A Cloud Computing Platform for Scalable Relative and Absolute Binding Free Energy Prediction: New Opportunities and Challenges for Drug Discovery
Preprints are manuscripts made publicly available before they have been submitted for formal peer review and publication. They might contain new research findings or data. Preprints can be a draft or final version of an author's research but must not have been accepted for publication at the time of submission.
Free energy perturbation (FEP) has become widely used in drug discovery programs for binding affinity prediction between candidate compounds and their biological targets. Simultaneously limitations of FEP applications also exist, including but not limited to, the high cost, long waiting time, limited scalability and application scenarios. To overcome these problems, we have developed a scalable cloud computing platform (XFEP) for both relative and absolute free energy predictions with refined simulation protocols. XFEP enables large-scale FEP calculations in a more efficient, scalable and affordable way, e.g. the evaluation of 5,000 compounds can be performed in one week using 50-100 GPUs with a computing cost approximately corresponding to the cost for one new compound synthesis. Together with artificial intelligence (AI) techniques for goal-directed molecule generation and evaluation, new opportunities can be explored for FEP applications in the drug discovery stages of hit identification, hit-to-lead, and lead optimization with R-group substitutions, scaffold hopping, and completely different molecule evaluation. We anticipate scalable FEP applications will become widely used in more drug discovery projects to speed up the drug discovery process from hit identification to pre-clinical candidate compound nomination.