M 3 -20M: A large-scale multi-modal molecule dataset for AI-driven drug design and discovery
Journal of Bioinformatics and Computational Biology · 2025-04 · 23 (02)
DOI: 10.1142/s0219720025500064 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Bioinformatics and Computational Biology, online erschienen am 09.06.2025. Verfasst von Siyuan Guo und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Technology, Tongji University, No. 4800 Cao'an Road, Shanghai 201804, China. Hauptthemen laut MEDLINE: Drug Discovery, Drug Design, Artificial Intelligence. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Innovative Research Group Project of the National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper introduces M 3 -20M, a large-scale Multi-Modal Molecule dataset that contains over 20 million molecules, with the data mainly being integrated from existing databases and partially generated by large language models. Designed to support AI-driven drug design and discovery, M 3 -20M is 71 times more in the number of molecules than the largest existing dataset, providing an unprecedented scale that can highly benefit the training or fine-tuning of models, including large language models for drug design and discovery tasks. This dataset integrates one-dimensional SMILES, two-dimensional molecular graphs, three-dimensional molecular structures, physicochemical properties, and textual descriptions collected through web crawling and generated using GPT-3.5, offering a comprehensive view of each molecule. To demonstrate the power of M 3 -20M in drug design and discovery, we conduct extensive experiments on two key tasks: molecule generation and molecular property prediction, using large language models including GLM4, GPT-3.5, GPT-4, and Llama3-8b. Our experimental results show that M 3 -20M can significantly boost model performance in both tasks. Specifically, it enables the models to generate more diverse and valid molecular structures and achieve higher property prediction accuracy than existing single-modal datasets, which validates the value and potential of M 3 -20M in supporting AI-driven drug design and discovery. The dataset is available at https://github.com/bz99bz/M-3.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science and Technology, Tongji University, No. 4800 Cao'an Road, Shanghai 201804, China.
- Shanghai Key Lab of Intelligent Information Processing and School of Computer Science, Fudan University, 2005 Songhu Road, Shanghai 200438, China.
ORCID-Profile: Siyuan Guo, Lexuan Wang, Jinxian Wang, Han Peng, Huayang Shi, Wengen Li, Jihong Guan, Shuigeng Zhou
Förderung
- Innovative Research Group Project of the National Natural Science Foundation of China
Zitieren
APA
Guo, S., Wang, L., Jin, C., Wang, J., Peng, H., Shi, H., Li, W., Guan, J., & Zhou, S. (2025). M 3 -20M: A large-scale multi-modal molecule dataset for AI-driven drug design and discovery. Journal of Bioinformatics and Computational Biology, 23(02). https://doi.org/10.1142/s0219720025500064
Vancouver
Guo S, Wang L, Jin C, Wang J, Peng H, Shi H, et al. M 3 -20M: A large-scale multi-modal molecule dataset for AI-driven drug design and discovery. Journal of Bioinformatics and Computational Biology. 2025;23(02). doi:10.1142/s0219720025500064
BibTeX
@article{Guo2025,
author = {Guo, Siyuan and Wang, Lexuan and Jin, Chang and Wang, Jinxian and Peng, Han and Shi, Huayang and Li, Wengen and Guan, Jihong and Zhou, Shuigeng},
title = {M 3 -20M: A large-scale multi-modal molecule dataset for AI-driven drug design and discovery},
journal = {Journal of Bioinformatics and Computational Biology},
year = {2025},
volume = {23},
number = {02},
doi = {10.1142/s0219720025500064}
}
EUVIMED