Explainable Artificial Intelligence (XAI) and Molecular Modeling Techniques to Discover Putative HER2 Inhibitors

Breast cancer is one of the prominent reasons of death in women. HER2 is a promising target to counter breast cancer. In the current research, a structure-based pharmacophore model was generated to map and screen CMNPD, a comprehensive database of marine natural products. The two compounds (CMNPD30448 (hit1) and CMNPD7060 (hit2)) displayed better LibDock scores than the reference co-crystallized ligand. These compounds demonstrated stable molecular dynamics results conducted for 500 ns with stable root mean square deviation (RMSD) at 0.3 nm, stable radius of gyration (Rg) and root mean square fluctuation (RMSF). On ChEMBL compounds, different PaDEL descriptors and various machine learning (ML) and dense neural network (DNN) methods were used. The results showed that PubChem fingerprints with random forest classification model displayed an accuracy of 0.91 and a receiver operating characteristic area under the curve (ROC-AUC) of 0.96. This model further predicted the retrieved compounds as ‘active’. The explainable random forest with LIME showed that PubChem fingerprint440 [C(-C)(-O)(=O)], PubChem fingerprint452 [C(-O)(=O)], PubChem fingerprint380 [C(~O)(~O)], PubChem fingerprint566 [O-C-C-N] and PubChem fingerprint712 [C-C(C)-C(C)-C] for hit1 and PubChem fingerprint700 [O-C-C-C-C-C-O-C], PubChem fingerprint380 [C(~O)(~O)], and PubChem fingerprint712 [C-C(C)-C(C)-C] for hit2 have contributed towards plausible inhibitory potential. These findings suggest the two compounds CMNPD30448 and CMNPD7060 might serve as HER2 inhibitors. Further in vitro and in vivo analysis are required before using them.