Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining
Briefings in Bioinformatics · 2024
DOI: 10.1093/bib/bbae340 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Wenkai Xiang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Lingang Laboratory, Shanghai 200031, China. Hauptthemen laut MEDLINE: Molecular Conformation. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Rising-Star Program, Shanghai Sailing Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate prediction of molecular properties is fundamental in drug discovery and development, providing crucial guidance for effective drug design. A critical factor in achieving accurate molecular property prediction lies in the appropriate representation of molecular structures. Presently, prevalent deep learning–based molecular representations rely on 2D structure information as the primary molecular representation, often overlooking essential three-dimensional (3D) conformational information due to the inherent limitations of 2D structures in conveying atomic spatial relationships. In this study, we propose employing the Gram matrix as a condensed representation of 3D molecular structures and for efficient pretraining objectives. Subsequently, we leverage this matrix to construct a novel molecular representation model, Pre-GTM, which inherently encapsulates 3D information. The model accurately predicts the 3D structure of a molecule by estimating the Gram matrix. Our findings demonstrate that Pre-GTM model outperforms the baseline Graphormer model and other pretrained models in the QM9 and MoleculeNet quantitative property prediction task. The integration of the Gram matrix as a condensed representation of 3D molecular structure, incorporated into the Pre-GTM model, opens up promising avenues for its potential application across various domains of molecular research, including drug design, materials science, and chemical engineering.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Lingang Laboratory, Shanghai 200031, China.
- Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, Shanghai 201203, China.
- University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China.
- Fujian Key Laboratory of Drug Target Discovery and Structural and Functional Research, School of Pharmacy, Fujian Medical University, Fuzhou 350122, China.
- Nanjing University of Chinese Medicine, 138 Xianlin Road, Nanjing 210023, China.
ORCID-Profile: Mingyue Zheng, Xutong Li, Dingyan Wang
Förderung
- Shanghai Rising-Star Program
- Shanghai Sailing Program
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Xiang, W., Zhong, F., Ni, L., Zheng, M., Li, X., Shi, Q., & Wang, D. (2024). Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae340
Vancouver
Xiang W, Zhong F, Ni L, Zheng M, Li X, Shi Q, et al. Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae340
BibTeX
@article{Xiang2024,
author = {Xiang, Wenkai and Zhong, Feisheng and Ni, Lin and Zheng, Mingyue and Li, Xutong and Shi, Qian and Wang, Dingyan},
title = {Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining},
journal = {Briefings in Bioinformatics},
year = {2024},
doi = {10.1093/bib/bbae340}
}
EUVIMED