Reliable and Efficient Agentic Protein Design with Toolset Harnessing
- 1Institute for Protein Design, University of Washington, Seattle, WA, USA; Howard Hughes Medical Institute, University of Washington, Seattle, WA, USA; Departmen
Abstract
Computational protein design workflows require the orchestration of multiple tools, data formats, and analysis steps that are often fragmented. Here, we introduce Chaperone, a lightweight and customizable framework that enables seamless integration of RFdiffusion3 (RFD3) with downstream sequence design, structure prediction, and evaluation tools, including ProteinMPNN, AlphaFold3 (AF3), and more than 50 other protein design tools. By combining a programmable agent-friendly interface with parallelized execution on high-performance computing systems, Chaperone as a harness enables rapid iteration and scalable exploration of complex protein design workflows. Across an evaluation of nine biomolecular design tasks, we find using Chaperone reduces total token usage relative to baseline agents by 86% and GPU costs by 64%, while increasing the overall computational design pass rate. We demonstrate Chaperones utility for large-scale design-space exploration through a two-week end-to-end small-molecule binder design campaign, yielding low nanomolar binders to cortisol zero shot. We further demonstrate its versatility across distinct design challenges, including the design of a symmetric 12-subunit self-assembly nanoparticle and a linker that mediates interactions between C2- and D3-symmetric protein complexes to form crystalline assemblies. Together, these results demonstrate how agent harnesses built around standardized tool interfaces can substantially improve the efficiency and success of complex, long-horizon agentic design workflows in biology. We make Chaperone freely available to the community on GitHub: https://github.com/RosettaCommons/chaperone.
Related
- What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
- An evolutionary strategy for highly efficient secretion of multidomain Staphylococcal protein A: N- to C-terminal stability gradient
- Efficient structural information integration into protein language models with implicit mixture-of-experts ProBEiT
- Yeast knockout library allows for efficient testing of genomic mutations for cell-free protein synthesis
- Sequential Design of Experiments enables accessible and efficient multidimensional mapping of single- and multi-protein condensates
BibTeX
@misc{butcher2026reliable,
title = {{Reliable and Efficient Agentic Protein Design with Toolset Harnessing}},
author = {J. Butcher and J. Chen and A. Hunt and C. M. Haas and W. Dai and S. Sharma and R. Mitra and S. Salike and J. Koob and A. Muraishi and Z. Li and H. Pyles and M. D. Tyka and M. S. Bauer and R. I. Brent and A. Mittal and N. P. King and D. Baker},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.19.759896},
url = {https://www.biorxiv.org/content/10.64898/2026.10.19.759896v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Reliable and Efficient Agentic Protein Design with Toolset Harnessing
AU - J. Butcher
AU - J. Chen
AU - A. Hunt
AU - C. M. Haas
AU - W. Dai
AU - S. Sharma
AU - R. Mitra
AU - S. Salike
AU - J. Koob
AU - A. Muraishi
AU - Z. Li
AU - H. Pyles
AU - M. D. Tyka
AU - M. S. Bauer
AU - R. I. Brent
AU - A. Mittal
AU - N. P. King
AU - D. Baker
PY - 2026
DA - 2026/10/19
PB - bioRxiv
DO - 10.64898/2026.10.19.759896
UR - https://www.biorxiv.org/content/10.64898/2026.10.19.759896v1
AB - Computational protein design workflows require the orchestration of multiple tools, data formats, and analysis steps that are often fragmented. Here, we introduce Chaperone, a lightweight and customizable framework that enables seamless integration of RFdiffusion3 (RFD3) with downstream sequence design, structure prediction, and evaluation tools, including ProteinMPNN, AlphaFold3 (AF3), and more than 50 other protein design tools. By combining a programmable agent-friendly interface with parallelized execution on high-performance computing systems, Chaperone as a harness enables rapid iteration and scalable exploration of complex protein design workflows. Across an evaluation of nine biomolecular design tasks, we find using Chaperone reduces total token usage relative to baseline agents by 86% and GPU costs by 64%, while increasing the overall computational design pass rate. We demonstrate Chaperones utility for large-scale design-space exploration through a two-week end-to-end small-molecule binder design campaign, yielding low nanomolar binders to cortisol zero shot. We further demonstrate its versatility across distinct design challenges, including the design of a symmetric 12-subunit self-assembly nanoparticle and a linker that mediates interactions between C2- and D3-symmetric protein complexes to form crystalline assemblies. Together, these results demonstrate how agent harnesses built around standardized tool interfaces can substantially improve the efficiency and success of complex, long-horizon agentic design workflows in biology. We make Chaperone freely available to the community on GitHub: https://github.com/RosettaCommons/chaperone.
ER -