MSformer: A Meta-Structure Based Interpretable Framework for Representation Learning of Natural Products
Analytical Chemistry · 2025
DOI: 10.1021/acs.analchem.5c03958 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytical Chemistry, 2025. Verfasst von Bingjie Zhu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmaceutical Sciences, Zhejiang University, 310058 Hangzhou, China. Hauptthemen laut MEDLINE: Biological Products, Deep Learning. Die Arbeit nennt 61 Literaturangaben. Gefördert von: Key Research and Development Program of Zhejiang Province, National Science and Technology Major Project.
Abstract (Originalsprache)
Natural products (NPs) are a treasure trove of drug discovery, yet their structural complexity and extreme data scarcity critically hinder AI-driven exploration. To address this challenge, we present MSformer, a transformer-based architecture that bridges this gap by leveraging molecule fragments to systematically encode NP chemical space. These fragments were generated by a mass spectrometry-inspired fragmentation algorithm, termed meta-structures. Unlike chemical models pretrained on comprehensive molecule databases, MSformer is totally pretrained on very limited NP data set by deconstructing 400,000 NPs into 234 million meta-structures. This design enables MSformer to capture the structural richness and drug-like relevance of NPs. Evaluated on 14 tasks across MoleculeNet and the Therapeutics Data Commons data sets, MSformer outperforms state-of-the-art models, demonstrating superior generalizability in property prediction. The abundant meta-structures enable MSformer hierarchical interpretability that reveals task-specific structural determinants and successfully deconstructing approved drugs into bioactive fragments. By integrating domain knowledge with deep learning, MSformer establishes a transformative paradigm for NP-based drug discovery, offering a scalable framework to navigate nature's underexplored chemical repertoire and accelerate the identification of bioactive candidates.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- College of Pharmaceutical Sciences, Zhejiang University, 310058 Hangzhou, China.
- State Key Laboratory of Chinese Medicine Modernization, Innovation Center of Yangtze River Delta, Zhejiang University, 314100 Jiaxing, China.
- Zhejiang Key Laboratory of Chinese Medicine Modernization, Innovation Center of Yangtze River Delta, Zhejiang University, 314100 Jiaxing, China.
- School of Pharmaceutical Sciences, Zhejiang Chinese Medical University, 310058 Hangzhou, China.
ORCID-Profile: Xiaohui Fan
Förderung
- Key Research and Development Program of Zhejiang Province
- National Science and Technology Major Project
Zitieren
APA
Zhu, B., Liao, J., Liu, H., Fan, X., & Cheng, Y. (2025). MSformer: A Meta-Structure Based Interpretable Framework for Representation Learning of Natural Products. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.5c03958
Vancouver
Zhu B, Liao J, Liu H, Fan X, Cheng Y. MSformer: A Meta-Structure Based Interpretable Framework for Representation Learning of Natural Products. Analytical Chemistry. 2025. doi:10.1021/acs.analchem.5c03958
BibTeX
@article{Zhu2025,
author = {Zhu, Bingjie and Liao, Jie and Liu, Huihui and Fan, Xiaohui and Cheng, Yiyu},
title = {MSformer: A Meta-Structure Based Interpretable Framework for Representation Learning of Natural Products},
journal = {Analytical Chemistry},
year = {2025},
doi = {10.1021/acs.analchem.5c03958}
}
EUVIMED