Machine Learning Guided Design of High-Affinity ACE2 Decoys for SARS-CoV‑2 Neutralization

• Published in: The journal of physical chemistry. B Vol. 127; no. 9; pp. 1995 - 2001
• Main Authors: Chan, Matthew C., Chan, Kui. K., Procko, Erik, Shukla, Diwakar
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 09.03.2023
• Subjects: Algorithms; Angiotensin-Converting Enzyme 2; B: Biophysical and Biochemical Systems and Processes; COVID-19; Humans; Machine Learning; Mutation; Protein Binding; SARS-CoV-2 - genetics
• ISSN: 1520-6106; 1520-5207
• DOI: 10.1021/acs.jpcb.3c00469

A potential therapeutic strategy for neutralizing SARS-CoV-2 infection is engineering high-affinity soluble ACE2 decoy proteins to compete for binding to the viral spike (S) protein. Previously, a deep mutational scan of ACE2 was performed and has led to the identification of a triple mutant variant, named sACE22.v.2.4, that exhibits subnanomolar affinity to the receptor-binding domain (RBD) of S. Using a recently developed transfer learning algorithm, TLmutation, we sought to identify other ACE2 variants that may exhibit similar binding affinity with decreased mutational load. Upon training a TLmutation model on the effects of single mutations, we identified multiple ACE2 double mutants that bind SARS-CoV-2 S with tighter affinity as compared to the wild type, most notably L79V;N90D that binds RBD similarly to ACE22.v.2.4. The experimental validation of the double mutants successfully demonstrates the use of machine learning approaches for engineering protein–protein interactions and identifying high-affinity ACE2 peptides for targeting SARS-CoV-2.