Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
This addresses the need for a generalist tool in protein design, particularly for non-canonical residues where ML methods often fail, though it is incremental as it builds on existing software.
The authors tackled the problem of automating protein design with non-canonical amino acids by introducing Agent Rosetta, an LLM agent integrated with Rosetta software, achieving performance comparable to specialized models and expert baselines in both canonical and non-canonical cases.
Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong results, these are largely restricted to canonical amino acids and narrow objectives, leaving unfilled need for a generalist tool for broad design pipelines. We introduce Agent Rosetta, an LLM agent paired with a structured environment for operating Rosetta, the leading physics-based heteropolymer design software, capable of modeling non-canonical building blocks and geometries. Agent Rosetta iteratively refines designs to achieve user-defined objectives, combining LLM reasoning with Rosetta's generality. We evaluate Agent Rosetta on design with canonical amino acids, matching specialized models and expert baselines, and with non-canonical residues -- where ML approaches fail -- achieving comparable performance. Critically, prompt engineering alone often fails to generate Rosetta actions, demonstrating that environment design is essential for integrating LLM agents with specialized software. Our results show that properly designed environments enable LLM agents to make scientific software accessible while matching specialized tools and human experts.