Jameel Clinic research develops 'FrameDiff', a computational tool that uses generative AI to craft new protein structures

The search to identify proteins that can strongly bind to targets or speed up chemical reactions is vital for drug development, diagnostics and numerous industrial applications, but it is often a protracted and costly process. Research supported by the Jameel Clinic at the Massachusetts Institute of Technology (MIT) and conducted by researchers within the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), came up with 'FrameDiff', a computational tool for creating new protein structures beyond what nature has already produced. The approach generates 'frames' that align with the inherent properties of protein structures, enabling it to construct new proteins independently of preexisting designs. This means proteins can attach to other molecules more efficiently and selectively, which can have implications for targeted drug delivery and biotechnology, where it could result in the development of better biosensors. MIT CSAIL student Jason Yim wrote a paper about the work, on which he was advised by MIT Jameel Clinic AI faculty lead Regina Barzilay and principal investigator (2022) Tommi Jaakkola.