def __init__(self, genomes, name, log_file, tl):
if len(genomes) != 3:
raise Exception("Incorrect number of genomes for median problems")
self.gene_sets = [
set(genome.get_gene_multiset().keys()) for genome in genomes
]
self.s_all_genes = complete_genes_multiset(
reduce(operator.or_, self.gene_sets, set()), 1)
self.cbg_vertex_set = vertex_set_from_gene_multiset(self.s_all_genes)
self.cbg_ind2vertex = [''] + [u for u in self.cbg_vertex_set]
self.cbg_vertex2ind = {
self.cbg_ind2vertex[i]: i
for i in range(1, len(self.cbg_ind2vertex))
}
obverse_edges = observed_edges_from_gene_multiset(self.s_all_genes)
self.ind_cbg_obverse_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in obverse_edges
}
genome_graphs = [
genome.convert_to_genome_graph() for genome in genomes
]
self.ind_cbg_p_i_vertex_sets = [{
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(
complete_genes_multiset(gene_set, 1))
} for gene_set in self.gene_sets]
self.ind_cbg_p_i_edges = [{
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in matching
} for matching, _ in genome_graphs]
self.ind_cbg_p_i_telomers = [{
self.cbg_vertex2ind[u]
for u in telomers
} for _, telomers in genome_graphs]
self.ind_ancestral_set = set(
reduce(operator.or_, [
self.ind_cbg_p_i_vertex_sets[i]
& self.ind_cbg_p_i_vertex_sets[j]
for i, j in itertools.combinations(range(len(genomes)), 2)
], set()))
self.ancestral_gene_set = reduce(operator.or_, [
self.gene_sets[i] & self.gene_sets[j]
for i, j in itertools.combinations(range(len(self.gene_sets)), 2)
], set())
self.number_of_genomes = len(genomes)
self.biggest_const = len(self.cbg_ind2vertex)
self.name_model = name
self.log_file = log_file
self.time_limit = tl
def __init__(self,
duplicated_genome,
ordinary_genomes,
name,
log_file,
tl,
mult=2):
if len(ordinary_genomes) != 1:
raise Exception(
"Incorrect number of genomes for guided halving problems")
if mult < 2 or mult > 3:
raise Exception("Unsupported multiplication of a genome")
self.gene_sets = [
set(genome.get_gene_multiset().keys())
for genome in ordinary_genomes
]
self.genes_of_dupl_genome = duplicated_genome.get_gene_multiset()
self.s_all_genes = complete_genes_multiset(
reduce(operator.or_, self.gene_sets, set())
| self.genes_of_dupl_genome.keys(), 1)
# Coding contracted breakpoint graph
self.cbg_vertex_set = vertex_set_from_gene_multiset(self.s_all_genes)
self.cbg_ind2vertex = [''] + [u for u in self.cbg_vertex_set]
self.cbg_vertex2ind = {
self.cbg_ind2vertex[i]: i
for i in range(1, len(self.cbg_ind2vertex))
}
obverse_edges = observed_edges_from_gene_multiset(self.s_all_genes)
self.ind_cbg_obverse_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in obverse_edges
}
genome_graphs = [
genome.convert_to_genome_graph() for genome in ordinary_genomes
]
self.ind_cbg_p_i_vertex_sets = [{
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(
complete_genes_multiset(gene_set, 1))
} for gene_set in self.gene_sets]
self.ind_cbg_p_i_edges = [{
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in matching
} for matching, _ in genome_graphs]
self.ind_cbg_p_i_telomers = [{
self.cbg_vertex2ind[u]
for u in telomers
} for _, telomers in genome_graphs]
