AI agent supervision of structural model building and refinement
- 1Academia Sinica
Abstract
Structural model building and refinement need many decisions between different programs. These decisions often depend on an experienced researcher who knows how the programs work together and how to read experimental data. We used Claude Code with Claude Opus 5.5 to supervise this work for 24 cryo-EM and X-ray cases. The work finished in about 36 hours on one workstation. The agent prepared the inputs, ran established programs, read the validation results, compared candidate models and chose the next step. For 15 deposited cryo-EM models with weak starting geometry, the median MolProbity score improved from 2.62 to 1.76. For three crystal structures, the agent models came close to the published Rfree values. Chemical information such as ligands, ions and modifications must be provided by the researcher, in the same way as the sequence. With this information, the agent can place and check these components. These results show that agent supervision is acceptable when every decision can be inspected. The researcher makes the final scientific judgment. We suggest practical requirements for this kind of use. Future AI agents may help researchers obtain high quality and reliable structures of biological macromolecules.
Related
- PULSES: multi-agent AI for autonomous excited-state model building and dynamics
- Transforming biomass to graphitic carbon: Catalytic mechanisms, structural refinement, and emerging applications
- Poly(lactic acid) - PLA as sustainable building block to enhance structural stability and performance of PEO-based electrolytes
- From Molecular Building Blocks to Corrugated Graphitic Carbon Nitride: Chemical Origins of Structural Preference and Electronic Diversity
- Bridging the Training–Application Gap in Kohn–Sham Hamiltonian Learning through Dual-Space Supervision
BibTeX
@misc{wu2026agent,
title = {{AI agent supervision of structural model building and refinement}},
author = {K.-P. Wu and C.-K. Chueh},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.756902},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.756902v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - AI agent supervision of structural model building and refinement
AU - K.-P. Wu
AU - C.-K. Chueh
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.756902
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.756902v1
AB - Structural model building and refinement need many decisions between different programs. These decisions often depend on an experienced researcher who knows how the programs work together and how to read experimental data. We used Claude Code with Claude Opus 5.5 to supervise this work for 24 cryo-EM and X-ray cases. The work finished in about 36 hours on one workstation. The agent prepared the inputs, ran established programs, read the validation results, compared candidate models and chose the next step. For 15 deposited cryo-EM models with weak starting geometry, the median MolProbity score improved from 2.62 to 1.76. For three crystal structures, the agent models came close to the published Rfree values. Chemical information such as ligands, ions and modifications must be provided by the researcher, in the same way as the sequence. With this information, the agent can place and check these components. These results show that agent supervision is acceptable when every decision can be inspected. The researcher makes the final scientific judgment. We suggest practical requirements for this kind of use. Future AI agents may help researchers obtain high quality and reliable structures of biological macromolecules.
ER -