Rice University Develops New AI Method to Enhance Protein Engineering
Researchers at Rice University, in collaboration with Johns Hopkins University and Microsoft, have developed a new method to enhance protein engineering using artificial intelligence. The method, known as Sequence Display, allows for the generation of over 10 million data points in a single experiment. These data points are crucial for training AI models to predict optimal protein modifications. The research, published in Nature Biotechnology, addresses a significant bottleneck in AI-driven protein engineering: the lack of sufficient experimental data to train machine learning models. By generating comprehensive datasets, the team was able to create accurate models in just three days, significantly improving the activity of proteins such as CRISPR-Cas9. This approach combines experimental data with AI to predict beneficial mutations in proteins, offering a practical framework for integrating AI with protein engineering. 
