def submit_predictions(self, curs, schema_instance, prediction_pair2instance, cluster_id2properties):
sys.stderr.write("Submitting predictions...\n")
MpiPredictionFilter_instance = MpiPredictionFilter()
MpiPredictionFilter_instance.createGeneTable(curs, schema_instance.p_gene_table)
no_of_total_genes = get_no_of_total_genes(curs)
go_no2gene_no_set = get_go_no2gene_no_set(curs)
counter = 0
for prediction_pair, p_attr_instance in prediction_pair2instance.iteritems():
#1st fill those empty items
properties = cluster_id2properties[p_attr_instance.mcl_id]
vertex_set = properties[2]
p_attr_instance.p_value_cut_off = cal_hg_p_value(p_attr_instance.gene_no, p_attr_instance.go_no,\
vertex_set, no_of_total_genes, go_no2gene_no_set, r)
p_attr_instance.avg_p_value = p_attr_instance.p_value_cut_off
p_attr_instance.connectivity_cut_off = properties[0]
p_attr_instance.cluster_size_cut_off = len(vertex_set)
p_attr_instance.unknown_cut_off = properties[1]
MpiPredictionFilter_instance.submit_to_p_gene_table(curs, schema_instance.p_gene_table, p_attr_instance)
counter += 1
if self.report and counter%2000==0:
sys.stderr.write("%s%s"%('\x08'*20, counter))
if self.report:
sys.stderr.write("%s%s"%('\x08'*20, counter))
sys.stderr.write("Done.\n")
def data_fetch(
self,
curs,
schema_instance,
filter_type,
is_correct_type,
no_of_total_genes,
go_no2gene_no_set,
need_cal_hg_p_value=0,
):
"""
11-09-05
1st get the data from p_gene_table and remove redundancy given filter_type
2nd transform the data to three lists
11-10-05 add a chunk of code to get hg p-value(leave one out) for the prediction
mcl_id2vertex_list might blow the memory.(?)
11-19-05
separate predictions totally into known and unknown
2006-10-30, add avg_degree(vertex_gradient) and unknown_cut_off
"""
sys.stderr.write("Fetching data from old p_gene_table...\n")
prediction_pair2instance = {}
curs.execute(
"DECLARE crs CURSOR FOR SELECT p.p_gene_id, p.gene_no, p.go_no, p.is_correct, p.is_correct_l1, \
p.is_correct_lca, p.avg_p_value, p.no_of_clusters, p.cluster_array, p.p_value_cut_off, p.recurrence_cut_off, \
p.connectivity_cut_off, p.cluster_size_cut_off, p.unknown_cut_off, p.depth_cut_off, p.mcl_id, p.lca_list, p.vertex_gradient,\
p.edge_gradient from %s p"
% (schema_instance.p_gene_table)
)
curs.execute("fetch 10000 from crs")
rows = curs.fetchall()
counter = 0
real_counter = 0
while rows:
for row in rows:
p_attr_instance = prediction_attributes(row, type=2)
prediction_pair = (p_attr_instance.gene_no, p_attr_instance.go_no)
if prediction_pair not in prediction_pair2instance:
prediction_pair2instance[prediction_pair] = p_attr_instance
real_counter += 1
else: # remove redundancy
if filter_type == 1:
new_cmp_value = p_attr_instance.recurrence_cut_off
old_cmp_value = prediction_pair2instance[prediction_pair].recurrence_cut_off
elif filter_type == 2:
new_cmp_value = p_attr_instance.edge_gradient
old_cmp_value = prediction_pair2instance[prediction_pair].edge_gradient
elif filter_type == 3:
new_cmp_value = p_attr_instance.recurrence_cut_off + p_attr_instance.edge_gradient
old_cmp_value = (
prediction_pair2instance[prediction_pair].recurrence_cut_off
+ prediction_pair2instance[prediction_pair].edge_gradient
)
if new_cmp_value > old_cmp_value:
prediction_pair2instance[prediction_pair] = p_attr_instance
counter += 1
if self.report:
sys.stderr.write("%s%s/%s" % ("\x08" * 20, counter, real_counter))
curs.execute("fetch 10000 from crs")
rows = curs.fetchall()
unknown_prediction_ls = []
known_prediction_ls = []
unknown_data = [] # 11-19-05
known_data = []
for prediction_pair, p_attr_instance in prediction_pair2instance.iteritems():
# 11-10-05
mcl_id2vertex_list = {}
if need_cal_hg_p_value:
mcl_id = p_attr_instance.mcl_id
if mcl_id not in mcl_id2vertex_list:
mcl_id2vertex_list[mcl_id] = self.get_vertex_list(curs, schema_instance, mcl_id)
p_attr_instance.p_value_cut_off = cal_hg_p_value(
p_attr_instance.gene_no,
p_attr_instance.go_no,
mcl_id2vertex_list[mcl_id],
no_of_total_genes,
go_no2gene_no_set,
r,
)
is_correct = p_attr_instance.is_correct_dict[is_correct_type]
# 2006-10-30, add avg_degree(vertex_gradient) and unknown_cut_off
data_row = [
p_attr_instance.p_value_cut_off,
p_attr_instance.recurrence_cut_off,
p_attr_instance.connectivity_cut_off,
p_attr_instance.cluster_size_cut_off,
p_attr_instance.edge_gradient,
p_attr_instance.vertex_gradient,
p_attr_instance.unknown_cut_off,
p_attr_instance.gene_no,
p_attr_instance.go_no,
is_correct,
]
if is_correct != -1:
known_data.append(data_row) # to do fitting
known_prediction_ls.append(p_attr_instance)
else:
unknown_data.append(data_row)
unknown_prediction_ls.append(p_attr_instance)
sys.stderr.write("Done fetching data.\n")
return unknown_prediction_ls, known_prediction_ls, unknown_data, known_data
