新型蛋白质改造方法成功开发

Core Insights - The research team from the Chinese Academy of Sciences has developed a new AI-based protein modification method that utilizes existing universal protein folding AI models, allowing for efficient protein evolution simulation and functional design without the need for specialized AI training [1][2] - This new method significantly improves the efficiency and applicability of protein modification compared to traditional techniques, which are time-consuming and costly [1][2] Group 1: Methodology and Innovation - The new method, named AiCEsingle, leverages a universal protein folding AI model to predict possible amino acid sequences based on given three-dimensional structures [1] - The accuracy of the new method's predictions is reported to be 16%, with performance improvements ranging from 36% to 90% compared to other common AI models [2] Group 2: Practical Applications and Benefits - The research successfully modified eight different proteins, including key gene-editing tools like deaminases, demonstrating the method's versatility [2] - The new approach lowers the barrier for AI technology usage, enabling ordinary laboratories to benefit from intelligent predictions without the need for expensive computational resources [2]