Active Learning Guided Drug Design Lead Optimization Based on Relative Binding Free Energy Modeling

In silico identification of potent protein inhibitors commonly requires prediction of a ligand binding free energy (BFE). Thermodynamics integration (TI) based on molecular dynamics (MD) simulations is a BFE calculation method capable of acquiring accurate BFE, but it is computationally expensive and time-consuming. In this work, we have developed an efficient automated workflow for identifying compounds with the lowest BFE among thousands of congeneric ligands, which requires only hundreds of TI calculations. Automated machine learning (AutoML) orchestrated by active learning (AL) in an AL-AutoML workflow allows unbiased and efficient search for a small set of best-performing molecules. We have applied this workflow to select inhibitors of the SARS-CoV-2 papain-like protease and were able to find 133 compounds with improved binding affinity, including 16 compounds with better than 100-fold binding affinity improvement. We obtained a hit rate that outperforms that expected of traditional expert medicinal chemist-guided campaigns. Thus, we demonstrate that the combination of AL and AutoML with free energy simulations provides at least 20x speedup relative to the nai''ve brute force approaches.

Automated summary

In this study, an efficient automated workflow was developed to identify compounds with the lowest binding free energy among thousands of congeneric ligands, which required only hundreds of thermodynamics integration calculations. The combination of active learning and automated machine learning allowed unbiased and efficient search for a small set of best-performing molecules. By applying this workflow to select inhibitors of the SARS-CoV-2 papain-like protease, 133 compounds with improved binding affinity, including 16 compounds with more than 100-fold improvement, were identified. The results demonstrate that the combination of active learning, automated machine learning, and free energy simulations provides a speedup of at least 20x compared to traditional expert-guided approaches.