'), (0, 1, 'backbone'), (1, 2, 'backbone'), (1, 7, 'basepair'), (2, 3, 'backbone'), (2, 6, 'basepair'), (3, 4, 'backbone'), (4, 5, 'backbone'), (5, 6, 'backbone'), (6, 7, 'backbone'), (7, 8, 'backbone'), (8, 9, 'backbone')]
example: transform a simple sequence using RNAshapes version 3+, splitting components
>>> graphs = rnashapes_to_eden([("ID", "CCCCCGGGGG")], split_components=True, rnashapes_version=3)
>>> g = graphs.next()
>>> # extract sequence from graph nodes
>>> "".join([ value["label"] for (key, value) in g.nodes(data=True)])
'CCCCCGGGGG'
>>> # get dotbracket structure annotation
>>> g.graph["structure"]
'(((...))).'
>>> # get vertice types
>>> [ (start, end, g.edge[start][end]["type"]) for start, end in g.edges()]
[(0, 8, 'basepair'), (0, 1, 'backbone'), (1, 2, 'backbone'), (1, 7, 'basepair'), (2, 3, 'backbone'), (2, 6, 'basepair'), (3, 4, 'backbone'), (4, 5, 'backbone'), (5, 6, 'backbone'), (6, 7, 'backbone'), (7, 8, 'backbone'), (8, 9, 'backbone')]
test max_num parameter with RNAshapes version 3+
>>> seq = "CGUCGUCGCAUCGUACGCAUGACUCAGCAUCAGACUACGUACGCAUACGUCAGCAUCAGUCAGCAUCAGCAUGCAUCACUAGCAUGCACCCCCGGGGGCACAUCGUACGUACGCUCAGUACACUGCAUGACUACGU"
>>> graphs = rnashapes_to_eden([("ID", seq)], split_components=True, max_num=2, rnashapes_version=3)
>>> g = graphs.next()
>>> # get dotbracket structure annotations
>>> len([g.graph["structure"] for g in graphs])
2
"""
assert(is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
for graph in string_to_networkx(header, seq, **options):
yield graph
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
graph = seq_to_networkx(header, seq, **options)
yield graph
def rnashapes_to_eden(iterable, **options):
"""Transforms sequences to graphs that encode secondary structure information
according to the RNAShapes algorithm.
Parameters
----------
sequences : iterable
iterable pairs of header and sequence strings
rnashapes_version : int (default 2)
The version of RNAshapes that is in the path.
2 e.g. RNAshapes version 2.1.6
3 e.g. RNAshapes version 3.3.0
shape_type : int (default 5)
Is the level of abstraction or dissimilarity which defines a different shape.
In general, helical regions are depicted by a pair of opening and closing brackets
and unpaired regions are represented as a single underscore. The differences of the
shape types are due to whether a structural element (bulge loop, internal loop, multiloop,
hairpin loop, stacking region and external loop) contributes to the shape representation:
Five types are implemented.
1 Most accurate - all loops and all unpaired [_[_[]]_[_[]_]]_
2 Nesting pattern for all loop types and unpaired regions in external loop
and multiloop [[_[]][_[]_]]
3 Nesting pattern for all loop types but no unpaired regions [[[]][[]]]
4 Helix nesting pattern in external loop and multiloop [[][[]]]
5 Most abstract - helix nesting pattern and no unpaired regions [[][]]
energy_range : float (default 10)
Sets the energy range as percentage value of the minimum free energy.
For example, when relative deviation is specified as 5.0, and the minimum free energy
is -10.0 kcal/mol, the energy range is set to -9.5 to -10.0 kcal/mol.
Relative deviation must be a positive floating point number; by default it is set to to 10 %.
max_num : int (default 3)
Is the maximum number of structures that are generated.
split_components : bool (default False)
If True each structure is yielded as an independent graph. Otherwise all structures
are part of the same graph that has therefore several disconnectd components.
example: transform a simple sequence using RNAshapes version 3+
>>> graphs = rnashapes_to_eden([("ID", "CCCCCGGGGG")], rnashapes_version=3)
>>> g = graphs.next()
>>> # extract sequence from graph nodes
>>> "".join([ value["label"] for (key, value) in g.nodes(data=True)])
'CCCCCGGGGG'
>>> # get vertice types
>>> [(start, end, g.edge[start][end]["type"]) for start, end in g.edges()]
[(0, 8, 'basepair'), (0, 1, 'backbone'), (1, 2, 'backbone'), (1, 7, 'basepair'), (2, 3, 'backbone'), (2, 6, 'basepair'), (3, 4, 'backbone'), (4, 5, 'backbone'), (5, 6, 'backbone'), (6, 7, 'backbone'), (7, 8, 'backbone'), (8, 9, 'backbone')]
example: transform a simple sequence using RNAshapes version 3+, splitting components
>>> graphs = rnashapes_to_eden([("ID", "CCCCCGGGGG")], split_components=True, rnashapes_version=3)
>>> g = graphs.next()
>>> # extract sequence from graph nodes
>>> "".join([ value["label"] for (key, value) in g.nodes(data=True)])
'CCCCCGGGGG'
>>> # get dotbracket structure annotation
>>> g.graph["structure"]
'(((...))).'
>>> # get vertice types
>>> [ (start, end, g.edge[start][end]["type"]) for start, end in g.edges()]
[(0, 8, 'basepair'), (0, 1, 'backbone'), (1, 2, 'backbone'), (1, 7, 'basepair'), (2, 3, 'backbone'), (2, 6, 'basepair'), (3, 4, 'backbone'), (4, 5, 'backbone'), (5, 6, 'backbone'), (6, 7, 'backbone'), (7, 8, 'backbone'), (8, 9, 'backbone')]
test max_num parameter with RNAshapes version 3+
>>> seq = "CGUCGUCGCAUCGUACGCAUGACUCAGCAUCAGACUACGUACGCAUACGUCAGCAUCAGUCAGCAUCAGCAUGCAUCACUAGCAUGCACCCCCGGGGGCACAUCGUACGUACGCUCAGUACACUGCAUGACUACGU"
>>> graphs = rnashapes_to_eden([("ID", seq)], split_components=True, max_num=2, rnashapes_version=3)
>>> g = graphs.next()
>>> # get dotbracket structure annotations
>>> len([g.graph["structure"] for g in graphs])
2
"""
assert (is_iterable(iterable)), 'Not iterable'
for header, seq in iterable:
try:
for graph in string_to_networkx(header, seq, **options):
yield graph
except Exception as e:
print e.__doc__
print e.message
print 'Error in: %s' % seq
graph = seq_to_networkx(header, seq, **options)
yield graph
