def compute_regression(input_cancer_type): if input_cancer_type == "CCRCC": cancer = cptac.Ccrcc() elif input_cancer_type == "Endometrial": cancer = cptac.Endometrial() elif input_cancer_type == "LUAD": cancer = cptac.Luad() elif input_cancer_type == "HNSCC": cancer = cptac.Hnscc() elif input_cancer_type == "LSCC": cancer = cptac.Lscc() elif input_cancer_type == "PDAC": cancer = cptac.Pdac() df = dc.get_prot_trans_df(cancer) results = df.groupby('Gene').apply(regression) reg_df = pd.DataFrame(list(results)) reg_df.index = results.index reg_df.reset_index(inplace=True) reg_df = reg_df.dropna() reg_df['interaction_FDR'] = ssm.fdrcorrection( reg_df['interaction_pval'])[1] reg_df['condition_FDR'] = ssm.fdrcorrection(reg_df['condition_pval'])[1] reg_df['intercept_FDR'] = ssm.fdrcorrection(reg_df['intercept_pval'])[1] reg_df['Cancer'] = [input_cancer_type] * len(reg_df) file_name = input_cancer_type + '_regressions.csv' reg_df.to_csv(file_name, index=False)
def load_cancers(include_pdac=False): ccrcc = cptac.Ccrcc() en = cptac.Endometrial() luad = cptac.Luad() hnscc = cptac.Hnscc() lscc = cptac.Lscc() cancers = [ccrcc, en, luad, hnscc, lscc] cancer_names = ['CCRCC', 'Endometrial', 'LUAD', 'HNSCC', 'LSCC'] if include_pdac: pdac = cptac.Pdac() cancers.append(pdac) cancer_names.append('PDAC') return cancers, cancer_names
input_cancer_type = sys.argv[1] mutated_gene = sys.argv[2] input_permutation_number = int(sys.argv[3]) cutoff = 15 if input_cancer_type == "CCRCC": cancer = cptac.Ccrcc() elif input_cancer_type == "Endometrial": cancer = cptac.Endometrial() cutoff = 10 elif input_cancer_type == "LUAD": cancer = cptac.Luad() elif input_cancer_type == "HNSCC": cancer = cptac.Hnscc() elif input_cancer_type == "LSCC": cancer = cptac.Lscc() elif input_cancer_type == "PDAC": cancer = cptac.Pdac() mutation_df = cancer.get_somatic_mutation() mutation_df = mutation_df[mutation_df.Gene == mutated_gene] mutation_df = mutation_df[mutation_df.Mutation != 'Silent'] mutation_df = mutation_df[mutation_df.Mutation != 'RNA'] mutation_df = mutation_df[mutation_df.Mutation != 'synonymous SNV'] mutation_df.reset_index(inplace=True) prot_trans_df = dc.get_prot_trans_df(cancer) prot_trans_df = prot_trans_df[prot_trans_df.Tissue == 'tumor'] prot_trans_df['Mutation'] = prot_trans_df.Patient_ID.isin( mutation_df.Patient_ID)
test_coord_1 = ((index_1, 1), (index_2, 1), (index_3, 1)) # C3N-01515 test_vals_1 = ('No_Mutation', 'No_Mutation', 'No_Mutation') # Test Del test_coord_2 = ((index_4, 1), (index_5, 1), (index_6, 1)) test_vals_2 = ('Deletion', 'Deletion', 'Deletion') # Test Amp test_coord_3 = ((index_7, 1), (index_8, 1), (index_9, 1)) test_vals_3 = ('Amplification', 'Amplification', 'Amplification') test_coord_vals = [(test_coord_1, test_vals_1), (test_coord_2, test_vals_2), (test_coord_3, test_vals_3)] for coord, vals in test_coord_vals: PASS = check_getter(df, dimensions, headers, coord, vals) print_test_result(PASS) k = cptac.Ccrcc() g = cptac.Gbm() h = cptac.Hnscc() print("\nRunning tests:\n") test_genotype_ccrcc_KRAS() test_genotype_gbm_KRAS() test_genotype_hnscc_KRAS() print("Version:", cptac.version())
import warnings warnings.filterwarnings("ignore") input_cancer_type = sys.argv[1] if input_cancer_type == "ccrcc": ccrcc = cptac.Ccrcc() cancer_list = [ccrcc] elif input_cancer_type == "en": en = cptac.Endometrial() cancer_list = [en] elif input_cancer_type == "luad": luad = cptac.Luad() cancer_list = [luad] elif input_cancer_type == "hnscc": hnscc = cptac.Hnscc() cancer_list = [hnscc] elif input_cancer_type == "lscc": lscc = cptac.Lscc() cancer_list = [lscc] # brca = cptac.Brca() # ccrcc = cptac.Ccrcc() # colon = cptac.Colon() # en = cptac.Endometrial() # gbm = cptac.Gbm() # luad = cptac.Luad() # ovarian = cptac.Ovarian() # hnscc = cptac.Hnscc() # lscc = cptac.Lscc() # type_dict = {brca:"brca",ccrcc:"ccrcc",colon:"colon",en:"endometrial",gbm:"gbm",luad:"luad",