def main():
if len(sys.argv) != 2:
print "Usage:python %s mouse/tcga_cancer_index" % sys.argv[0]
exit()
data_type = sys.argv[1]
assert data_type == "mouse" or data_type.isdigit()
if data_type.isdigit():
data_type = file_operations.get_tcga_disease_list()[int(data_type)]
if data_type == "mouse":
pcc_threshold = 0.9
else:
# TCGA coefficients are worse.
pcc_threshold = 0.5
# Read in the tsv file.
gene_exp_dct = file_operations.get_gene_expression_dct(data_type)
high_std_genes = file_operations.get_high_std_genes(data_type)
gene_exp_matrix = create_gene_exp_matrix(gene_exp_dct, high_std_genes)
r, p = corrcoef(gene_exp_matrix)
out = open("./data/%s_data/high_std_network.txt" % data_type, "w")
for row_idx, row in enumerate(r):
for col_idx, pcc in enumerate(row):
if col_idx <= row_idx or pcc < pcc_threshold or pcc == 1:
continue
# if p[row_idx][col_idx] > P_VALUE_THRESOLD:
# continue
# Write out gene information.
gene_a, gene_b = (high_std_genes[row_idx], high_std_genes[col_idx])
out.write("%s\t%s\t%f\n" % (gene_a, gene_b, abs(pcc)))
out.close()