MutexaGPT: an intuition-to-design translator for physics-based enzyme engineering.

MutexaGPT enables physics-based enzyme design from plain-English intuition, generating actionable mutation proposals with high-throughput molecular modeling in diverse engineering tasks.

• Why it matters: Understanding how enzyme structure and dynamics influence function is crucial for effective engineering, but translating intuitive ideas into quantitative models remains a challenge, limiting innovation.
• What they did: The platform uses large language model agents to interpret intuition-driven requests, build physics-based models, run molecular simulations, and produce design proposals, demonstrated in two enzyme engineering cases.
• The result: MutexaGPT successfully bridges human creativity and computational modeling, facilitating accessible, physics-guided enzyme engineering and expanding possibilities for designing enzymes with desired traits.