Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
This work addresses the challenge of slow hypothesis generation in protein design for researchers, though it is incremental as it builds on existing LLM and tool-augmented methods.
The authors tackled the problem of accelerating scientific hypothesis generation in protein design by developing Genie-CAT, an agentic LLM framework that integrates multiple tools for mechanistic enzyme design, resulting in autonomous identification of residue-level modifications that reproduce expert-derived hypotheses in a fraction of the time.
We present Genie-CAT, a tool-augmented large-language-model (LLM) system designed to accelerate scientific hypothesis generation in protein design. Using metalloproteins (e.g., ferredoxins) as a case study, Genie-CAT integrates four capabilities -- literature-grounded reasoning through retrieval-augmented generation (RAG), structural parsing of Protein Data Bank files, electrostatic potential calculations, and machine-learning prediction of redox properties -- into a unified agentic workflow. By coupling natural-language reasoning with data-driven and physics-based computation, the system generates mechanistically interpretable, testable hypotheses linking sequence, structure, and function. In proof-of-concept demonstrations, Genie-CAT autonomously identifies residue-level modifications near [Fe--S] clusters that affect redox tuning, reproducing expert-derived hypotheses in a fraction of the time. The framework highlights how AI agents combining language models with domain-specific tools can bridge symbolic reasoning and numerical simulation, transforming LLMs from conversational assistants into partners for computational discovery.