def dstruc_loadin(self, curs):
'''
'''
sys.stderr.write("Loading Data STructure...\n")
from codense.common import get_go_no2go_id, get_gene_no2gene_id, get_go_no2name, get_gene_id2gene_no, get_gene_no2go_no
self.go_no2go_id = get_go_no2go_id(curs)
self.go_no2go_name = get_go_no2name(curs)
self.gene_no2gene_id = get_gene_no2gene_id(curs)
self.gene_id2gene_no = get_gene_id2gene_no(curs)
self.global_gene_to_go_dict = get_gene_no2go_no(curs)
#04-01-05 the second kind in label_dict
gene_no2no = {}
for gene_no in self.gene_no2gene_id:
gene_no2no[gene_no] = gene_no
self.label_dict = {1:self.gene_no2gene_id,
2: gene_no2no}
curs.execute("select gene_no,go_functions from gene")
if self.type == 3:
curs.execute("select array_upper(recurrence_array,1) from %s limit 1"%self.table)
rows = curs.fetchall()
self.no_of_datasets = int(rows[0][0])
sys.stderr.write("Done\n")
def on_button_cluster_info_clicked(self, button_cluster_info, *args): if self.curs==None: print "db_connect first" return self.no_of_datasets = int(self.entry_no_of_datasets.get_text()) self.treeview_init(self.no_of_datasets) self.gene_no2gene_id = get_gene_no2gene_id(self.curs) self.gene_no2go_no = get_gene_no2go_no(self.curs) self.window_cluster_info1.show() self.window_cluster_info2.show()
def run(self):
communicator = MPI.world.duplicate()
node_rank = communicator.rank
free_computing_nodes = range(1,communicator.size-1) #exclude the last node
if node_rank == 0:
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
schema_instance = form_schema_tables(self.fname, self.acc_cutoff, self.lm_bit)
gene_id2no = get_gene_id2gene_no(curs)
gene2enc_array = self.get_gene2enc_array(self.gim_inputfname, gene_id2no)
gene2enc_array_pickle = cPickle.dumps(gene2enc_array, -1)
gene_no2id = get_gene_no2gene_id(curs)
gene_no2go_no = get_gene_no2go_no(curs)
gene_no2id_pickle = cPickle.dumps(gene_no2id, -1)
gene_no2go_no_pickle = cPickle.dumps(gene_no2go_no, -1)
for node in free_computing_nodes: #send it to the computing_node
communicator.send(gene2enc_array_pickle, node, 0)
communicator.send(gene_no2id_pickle, communicator.size-1, 0)
communicator.send(gene_no2go_no_pickle, communicator.size-1, 0)
elif node_rank in free_computing_nodes:
data, source, tag = communicator.receiveString(0, 0)
gene2enc_array = cPickle.loads(data) #take the data
elif node_rank==communicator.size-1:
schema_instance = form_schema_tables(self.fname, self.acc_cutoff, self.lm_bit)
data, source, tag = communicator.receiveString(0, 0)
gene_no2id = cPickle.loads(data)
data, source, tag = communicator.receiveString(0, 0)
gene_no2go_no = cPickle.loads(data)
mpi_synchronize(communicator)
if node_rank == 0:
curs.execute("DECLARE crs CURSOR FOR SELECT p.id, p.vertex_set, p.edge_set, p.recurrence_array,\
g.go_no_list from %s p, %s g where g.mcl_id=p.id"%(schema_instance.pattern_table, schema_instance.good_cluster_table))
input_node(communicator, curs, free_computing_nodes, self.message_size, self.report)
elif node_rank in free_computing_nodes:
parameter_list = [gene2enc_array, self.dataset_signature_set, self.p_value_cut_off]
computing_node(communicator, parameter_list, self.computing_node_handler, report=self.report)
elif node_rank==communicator.size-1:
if not os.path.isdir(self.pic_output_dir):
os.makedirs(self.pic_output_dir)
cluster_info_instance = cluster_info()
ofname = os.path.join(self.pic_output_dir, '%s_p%s'%(schema_instance.good_cluster_table, self.p_value_cut_off))
writer = csv.writer(open(ofname, 'w'), delimiter='\t')
parameter_list = [self.pic_output_dir, cluster_info_instance, gene_no2id, gene_no2go_no, writer]
output_node(communicator, free_computing_nodes, parameter_list, self.output_node_handler, self.report)
del writer
def prepare_gene_no2go_no(self, curs):
"""
04-15-05
different from get_gene_no2go_no, the value is a set.