# This contracted genome graph does not contain parallel edges. Maybe a problem.
cbg_A_matching, cbg_A_telomers = duplicated_genome.convert_to_contracted_genome_graph(
)
self.ind_cbg_A_vertices = {
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(
complete_genes_multiset(self.genes_of_dupl_genome.keys(), 1))
}
self.ind_cbg_A_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in cbg_A_matching
}
self.ind_cbg_A_telomers = {
self.cbg_vertex2ind[u]
for u in cbg_A_telomers
}
self.ms_all_genes = complete_genes_multiset(
reduce(operator.or_, self.gene_sets, set())
| self.genes_of_dupl_genome.keys(), mult)
# Coding breakpoint graph
self.bg_vertex_set = vertex_set_from_gene_multiset(self.ms_all_genes)
self.bg_ind2vertex = [''] + [u for u in self.bg_vertex_set]
self.bg_vertex2ind = {
self.bg_ind2vertex[i]: i
for i in range(1, len(self.bg_ind2vertex))
}
bg_A_matching, bg_A_telomers = duplicated_genome.convert_to_genome_graph(
)
self.ind_bg_A_vertices = {
self.bg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(self.genes_of_dupl_genome)
}
self.ind_bg_A_edges = {
tuple(sorted((self.bg_vertex2ind[u], self.bg_vertex2ind[v])))
for u, v in bg_A_matching
}
self.ind_bg_A_telomers = {self.bg_vertex2ind[u] for u in bg_A_telomers}
# Connection between graphs
self.equiv_map = define_equiv_function(self.ms_all_genes,
self.cbg_vertex2ind,
self.bg_vertex2ind)
# TODO: HERE need to extend for indels
self.ind_ancestral_set = self.ind_cbg_p_i_vertex_sets[0]
self.ancestral_gene_set = self.gene_sets[0]
self.multiplicity = mult
self.number_of_genomes = len(ordinary_genomes)
self.biggest_const = len(self.bg_ind2vertex)
self.name_model = name
self.log_file = log_file
self.time_limit = tl
flag = False
if len(self.ind_bg_A_telomers) != 0:
flag = True
for i in range(self.number_of_genomes):
if len(self.ind_cbg_p_i_telomers[i]) != 0:
flag = True
self.allowable_ancestral_telomers = {
x: flag
for x in self.ind_ancestral_set
}
graph = nx.MultiGraph()
graph.add_nodes_from(self.cbg_vertex2ind.values())
for edges in self.ind_cbg_A_edges:
for u, v in edges:
graph.add_edge(u, v)
self.number_of_even_cycles = 0
self.number_of_even_paths = 0
vertex_sets_for_ancestral_edges = []
meta_vertex_set_for_edges = []
for component in nx.connected_component_subgraphs(graph):
isCycle = True
for v in component.nodes():
if graph.degree(v) != 2:
isCycle = False
if isCycle and len(component.nodes()) % 2 == 0:
self.number_of_even_cycles += 1
vertex_sets_for_ancestral_edges.append(list(component.nodes()))
elif len(component.nodes()) % 2 != 0 and not isCycle:
self.number_of_even_paths += 1
meta_vertex_set_for_edges.extend(component.nodes())
else:
meta_vertex_set_for_edges.extend(component.nodes())
vertex_sets_for_ancestral_edges.append(meta_vertex_set_for_edges)
self.allowable_ancestral_edges = set()
self.connection_ancestral_constrs = dict()
for v_set in vertex_sets_for_ancestral_edges:
self.allowable_ancestral_edges.update({
tuple(sorted([u, v]))
for u, v in itertools.combinations(v_set, 2)
})
self.connection_ancestral_constrs.update({
u: {tuple(sorted((u, v)))
for v in v_set if u != v}
for u in v_set
})
def __init__(self, genomes, name, log_file, tl):
if len(genomes) != 3:
raise Exception("Incorrect number of genomes for median problem")
self.gene_sets = [
set(genome.get_gene_multiset().keys()) for genome in genomes
]
self.s_all_genes = complete_genes_multiset(
reduce(operator.or_, self.gene_sets, set()), 1)
self.cbg_vertex_set = vertex_set_from_gene_multiset(self.s_all_genes)
self.cbg_ind2vertex = [''] + [u for u in self.cbg_vertex_set]
self.cbg_vertex2ind = {
self.cbg_ind2vertex[i]: i
for i in range(1, len(self.cbg_ind2vertex))
}
obverse_edges = observed_edges_from_gene_multiset(self.s_all_genes)
self.ind_cbg_obverse_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in obverse_edges
}
genome_graphs = [
genome.convert_to_genome_graph() for genome in genomes
]
self.ind_cbg_p_i_vertex_sets = [{
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(
