MCPcopy Create free account
hub / github.com/Mew233/pairwise / process_dpi

Function process_dpi

pairwise/prepare_data.py:356–397  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

354
355
356 def process_dpi():
357 # load drug target dataset
358 targets = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'drug_data','all_targets.csv'))
359 enzymes = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'drug_data','all_enzyme.csv'))
360 carrier = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'drug_data','all_carrier.csv'))
361 transporter = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'drug_data','all_transporter.csv'))
362 all = pd.concat([targets,enzymes,carrier,transporter])
363 # all = targets
364 drug_targets = explode_dpi(all)
365
366 dtc = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'drug_data','dtc_db2ncbi.csv'))
367 drug_targets_L = pd.concat([drug_targets,dtc])
368 drug_targets_L = drug_targets_L.drop_duplicates(subset=['Drug IDs','NCBI_ID'])
369
370 drug_mapping = dict(zip(drug_targets_L['Drug IDs'].unique().tolist(), range(len(drug_targets_L['Drug IDs'].unique()))))
371 gene_mapping = dict(zip(drug_targets_L['NCBI_ID'].unique().tolist(), range(len(drug_targets_L['NCBI_ID'].unique()))))
372 encoding = np.zeros((len(drug_targets_L['Drug IDs'].unique()), len(drug_targets_L['NCBI_ID'].unique())))
373 for _, row in drug_targets_L.iterrows():
374 encoding[drug_mapping[row['Drug IDs']], gene_mapping[row['NCBI_ID']]] = 1
375 target_feats = dict()
376 for drug, row_id in drug_mapping.items():
377 target_feats[int(drug)] = encoding[row_id].tolist()
378
379 proessed_dpi = pd.DataFrame(target_feats)
380 proessed_dpi.index = drug_targets_L['NCBI_ID'].unique()
381 # proessed_dpi.to_csv(os.path.join(ROOT_DIR, 'results','proessed_dpi_db.csv'))
382
383 # network = nx.read_edgelist(os.path.join(ROOT_DIR, 'data','cell_line_data','PPI','string_network'), delimiter='\t', nodetype=int,
384 # data=(('weight', float),))
385
386 # data_dicts = np.load(os.path.join(ROOT_DIR, 'data', 'cell_line_data',"CCLE",'input_cellline_data.npy'),allow_pickle=True).item()
387 # ccle = data_dicts['exp']
388 # customized = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'cell_line_data',"Customized",'crc_exp.csv'), index_col=0)
389 # tcga = pd.read_csv(os.path.join(ROOT_DIR, 'data', 'cell_line_data',"Customized",'tcga_colon_exp.csv'), index_col=0)
390
391 # #column is drugbank id, row is entrez id
392 # proessed_dpi = proessed_dpi.loc[proessed_dpi.index.isin(list(network.nodes)), :]
393 # proessed_dpi = proessed_dpi.loc[proessed_dpi.index.isin(list(ccle.index)), :]
394 # proessed_dpi = proessed_dpi.loc[proessed_dpi.index.isin(list(customized.index)), :]
395 # proessed_dpi = proessed_dpi.loc[proessed_dpi.index.isin(list(tcga.index)), :]
396 # proessed_dpi.columns = proessed_dpi.columns.astype(int)
397 return proessed_dpi
398
399 ##RWR algorithm for drug-target from transynergy
400 def process_dpi_RWR():

Callers 1

load_drug_featuresFunction · 0.85

Calls 1

explode_dpiFunction · 0.85

Tested by

no test coverage detected