04-27-05
only depth ==5
"""
sys.stderr.write("Preparing gene_no2go_no...")
#from codense.common import get_gene_no2go_no, get_go_no2depth
go_no2depth = get_go_no2depth(curs)
gene_no2go_no = get_gene_no2go_no(curs)
gene_no2go_no_set = {}
for gene_no,go_no_list in gene_no2go_no.iteritems():
gene_no2go_no_set[gene_no] = Set()
for go_no in go_no_list:
if go_no2depth[go_no] == 5:
gene_no2go_no_set[gene_no].add(go_no)
sys.stderr.write("Done.\n")
return gene_no2go_no_set
def run(self):
"""
10-17-05
bit control whether that setting has linear model
"""
schema_instance1 = form_schema_tables(self.fname1, self.acc_cutoff1, self.lm_bit1)
schema_instance2 = form_schema_tables(self.fname2, self.acc_cutoff2, self.lm_bit2)
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
p_gene_id_set1 = p_gene_id_set_from_gene_p_table(curs, schema_instance1.gene_p_table)
p_gene_id_set2 = p_gene_id_set_from_gene_p_table(curs, schema_instance2.gene_p_table)
p_gene_id_set_total = p_gene_id_set_from_gene_p_table(curs, schema_instance2.p_gene_table)
catI_set = p_gene_id_set1 - p_gene_id_set2
catII_set = p_gene_id_set1 & p_gene_id_set2
catIII_set = p_gene_id_set2 - p_gene_id_set1
catIV_set = p_gene_id_set_total-(p_gene_id_set1|p_gene_id_set2)
sample_ls_ls = []
for p_gene_id_set in [catI_set, catII_set, catIII_set, catIV_set]:
sample_ls_ls.append(self.sample_p_gene_id_set(p_gene_id_set, self.no_of_samples))
writer = csv.writer(open(self.ofname, 'w'), delimiter = '\t')
writer.writerow(['linear model coeffs of two settings'])
writer.writerow([])
writer.writerow(['No.','intercept', 'coeff1', 'coeff2', 'coeff3', 'coeff4', 'coeff5', 'intercept_p_value',\
'coeff1_p_value', 'coeff2_p_value', 'coeff3_p_value', 'coeff4_p_value', 'coeff5_p_value',\
'score_cut_off'])
#fetch linear model coefficients
pga_instance_list = [None, None] #10-17-05 default is nothing, none of them have linear model
if self.bit[0] == '1':
pga_instance1 = p_gene_analysis()
pga_instance1.go_no2lm_results, lm_results_2d_list = pga_instance1.get_go_no2lm_results(curs, schema_instance1.lm_table)
pga_instance1.general_lm_results = pga_instance1.get_general_lm_results(lm_results_2d_list)
pga_instance_list[0] = pga_instance1
self.output_lm_model(curs, schema_instance1, writer)
if self.bit[1] == '1':
pga_instance2 = p_gene_analysis()
pga_instance2.go_no2lm_results, lm_results_2d_list = pga_instance2.get_go_no2lm_results(curs, schema_instance2.lm_table)
pga_instance2.general_lm_results = pga_instance2.get_general_lm_results(lm_results_2d_list)
pga_instance_list[1] = pga_instance2
self.output_lm_model(curs, schema_instance2, writer)
#following is for drawing graph in output_p_gene_id_list()
self.gene_no2gene_id = get_gene_no2gene_id(curs)
self.gene_no2go_no = get_gene_no2go_no(curs)
cluster_info_instance = cluster_info()
for i in range(len(sample_ls_ls)):
cat_no = i+1
sys.stderr.write("Category %s...\n"%cat_no)
writer.writerow(['Category %s'%cat_no])
writer.writerow([self.category_no2information[cat_no]])
cat_dir = 'cat%s'%cat_no
if not os.path.isdir(cat_dir):
os.makedirs(cat_dir)
if i==0: #this is different, prediction only in schema_instance1, so swap it
self.output_p_gene_id_list(curs, schema_instance2, schema_instance1, sample_ls_ls[i], writer, cat_dir, \
pga_instance_list[1], pga_instance_list[0], cluster_info_instance, self.simple)
else:
self.output_p_gene_id_list(curs, schema_instance1, schema_instance2, sample_ls_ls[i], writer, cat_dir, \
pga_instance_list[0], pga_instance_list[1], cluster_info_instance, self.simple)
sys.stderr.write("End Category %s.\n"%cat_no)
