You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

utils.py 1.7KB

12345678910111213141516171819202122232425262728293031323334
  1. import os
  2. DATA_FOLDER = 'data'
  3. TEST_TCGA_DATA_FOLDER = os.path.join(DATA_FOLDER, 'TCGA_test_data')
  4. RAW_BOTH_DATA_FOLDER = os.path.join(DATA_FOLDER, 'CTRP_GDSC_data')
  5. DRUG_DATA_FOLDER = os.path.join(DATA_FOLDER, 'drug_data')
  6. GDSC_RAW_DATA_FOLDER = os.path.join(DATA_FOLDER, 'GDSC_data')
  7. CCLE_RAW_DATA_FOLDER = os.path.join(DATA_FOLDER, 'CCLE_data')
  8. GDSC_SCREENING_DATA_FOLDER = os.path.join(GDSC_RAW_DATA_FOLDER, 'drug_screening_matrix_GDSC.tsv')
  9. CCLE_SCREENING_DATA_FOLDER = os.path.join(CCLE_RAW_DATA_FOLDER, 'drug_screening_matrix_ccle.tsv')
  10. BOTH_SCREENING_DATA_FOLDER = os.path.join(RAW_BOTH_DATA_FOLDER, 'drug_screening_matrix_gdsc_ctrp.tsv')
  11. CTRP_FOLDER = os.path.join(DATA_FOLDER, 'CTRP')
  12. GDSC_FOLDER = os.path.join(DATA_FOLDER, 'GDSC')
  13. CCLE_FOLDER = os.path.join(DATA_FOLDER, 'CCLE')
  14. MODEL_FOLDER = os.path.join(DATA_FOLDER, 'model')
  15. TCGA_DATA_FOLDER = os.path.join(DATA_FOLDER, 'TCGA_data')
  16. TCGA_SCREENING_DATA = os.path.join(TCGA_DATA_FOLDER, 'TCGA_screening_matrix.tsv')
  17. BUILD_SIM_MATRICES = True # Make this variable True to build similarity matrices from raw data
  18. SIM_KERNEL = {'cell_CN': ('euclidean', 0.001), 'cell_exp': ('euclidean', 0.01), 'cell_methy': ('euclidean', 0.1),
  19. 'cell_mut': ('jaccard', 1), 'drug_DT': ('jaccard', 1), 'drug_comp': ('euclidean', 0.001),
  20. 'drug_desc': ('euclidean', 0.001), 'drug_finger': ('euclidean', 0.001)}
  21. SAVE_MODEL = False # Change it to True to save the trained model
  22. VARIATIONAL_AUTOENCODERS = False
  23. # DATA_MODALITIES=['cell_CN','cell_exp','cell_methy','cell_mut','drug_comp','drug_DT'] # Change this list to only consider specific data modalities
  24. DATA_MODALITIES = ['cell_mut', 'drug_desc', 'drug_finger']
  25. RANDOM_SEED = 42 # Must be used wherever can be used