Physical/Analytical Seminar
"Physics-guided Protein Engineering: Platform and Applications"
Abstract: My group seeks to redefine protein engineering by anchoring it in molecular-level physical principles. We are developing Mutexa, a physics-informed artificial intelligence (AI) platform for “intelligent” protein engineering, enabling researchers to identify super-mutants with non-native functional performance while uncovering the molecular insights behind unpredictable experimental outcomes [1]. Protein engineering, despite over decades of progress, remains reliant on labor- and resource-intensive experimental screening, which delivers only “what you screen for” and offers little insight into the structure-function relationships underlying mutation effects. While AI is widely recognized for its potential to accelerate protein engineering, I question the feasibility of achieving generalizable predictive models through AI alone [2]. In this talk, I will present the technical foundations of Mutexa and its application in the protein engineering challenge for designing industrial bidomain enzymes that maintain high activity at lower temperatures (known as cold-adapted enzymes). I will also discuss about the structural prediction challenge for multidomain enzymes, and how physics-based approaches can potentially mitigate the problem. The example showcases Mutexa’s unique ability to drive the discovery of functional proteins beyond traditional screening-based approaches, offering solutions for sustainable biomanufacturing and antimicrobial development.