def run(self):
"""
10-29-05 call p_gene_id_set_from_gene_p_table()
"""
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
if self.new_table:
self.create_good_cluster_table(curs, self.good_cluster_table)
p_gene_id_set = p_gene_id_set_from_gene_p_table(curs, self.gene_p_table)
mcl_id2unknown_ratio = self.get_mcl_id2unknown_ratio(curs, self.p_gene_table, p_gene_id_set)
self.submit_good_clusters(curs, self.cluster_queue, self.good_cluster_table, mcl_id2unknown_ratio, self.occurrence_cutoff)
if self.commit:
curs.execute("end")
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)
def run(self):
"""
10-31-05
2006-09-26
modify it to be compatible with the modified pipeline from haifeng
2006-11-06
add type
2006-12-13
use font_path and font_size
--form_schema_tables()
--db_connect()
--get_char_dimension()
--get_no_of_p_funcs_gene_no_go_no_list()
--get_recurrence_go_no_rec_array_cluster_id_ls()
--get_go_no2name()
--draw_function_map()
--draw_gene_function_map()
--get_recurrence_rec_array_bs_no_list()
--get_mt_no2tf_name()
--draw_tf_map()
"""
schema_instance = form_schema_tables(self.inputfname, self.acc_cutoff, self.lm_bit)
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
font = ImageFont.truetype(self.font_path, self.font_size)
char_dimension = font.getsize('a')
#char_dimension = get_char_dimension()
#go_no2name = get_go_no2name(curs)
go_no2name = get_go_id2name(curs)
if self.type==1:
go_no2go_id = get_go_no2go_id(curs)
given_p_gene_set = p_gene_id_set_from_gene_p_table(curs, schema_instance.gene_p_table)
no_of_p_funcs_gene_no_go_no_list, mcl_id2go_no_set = self.get_no_of_p_funcs_gene_no_go_no_list_from_db(curs, \
schema_instance.p_gene_table, given_p_gene_set, go_no2go_id)
elif self.type==2:
no_of_p_funcs_gene_no_go_no_list, mcl_id2go_no_set = self.get_no_of_p_funcs_gene_no_go_no_list_from_file(self.inputfname)
recurrence_go_no_rec_array_cluster_id_ls, no_of_datasets, mcl_id2enc_recurrence = \
self.get_recurrence_go_no_rec_array_cluster_id_ls(curs, self.pattern_table, mcl_id2go_no_set)
no_of_functions = len(recurrence_go_no_rec_array_cluster_id_ls)
function_map_output_fname = '%s.function_map.png'%self.output_prefix
go_no2index, function_name_region = self.draw_function_map(recurrence_go_no_rec_array_cluster_id_ls, no_of_datasets,\
go_no2name, function_map_output_fname, self.function_name_length, char_dimension, no_of_functions, font)
gene_function_map_output_fname = '%s.gene_function_map.png'%self.output_prefix
self.draw_gene_function_map(no_of_p_funcs_gene_no_go_no_list, go_no2index, function_name_region,\
gene_function_map_output_fname, self.function_name_length, char_dimension, no_of_functions, font)
#tf_map requires mcl_id2enc_recurrence and no_of_datasets from above
recurrence_rec_array_bs_no_list = self.get_recurrence_rec_array_bs_no_list(curs, self.cluster_bs_table, mcl_id2enc_recurrence)
mt_no2tf_name = get_gene_id2gene_symbol(curs, tax_id=9606)
#mt_no2tf_name = get_mt_no2tf_name()
tf_map_output_fname = '%s.tf_map.png'%self.output_prefix
self.draw_tf_map(recurrence_rec_array_bs_no_list, no_of_datasets, mt_no2tf_name, \
tf_map_output_fname, self.function_name_length, char_dimension, font)
