AI & ML New Capability

Integrates LLM agents with the industry-standard Rosetta software to automate physics-based protein design for non-canonical amino acids.

arXiv · March 18, 2026 · 2603.15952

Jacopo Teneggi, S.M. Bargeen A. Turzo, Tanya Marwah, Alberto Bietti, P. Douglas Renfrew, Vikram Khipple Mulligan, Siavash Golkar

The Takeaway

Bridging the gap between LLMs and specialized scientific software like Rosetta allows non-experts to execute complex heteropolymer design pipelines. It matches human expert performance in areas where standard ML models for protein design currently fail.

From the abstract

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 fo