Multimodal pre-training models of molecular representation for drug discovery
National Science Review · 10.01.2026 · 13 (1)
DOI: 10.1093/nsr/nwaf495 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift National Science Review, online erschienen am 11.11.2025. Verfasst von Xiaoqi Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Northwestern Polytechnical University, Xi'an, 710129, China. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 122 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, FDCT, National Key Research and Development Program of China.
Abstract (Originalsprache)
With the great success of large language models in natural language processing, self-supervised pre-training models have emerged as an important technique in drug discovery. In particular, multimodal pre-training models have opened a new avenue for drug discovery. The experience and ideas from previous works can provide important reference points for further research in drug discovery. Therefore, this review summarizes the foundation of multimodal pre-training models and their progress in the field of drug discovery. We emphasize the adaptability between various modalities and network frameworks or pre-training tasks. At the same time, we summarize the difference and relevance between various modalities or pre-training models. Importantly, we identify two increasing trends that may serve as reference points for future research. Specifically, Transformers and graph neural networks are often integrated as encoders and then combined with multiple pre-training tasks to learn cross-scale molecular representation, thereby promoting the accuracy of drug discovery. In addition, molecular captions as brief biomedical text provide a bridge for collaboration between drug discovery and large language models. Finally, we discuss the challenges of multimodal pre-training models in drug discovery, and explore future opportunities.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710129, China.
- Key Laboratory of Big Data Storage and Management, Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi'an, 710129, China.
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China.
- Division of Applied Oral Sciences & Community Dental Care, Faculty of Dentistry, the University of Hong Kong, Hong Kong 999077, China.
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai 201203, China.
ORCID-Profile: Boya Ji, Junwen Wang, Mingyue Zheng
Förderung
- National Natural Science Foundation of China
- FDCT
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
- Innovative Research Group Project
- Hunan Science and Technology Innovation Plan
- Key Research and Development Program of Hunan Province of China
- Key Technologies Research and Development Program
Zitieren
APA
Wang, X., Wang, C., Ji, B., Wang, J., Zheng, M., Song, L., Peng, S., & Shang, X. (2026). Multimodal pre-training models of molecular representation for drug discovery. National Science Review, 13(1). https://doi.org/10.1093/nsr/nwaf495
Vancouver
Wang X, Wang C, Ji B, Wang J, Zheng M, Song L, et al. Multimodal pre-training models of molecular representation for drug discovery. National Science Review. 2026;13(1). doi:10.1093/nsr/nwaf495
BibTeX
@article{Wang2026,
author = {Wang, Xiaoqi and Wang, Chuanshi and Ji, Boya and Wang, Junwen and Zheng, Mingyue and Song, Lingyun and Peng, Shaoliang and Shang, Xuequn},
title = {Multimodal pre-training models of molecular representation for drug discovery},
journal = {National Science Review},
year = {2026},
volume = {13},
number = {1},
doi = {10.1093/nsr/nwaf495}
}
EUVIMED