A physics-infused heterogeneous graph neural network has been developed to address challenges in designing complex nanomaterials with spatially varying compositions. This fully differentiable model enables the rapid optimization and discovery of photon upconverting nanoparticle heterostructures that are 6.5-fold brighter than any nanoparticle in the training set.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Chan, E. M., Levy, E. S. & Cohen, B. E. Rationally designed energy transfer in upconverting nanoparticles. Adv. Mater. 27, 5753–5761 (2015). A review article on UCNPs that highlights the use of multi-shell heterostructures for controlling energy transfer.
Panfil, Y. E., Oded, M. & Banin, U. Colloidal quantum nanostructures: emerging materials for display applications. Angew. Chem. Int. Ed. 57, 4274–4295 (2018). A review article that describes the use of heterostructures for band gap engineering of semiconductor nanocrystals for displays.
Xia, X., Sivonxay, E., Helms, B. A., Blau, S. M. & Chan, E. M. Accelerating the design of multishell upconverting nanoparticles through Bayesian optimization. Nano Lett. 23, 11129–11136 (2023). This article describes the theory and methods used to simulate energy transfer in complex UCNP heterostructures with kinetic Monte Carlo.
Sanchez-Lengeling, B. & Aspuru-Guzik, A. Inverse molecular design using machine learning: generative models for matter engineering. Science 361, 360–365 (2018). This review highlights the utility of gradients for rapid inverse design.
Zichi, L. et al. RNMC: Kinetic Monte Carlo implementations for complex reaction networks. J. Open Source Softw. 9, 7244 (2024). This article describes and links to the software developed to perform kinetic Monte Carlo simulations.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Sivonxay, E. et al. Gradient-based optimization of complex nanoparticle heterostructures enabled by deep learning on heterogeneous graphs. Nat. Comput. Sci. https://doi.org/10.1038/s43588-025-00917-3 (2025).
Rights and permissions
About this article
Cite this article
Deep learning accelerates discovery of complex nanomaterials. Nat Comput Sci 6, 19–20 (2026). https://doi.org/10.1038/s43588-025-00918-2
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s43588-025-00918-2
