Artificial intelligence-assisted atomic precision clusters for central nerve diseases

Abstract

Owing to their nanoscale dimensions, well-defined atomic structure, and elevated specific surface area, clusters have emerged as a novel therapeutic platform for neurological disorders. However, efficiently and rationally designing functionalized clusters capable of specifically recognizing and modulating key disease targets remains a major difficulty. The rapid advancement of artificial intelligence (AI) technology offers a revolutionary solution to this bottleneck. By integrating deep learning, generative models, and multi-omics big data, AI can mine vast amounts of biomedical and chemical information with unprecedented speed and precision. It will drive transformative innovations in rational design of clusters, precise modulation of enzymatic activity, and high-throughput screening of therapeutic targets for neurological disorders.

References

[1] Zhang C, Yang X, Wan D, et al. Burden of neurological disorders in China and its provinces, 1990–2021: findings from the global burden of disease study 2021. Med. 2025; 6(8):100692. https://doi.org/10.1016/j.medj.2025.100692

[2] Xiang K, Wu H, Liu Y, et al. MOF-derived bimetallic nanozyme to catalyze ROS scavenging for protection of myocardial injury. Theranostics. 2023; 13(8): 2721-2733. https://doi.org/10.7150/thno.83543

[3] Cheng X, Xia T, Han M, et al. Mitochondria-targeting bimetallic cluster nanozymes alleviate neuropathic pain through scavenging ROS and reducing inflammation. Adv Healthcare Mater. 2025; 14(8):2401607. https://doi.org/10.1002/adhm.202401607

[4] Wang M, Tian F, Xin Q, et al. In vivo toxicology of metabolizable atomically precise Au₂₅ clusters at ultrahigh doses. Bioconjug Chem. 2024; 35(4): 540-550. https://doi.org/10.1021/acs.bioconjchem.4c00113

[5] Hao W, Liu S, Liu H, et al. In vivo neuroelectrophysiological monitoring of atomically precise Au₂₅ clusters at an ultrahigh injected dose. ACS Omega. 2020; 5(38): 24537-24545. https://doi.org/10.1021/acsomega.0c03005

[6] Liu H, Li Y, Sun S, et al. Catalytically potent and selective clusterzymes for modulation of neuroinflammation through single-atom substitutions. Nat Commun. 2021; 12(1): 114. https://doi.org/10.1038/s41467-020-20275-0

[7] Zhao R, Li L, Yan Y, et al. Single-atom modulated biocatalytic selectivity on WSe₂ clusters. ACS Appl Mater Interfaces. 2025; 17(26): 38367-38378. https://doi.org/10.1021/acsami.5c07454

[8] Zhang S, Li Y, Sun S, et al. Single-atom nanozymes catalytically surpassing naturally occurring enzymes as sustained stitching for brain trauma. Nat Commun. 2022; 13(1):4744. https://doi.org/10.1038/s41467-022-32411-z

[9] Ma H, Zhang X, Liu L, et al. Bioactive NIR-II gold clusters for three-dimensional imaging and acute inflammation inhibition. Sci Adv. 2023; 9(31):eadh7828. https://doi.org/10.1126/sciadv.adh7828

[10] Zhang W, Gao G, Ma Z, Luo Z, He M, Sun T. Au₂₃(CR)₁₄ nanocluster restores fibril Aβ’s unfolded state with abolished cytotoxicity and dissolves endogenous Aβ plaques. Natl Sci Rev. 2020; 7(4): 763-774. https://doi.org/10.1093/nsr/nwz215

[11] Fu S, Chen H, Yang W, et al. ROS-targeted depression therapy via BSA-incubated ceria nanoclusters. Nano Lett. 2022; 22(11): 4519-4527. https://doi.org/10.1021/acs.nanolett.2c01334

[12] Liu J, Wang T, Liao C, et al. Constructing electron-rich Ru clusters on non-stoichiometric copper hydroxide for superior biocatalytic ROS scavenging to treat inflammatory spinal cord injury. Adv Mater. 2024; 36(48):e2411618. https://doi.org/10.1002/adma.202411618

[13] Chen J, Xu G, Shen R, et al. Communications among neurocytes in Parkinson's disease regulated by differential metabolism and blood-brain barrier traversing of chiral gold cluster-MOF integrated nanoparticles. Adv Sci. 2025; 12(23):e2411618. https://doi.org/10.1002/advs.202500026

[14] Ma W, Cheng F, Liu Y. Deep-learning-enabled on-demand design of chiral metamaterials. ACS Nano. 2018; 12(6): 6326-6334. https://doi.org/10.1021/acsnano.8b03569

[15] Mo X, Zhang J, Li Y, Zhang XD. Advances in machine learning applications for thiolate-protected metal nanoclusters with potential metallic core exploration. J Intell Med. 2025; 2(1): 44-63. https://doi.org/10.1002/jim4.70004

[16] Muroga S, Miki Y, Hata K. A comprehensive and versatile multimodal deep-learning approach for predicting diverse properties of advanced materials. Adv Sci. 2023; 10(24):e2302508. https://doi.org/10.1002/advs.202302508

[17] Kang M, Ko E, Mersha TB. A roadmap for multi-omics data integration using deep learning. Briefings Bioinf. 2022; 23(1):bbab454. https://doi.org/10.1093/bib/bbab454

[18] Li H, Li Y, Liu Y, et al. A multistage, multitask transformer-based framework for multi-disease diagnosis and prediction using personal proteomes. medRxiv. 2025. 02.19.25322536.

[19] Wu K-M, Xu Q-H, Liu Y-Q, et al. Neuronal FAM171A2 mediates α-synuclein fibril uptake and drives Parkinson’s disease. Science. 2025; 387(6736): 892-900. https://doi.org/10.1126/science.adp3645

[20] Nativio R, Lan Y, Donahue G, et al. An integrated multi-omics approach identifies epigenetic alterations associated with Alzheimer’s disease. Nat Genet. 2020; 52(10): 1024-1035. https://doi.org/10.1038/s41588-020-0696-0

RIGHTS & PERMISSIONS

2025 The Author(s). Journal of Intelligent Medicine published by John Wiley & Sons Australia, Ltd on behalf of Tianjin University.