Mitigating activity cliff-induced discrepancies by structure-free compound-protein interaction and integrated bioactivity learning

CPI2M data for "Complex structure-free compound-protein interaction prediction for mitigating activity cliff-induced discrepancies and integrated bioactivity learning". ki.csv: Bioactivity data with pKi activity type. kd.csv: Bioactivity data with pKd activity type. ec50.csv: Bioactivity data with pEC50 activity type. ic50.csv: Bioactivity data with pIC50 activity type. Protein_pretrained_feat.zip: pre-calculated protein feature files with UniProt ID naming. Should be unzipped before start model training with CPI2M data. For each .csv data, columns include "smiles" (ligand SMILES), "exp_mean" (nM bioactivity), "y" (neg.log nM, final label), "cliff_mol" (whether activity cliff or not), "split" (splitting label by activity cliff), "Uniprot_id" (UniProt ID for protein), "Sequence" (wildtype sequence for protein). Please find the project code at https://github.com/gu-yaowen/GGAP-CPI