def dstruc_loadin(self, curs):
"""
03-14-05
remove the distance loading part
"""
sys.stderr.write("Loading Data STructure...\n")
from codense.common import get_known_genes_dict, get_go_no2go_id,\
get_go_no2term_id, get_go_no2depth, get_go_term_id2go_no, \
get_go_term_id2depth
self.known_genes_dict = get_known_genes_dict(curs)
self.go_no2go_id = get_go_no2go_id(curs)
self.go_no2term_id = get_go_no2term_id(curs)
self.go_no2depth = get_go_no2depth(curs)
self.go_term_id2go_no = get_go_term_id2go_no(curs)
self.go_term_id2depth = get_go_term_id2depth(curs)
sys.stderr.write("Done\n")
def output(self, curs, gene_no2go_id_set_list, go_id_set_list, support, prefix, gene_no2id, go_id2name, schema_list):
"""
07-06-05
"""
sys.stderr.write("Outputing...")
#get the total set
total_gene_no_set = Set()
total_go_id_set = Set()
for i in range(len(gene_no2go_id_set_list)):
total_gene_no_set |= Set(gene_no2go_id_set_list[i].keys())
total_go_id_set |= go_id_set_list[i]
print "the total number of genes is ",len(total_gene_no_set)
gene_ofname = '%s.gene'%prefix
function_ofname = '%s.function'%prefix
gene_writer = csv.writer(open(gene_ofname,'w'), delimiter='\t')
function_writer = csv.writer(open(function_ofname, 'w'), delimiter='\t')
gene_writer.writerow(['']+schema_list)
function_writer.writerow([''] + schema_list)
from gene_p_map_redundancy import gene_p_map_redundancy
node_distance_class = gene_p_map_redundancy()
go_id2term_id = get_go_id2term_id(curs)
go_term_id2depth = get_go_term_id2depth(curs)
#output the gene-oriented information
for gene_no in total_gene_no_set:
freq = 0
p_go_id_set_list = []
for i in range(len(gene_no2go_id_set_list)):
if gene_no in gene_no2go_id_set_list[i]:
p_go_id_set_list.append(gene_no2go_id_set_list[i][gene_no])
freq += 1
if freq == support:
if self.p_go_id_set_list_distinct(curs, p_go_id_set_list, node_distance_class, go_term_id2depth, go_id2term_id):
row = [gene_no2id[gene_no]]
for i in range(len(gene_no2go_id_set_list)):
if gene_no in gene_no2go_id_set_list[i]:
go_id_set = gene_no2go_id_set_list[i][gene_no]
go_name_list = dict_map(go_id2name, go_id_set)
row.append(';'.join(go_name_list))
else:
row.append('')
gene_writer.writerow(row)
#output the function_oriented information
for go_id in total_go_id_set:
freq = 0
for i in range(len(go_id_set_list)):
if go_id in go_id_set_list[i]:
freq += 1
if freq == support:
row = ['%s(%s)'%(go_id2name[go_id],go_id)]
for i in range(len(go_id_set_list)):
if go_id in go_id_set_list[i]:
row.append('1')
else:
row.append('0')
function_writer.writerow(row)
sys.stderr.write("Done.\n")
