The abstract is read at the publisher; the summary is JClub's.
MutexaGPT, an open-access multi-agent LLM platform, translates plain-English enzyme engineering intuition into physics-based simulations and actionable variant designs for two protein engineering tasks.
- Why it matters: A systematic way to convert qualitative, abstract intuition into quantitative, actionable enzyme design principles is still missing.
- What they did: Using a web interface, MutexaGPT elicits missing details, builds physics-based models, runs high-throughput molecular modeling workflows, and converts outputs into design proposals like smart mutation libraries.
- The result: It is demonstrated for engineering halide methyltransferase toward bulkier substrates and bidomain amylase for enhanced activity at lower temperature, supporting its use as an intuition-to-design translator.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.