complete_genes_multiset(gene_set, 1))
} for gene_set in self.gene_sets]
self.ind_cbg_p_i_edges = [{
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in matching
} for matching, _ in genome_graphs]
self.ind_cbg_p_i_telomers = [{
self.cbg_vertex2ind[u]
for u in telomers
} for _, telomers in genome_graphs]
self.ind_ancestral_set = set(
reduce(operator.or_, [
self.ind_cbg_p_i_vertex_sets[i]
& self.ind_cbg_p_i_vertex_sets[j]
for i, j in itertools.combinations(range(len(genomes)), 2)
], set()))
self.ancestral_gene_set = reduce(operator.or_, [
self.gene_sets[i] & self.gene_sets[j]
for i, j in itertools.combinations(range(len(self.gene_sets)), 2)
], set())
self.number_of_genomes = len(genomes)
self.biggest_const = len(self.cbg_ind2vertex)
self.name_model = name
self.log_file = log_file
self.time_limit = tl
flag = False
for i in range(3):
if len(self.ind_cbg_p_i_telomers[i]) != 0:
flag = True
self.allowable_telomers = {x: flag for x in self.ind_ancestral_set}
graph = nx.MultiGraph()
graph.add_nodes_from(self.cbg_vertex2ind.values())
for edges in self.ind_cbg_p_i_edges:
for u, v in edges:
graph.add_edge(u, v)
self.allowable_ancestral_edges = set()
self.connection_constrs = dict()
for component in nx.connected_component_subgraphs(graph):
for v in component.nodes():
connect_indices = set()
for u in component.nodes():
if u != v:
self.allowable_ancestral_edges.add(
tuple(sorted((u, v))))
connect_indices.add(tuple(sorted((u, v))))
self.connection_constrs[v] = connect_indices
self.number_of_cycles = 0
self.number_of_even_paths = 0
for component in nx.connected_component_subgraphs(graph):
isCycle = True
for v in component.nodes():
if graph.degree(v) != 2:
isCycle = False
if isCycle:
self.number_of_cycles += 1
elif (len(component.nodes()) - 1) % 2 == 0:
self.number_of_even_paths += 1
def __init__(self,
duplicated_genome,
ordinary_genomes,
name,
log_file,
tl,
mult=2):
if len(ordinary_genomes) != 1:
raise Exception(
"Incorrect number of genomes for guided halving problems")
if mult < 2 or mult > 3:
raise Exception("Unsupported multiplication of a genome")
self.gene_sets = [
set(genome.get_gene_multiset().keys())
for genome in ordinary_genomes
]
self.genes_of_dupl_genome = duplicated_genome.get_gene_multiset()
self.s_all_genes = complete_genes_multiset(
reduce(operator.or_, self.gene_sets, set())
| self.genes_of_dupl_genome.keys(), 1)
# Coding contracted breakpoint graph
self.cbg_vertex_set = vertex_set_from_gene_multiset(self.s_all_genes)
self.cbg_ind2vertex = [''] + [u for u in self.cbg_vertex_set]
self.cbg_vertex2ind = {
self.cbg_ind2vertex[i]: i
for i in range(1, len(self.cbg_ind2vertex))
}
obverse_edges = observed_edges_from_gene_multiset(self.s_all_genes)
self.ind_cbg_obverse_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in obverse_edges
}
genome_graphs = [
genome.convert_to_genome_graph() for genome in ordinary_genomes
]
self.ind_cbg_p_i_vertex_sets = [{
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(
complete_genes_multiset(gene_set, 1))
} for gene_set in self.gene_sets]
self.ind_cbg_p_i_edges = [{
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in matching
} for matching, _ in genome_graphs]
self.ind_cbg_p_i_telomers = [{
self.cbg_vertex2ind[u]
for u in telomers
} for _, telomers in genome_graphs]
# This contracted genome graph does not contain parallel edges. Maybe a problem.
cbg_A_matching, cbg_A_telomers = duplicated_genome.convert_to_contracted_genome_graph(
)
self.ind_cbg_A_vertices = {
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(
complete_genes_multiset(self.genes_of_dupl_genome.keys(), 1))
}
self.ind_cbg_A_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in cbg_A_matching
}
self.ind_cbg_A_telomers = {
self.cbg_vertex2ind[u]
for u in cbg_A_telomers
}
self.ms_all_genes = complete_genes_multiset(
reduce(operator.or_, self.gene_sets, set())
| self.genes_of_dupl_genome.keys(), mult)
# Coding breakpoint graph
self.bg_vertex_set = vertex_set_from_gene_multiset(self.ms_all_genes)
