AI Summary
The text describes a method using an AI system to identify critical amino acid regions for the development of peptide-based inhibitors against SARS-CoV-2. This approach can help accelerate the optimization step in drug development for emerging viruses.
The rapid development of drugs against emerging and re-emerging viruses is required to prevent future pandemics. However, inhibitors usually take a long time to optimize. Here, to improve the optimization step, we used two heptad repeats (HR) in the spike protein (S protein) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) as a model and established a screening system for peptide-based inhibitors containing an alpha-helix region (SPICA). SPICA can be used to identify critical amino acid regions and evaluate the inhibitory effects of peptides as decoys. We further employed an artificial intelligence structure-prediction system (AlphaFold2) for the rapid analysis of structure–activity relationships. Here, we identified that critical amino acid regions, DVDLGD (amino acids 1163–1168 in the S protein), IQKEIDRLNE (1179–1188), and NLNESLIDL (1192–1200), played a pivotal role in SARS-CoV-2 fusion. Peptides containing these critical amino acid regions efficiently blocked viral replication. We also demonstrated that AlphaFold2 could successfully predict structures similar to the reported crystal and cryo-electron microscopy structures of the post-fusion form of the SARS-CoV-2 S protein. Notably, the predicted structures of the HR1 region and the peptide-based fusion inhibitors corresponded well with the antiviral effects of each fusion inhibitor. Thus, the combination of SPICA and AlphaFold2 is a powerful tool to design viral fusion inhibitors using only the amino-acid sequence of the fusion protein.
This article is Open Access
Please wait while we load your content… Something went wrong. Try again?