Swiss scientists have developed a new type of artificial intelligence (AI) tool that can predict the future variants of novel coronavirus, which is expected to promote the research and development of next-generation antibody therapies and vaccines and provide important references for the formulation of public health policies. The research was published in the latest issue of cell. In order to create this new AI tool, the team of the Federal Institute of technology in Zurich produced about 1 million spike protein variants of novel coronavirus in the laboratory, which carry different mutations and combinations of mutations. Spike protein interacts with angiotensin converting enzyme 2 (ACE2) protein on human cells to infect humans. Antibodies obtained by vaccination, infection or antibody therapy play a role by blocking this mechanism. Many mutations in the mutant body of novel coronavirus occur in this region, which enables the virus to evade the immune system and continue to spread. Through high-throughput experiments and sequencing, researchers have determined how these variants interact with ACE2 protein and existing antibody therapies, revealing the extent to which a single potential variant can infect human cells and the extent to which they can evade antibodies. Subsequently, the researchers used the collected data to train machine learning models, which were able to identify complex patterns - given only the DNA sequence of a new variant, they could accurately predict whether it could bind to ACE2 to infect and evade neutralizing antibodies. The final machine learning model can be used to predict tens of billions of theoretically possible variants, including single mutations and combined mutations, far more than the million tested in the laboratory. Researchers said that the new method is helpful to develop the next generation of antibody therapy. At present, scientists have developed some antibodies. This method can determine which antibodies have the most extensive activity, and is also expected to promote the development of the next generation of COVID-19 vaccines. (Li Xinshe)