diff --git a/README.md b/README.md index 804fa08..ec52faf 100644 --- a/README.md +++ b/README.md @@ -10,10 +10,10 @@ This repo contains the code and datasets for the publication # Data and results ## Directories: -- datasets: contains the assay datasets exported from ChEMBL30 as well as the results of running SIMPD on the assay datasets. There's also a data catalog description for the intake package in here +- datasets: contains the Ki datasets exported from ChEMBL32 as well as the results of running SIMPD on the assay datasets. There's also a data catalog description for the intake package in here # Jupyter Notebooks -- 01_Get_ChEMBL30_Bioactivity_Data_assays.ipynb : export the raw ChEMBL assay datasets from ChEMBL +- 01_Get_ChEMBL32_Bioactivity_Data_assays.ipynb : export the raw ChEMBL Ki datasets from ChEMBL - 02_ChEMBL_ML_experiments.ipynb : analysis of the results of the ML experiments on the ChEMBL Datasets # Python files @@ -24,7 +24,7 @@ This repo contains the code and datasets for the publication - run_chemblassay_ml_nogap.py : script to run the ML experiments on the base assay data - run_chemblassay_ga_nogap.py : script to run SIMPD on the base assay data - run_chemblassay_ml_moo_nogap.py : script to run the ML experiments on the SIMPD results -- create_simpd_output_chemblassay.py : script to create CSV files with the final SIMPD datasets. This is what ends up in the datasets/chembl_SIMPD directory +- create_simpd_output_chemblKi.py : script to create CSV files with the final SIMPD datasets. This is what ends up in the datasets/chembl_SIMPD directory