print "Number of nodes in network:%d" % network.number_of_nodes()
'''
# Remove unannotated gene from network
for node in network.nodes():
if not node in gene_annotation:
network.remove_node(node)
print "Number of nodes in network after removing unannotated genes:%d" % network.number_of_nodes()
'''
# Remove individual nodes by get the largest indepedent connected component
network = nx.connected_component_subgraphs(network)[0]
print "Number of nodes in network after removing individual genes:%d" % network.number_of_nodes()
print "Number of edges in network after removing individual genes:%d" % network.number_of_edges()
network_annotated_gene = {} # cross validation set of annotated genes
for gene in gene_annotation:
if gene in network.nodes():
network_annotated_gene[gene] = gene_annotation[gene]
print "Number of annotated genes in network:%d" % len(network_annotated_gene)
sim_terms = utils.filtered_most_sim()
sim_cache = utils.read_sim(config.simcache_fpath)
wang_sim_cache = utils.read_sim(config.folder + "filtered_wang_sim.csv")
#remove_predict()
for GONUMBER in range(1, 11):
cross_validation()
sim = compute_gene_sim_total(nterms, terms)
#sim = compute_gene_sim_max(nterms, terms)
non_sim_avg += sim
non_sim_avg /= count
print "%s, %f, %f" % (gene, sim_avg, non_sim_avg)
if __name__ == "__main__":
dag = DAG(config.go_fpath)
gene_annotation = utils.get_annotation(config.annotation_fpath, config.filtered_annotation_fpath, dag.get_root().id)
term_ic = utils.calculate_ic(gene_annotation, dag, config.ic_fpath)
network = utils.create_network(config.network_fpath)
# Remove unannotated gene from network
for node in network.nodes():
if not node in gene_annotation:
network.remove_node(node)
# Remove individual nodes by get the largest indepedent connected component
network = nx.connected_component_subgraphs(network)[0]
sim_cache = utils.read_sim(config.simcache_fpath)
#compute_term_in_neighbour_ratio()
#compute_avg_term_num()
compute_avg_sim()
def iterate_weighted_mv(network, annotated_genes, go_num):
predicted_genes = {}
iter = 0
last_sum = -1.0
ITERATION = 20
sim_cache = utils.read_sim("pfalciparum_data/modified_wang_sim.csv")
while iter < ITERATION:
total_sum = 0.0
for gene in network.nodes():
if not gene in annotated_genes:
candidate_terms = get_candidate_terms(network, gene, annotated_genes, predicted_genes)
cterm_sim_sum = {}
for cterm in candidate_terms:
sim_sum = 0.0
# For each neighbour of gene
for neighbour in network.neighbors(gene):
if neighbour in annotated_genes:
max_sim = -1.0
for nterm in annotated_genes[neighbour]:
new_sim = sim_cache[cterm][nterm]
if new_sim > max_sim:
max_sim = new_sim
if gene in predicted_genes:
weight = compute_gene_sim(predicted_genes[gene], annotated_genes[neighbour], sim_cache)
else:
weight = compute_gene_sim([cterm], annotated_genes[neighbour], sim_cache)
sim_sum += 1.0 * weight * max_sim
elif neighbour in predicted_genes:
max_sim = -1.0
for nterm in predicted_genes[neighbour]:
new_sim = sim_cache[cterm][nterm]
if new_sim > max_sim:
max_sim = new_sim
if gene in predicted_genes:
weight = compute_gene_sim(predicted_genes[gene], predicted_genes[neighbour], sim_cache)
else:
weight = compute_gene_sim([cterm], predicted_genes[neighbour], sim_cache)
sim_sum += 1.0 * weight * max_sim
cterm_sim_sum[cterm] = sim_sum
if len(candidate_terms) > 0:
# Select top go_num terms as predicted GO terms for the gene
top_terms = heapq.nlargest(go_num, cterm_sim_sum.iteritems(), itemgetter(1))
if gene in predicted_genes:
del predicted_genes[gene]
predicted_genes[gene] = []
for rec in top_terms:
predicted_genes[gene].append(rec[0])
total_sum = compute_total_sim(network, annotated_genes, predicted_genes, sim_cache)
diff = int(total_sum) - int(last_sum)
if diff==0:
break
else:
last_sum = total_sum
iter += 1
return predicted_genes