self.bg_ind2vertex = [''] + [u for u in self.bg_vertex_set]
self.bg_vertex2ind = {
self.bg_ind2vertex[i]: i
for i in range(1, len(self.bg_ind2vertex))
}
bg_A_matching, bg_A_telomers = duplicated_genome.convert_to_genome_graph(
)
self.ind_bg_A_vertices = {
self.bg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(self.genes_of_dupl_genome)
}
self.ind_bg_A_edges = {
tuple(sorted((self.bg_vertex2ind[u], self.bg_vertex2ind[v])))
for u, v in bg_A_matching
}
self.ind_bg_A_telomers = {self.bg_vertex2ind[u] for u in bg_A_telomers}
# Connection between graphs
self.equiv_map = define_equiv_function(self.ms_all_genes,
self.cbg_vertex2ind,
self.bg_vertex2ind)
# TODO: HERE need to extend for indels
self.ind_ancestral_set = self.ind_cbg_p_i_vertex_sets[0]
self.ancestral_gene_set = self.gene_sets[0]
self.multiplicity = mult
self.number_of_genomes = len(ordinary_genomes)
self.biggest_const = len(self.bg_ind2vertex)
self.name_model = name
self.log_file = log_file
self.time_limit = tl
def __init__(self,
ordinary_genome,
duplicated_genome,
name,
log_file,
tl,
mult=2):
if mult < 2 or mult > 3:
raise Exception("Unsupported multiplication of a genome")
self.multiplicity = mult
self.genes_of_dupl_genome = duplicated_genome.get_gene_multiset()
self.genes_of_ord_genome = ordinary_genome.get_gene_multiset()
self.s_all_genes = complete_genes_multiset(
self.genes_of_ord_genome.keys() | self.genes_of_dupl_genome.keys(),
1)
self.ms_all_genes = complete_genes_multiset(
self.genes_of_ord_genome.keys() | self.genes_of_dupl_genome.keys(),
mult)
# Coding breakpoint graph
self.bg_vertex_set = vertex_set_from_gene_multiset(self.ms_all_genes)
self.bg_ind2vertex = [''] + [u for u in self.bg_vertex_set]
self.bg_vertex2ind = {
self.bg_ind2vertex[i]: i
for i in range(1, len(self.bg_ind2vertex))
}
bg_A_matching, bg_A_telomers = duplicated_genome.convert_to_genome_graph(
)
self.ind_bg_A_vertices = {
self.bg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(self.genes_of_dupl_genome)
}
self.ind_bg_A_edges = {
tuple(sorted((self.bg_vertex2ind[u], self.bg_vertex2ind[v])))
for u, v in bg_A_matching
}
self.ind_bg_A_telomers = {self.bg_vertex2ind[u] for u in bg_A_telomers}
# Coding contracted breakpoint graph
self.cbg_vertex_set = vertex_set_from_gene_multiset(self.s_all_genes)
self.cbg_ind2vertex = [''] + [u for u in self.cbg_vertex_set]
self.cbg_vertex2ind = {
self.cbg_ind2vertex[i]: i
for i in range(1, len(self.cbg_ind2vertex))
}
cbg_R_matching, cbg_R_telomers = ordinary_genome.convert_to_genome_graph(
)
self.ind_cbg_R_vertices = {
self.cbg_vertex2ind[u]
for u in vertex_set_from_gene_multiset(self.genes_of_ord_genome)
}
self.ind_cbg_R_edges = {
tuple(sorted((self.cbg_vertex2ind[u], self.cbg_vertex2ind[v])))
for u, v in cbg_R_matching
}
self.ind_cbg_R_telomers = {
self.cbg_vertex2ind[u]
for u in cbg_R_telomers
}
self.equiv_map = define_equiv_function(self.ms_all_genes,
self.cbg_vertex2ind,
self.bg_vertex2ind)
# Coding completion of genomes
self.ind_compl_A = set(
self.bg_vertex2ind.values()) - self.ind_bg_A_vertices
self.ind_compl_R = set(self.bg_vertex2ind.values()) - reduce(
operator.or_,
[set(self.equiv_map[v]) for v in self.ind_cbg_R_vertices], set())
# hat_V(X)\V(R)
self.ind_cbg_compl_R = set(
self.cbg_vertex2ind.values()) - self.ind_cbg_R_vertices
# J_0(2R)
self.ind_bg_2R_telomers = reduce(
operator.or_,
[set(self.equiv_map[v]) for v in self.ind_cbg_R_telomers], set())
# J_1(A)
self.ind_bg_A_nontelomers = self.ind_bg_A_vertices - self.ind_bg_A_telomers
# J^1
self.ind_first_type_telomers = self.ind_bg_2R_telomers - self.ind_bg_A_vertices
# J^2
self.ind_second_type_telomers = self.ind_compl_A - self.ind_bg_2R_telomers
# J^3
self.ind_third_type_telomers = self.ind_bg_A_nontelomers & self.ind_bg_2R_telomers
# J^4
self.ind_forth_type_telomers = self.ind_bg_A_telomers - self.ind_bg_2R_telomers
self.biggest_const = len(self.bg_ind2vertex)
self.name_model = name
self.log_file = log_file
self.time_limit = tl