AI‐Driven Acceleration of Fluorescence Probe Discovery
Advanced Science · 2026-02 · 13 (10)
DOI: 10.1002/advs.202515604 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 24.12.2025. Verfasst von Xuefeng Jiang und 18 weiteren Autor:innen. Beteiligte Einrichtung: National Clinical Research Center for Children and Adolescents' Health and Diseases, Children's Hospital of Chongqing Medical University, Chongqing, …. Hauptthemen laut MEDLINE: Fluorescent Dyes, Optical Imaging, Drug Discovery. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chongqing Science and Health Joint Medical Research Project, Natural Science Foundation of Chongqing Municipality.
Abstract (Originalsprache)
Fluorescence imaging probes are indispensable tools for clinical navigation and preclinical research. However, the discovery of target‐specific probes is hampered by the scarcity of targetable fluorophore scaffolds, making the development process slow, costly, and heavily reliant on trial‐and‐error design. Here, we present a hybrid strategy that integrates AI with bioassays to accelerate the development of target‐specific fluorescent probes. We developed an AI model (PROBY) based on over one million molecule entries from nine datasets, capable of identifying fluorescent molecules and predicting seven key photophysical properties. Applying PROBY to a library of 26,416 target‐validated molecules, we identified thousands of candidates with both target affinity and favorable optical characteristics. Focusing on three clinically relevant targets (tau, BCL‐2, and TDP‐43), we validated AI‐identified candidates and discovered PE859, obatoclax, and B3, which supported applications in spectral analysis, drug screening, pathological labeling, cell imaging, and ex vivo tumor imaging. Guided by PROBY, we chemically modify PE859, yielding two optimized derivatives (859‐1 and 859‐2). With improved photophysical properties, 859‐2 enabled in vivo two‐photon imaging of tau pathology in transgenic mice. This hybrid AI‐bioassay strategy substantially broadens the accessible scaffold landscape for designing target‐specific fluorescence probes and provides a scalable, efficient, and cost‐effective framework for next‐generation probe discovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- National Clinical Research Center for Children and Adolescents' Health and Diseases, Children's Hospital of Chongqing Medical University, Chongqing, China.
- Department of Radiation Oncology, Stanford University School of Medicine, Stanford, California, USA.
- Athinoula A. Martinos Center For Biomedical Imaging, Department of Radiology, Harvard Medical School, Massachusetts General Hospital, Boston, Massachusetts, USA.
- Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, USA.
- Harvard Data Science Initiative, Harvard University, Cambridge, Massachusetts, USA.
- College of Biomedical Engineering, Sichuan University, Chengdu, Sichuan, China.
ORCID-Profile: Xiyue Wang, Biyue Zhu
Förderung
- National Natural Science Foundation of China
- Chongqing Science and Health Joint Medical Research Project
- Natural Science Foundation of Chongqing Municipality
- NHLBI NIH HHS
- NIGMS NIH HHS
Zitieren
APA
Jiang, X., Li, Y., Tian, X., Yang, S., Luo, R., Zhou, C., Liu, Y., Hu, J., Feng, S., Gan, L., Ran, C., Yu, K. H., Zhao, J., Han, X., Zhai, X., Jia, Y., Dai, J., Wang, X., & Zhu, B. (2026). AI‐Driven Acceleration of Fluorescence Probe Discovery. Advanced Science, 13(10). https://doi.org/10.1002/advs.202515604
Vancouver
Jiang X, Li Y, Tian X, Yang S, Luo R, Zhou C, et al. AI‐Driven Acceleration of Fluorescence Probe Discovery. Advanced Science. 2026;13(10). doi:10.1002/advs.202515604
BibTeX
@article{Jiang2026,
author = {Jiang, Xuefeng and Li, Yanbo and Tian, Xue and Yang, Sen and Luo, Ruina and Zhou, Cenxing and Liu, Yuxuan and Hu, Jingying and Feng, Sen and Gan, Lu and Ran, Chongzhao and Yu, Kun-Hsing and Zhao, Junhan and Han, Xiao and Zhai, Xuan and Jia, Yuntao and Dai, Jiapei and Wang, Xiyue and Zhu, Biyue},
title = {AI‐Driven Acceleration of Fluorescence Probe Discovery},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {10},
doi = {10.1002/advs.202515604}
}
EUVIMED