Topological Fusion Model for Molecular Property Prediction

The prominence of 3D molecular property prediction arises from its ability to provide insights into the drug discovery and design, material science and chemical synthesis. Transformer-based models have been widely adopted to autonomously learn long-range atom-to-atom interactions on a global scale,...

Full description

Saved in:
Bibliographic Details
Published inApplied intelligence (Dordrecht, Netherlands) Vol. 55; no. 11; p. 819
Main Authors Rong, Xia, Haotian, Xu, Junwei, Wu, Shufei, Zhang, Mingjie, Sun, Jiejie, Liu, Quan, Zhang
Format Journal Article
LanguageEnglish
Published New York Springer US 01.07.2025
Springer Nature B.V
Subjects
Aldehydes
Artificial Intelligence
Chemical bonds
Chemical synthesis
Computer Science
Covalent bonds
Data analysis
Datasets
Deep learning
Functional groups
Hydrogen bonds
Machine learning
Machines
Manufacturing
Mechanical Engineering
Molecular properties
Neural networks
Processes
Signal processing
Topology
Topological structure
Positional encoding
3D molecular
Online AccessGet full text

Cover

More Information
Summary:The prominence of 3D molecular property prediction arises from its ability to provide insights into the drug discovery and design, material science and chemical synthesis. Transformer-based models have been widely adopted to autonomously learn long-range atom-to-atom interactions on a global scale, resulting in significant success. However, these models may struggle to capture intricate substructure details ( e . g .,  covalent bond and functional group). In this work, topological simplices defined on nodes, links, triangles are extracted from the atoms’ 3D positional information to provide comprehensive representations of the local substructure information, such as atoms, covalent bonds and functional groups. We then propose a topological fusion network, which enhances each atom’s features not only through global atom-to-atom interactions but also by incorporating the fine-grained topological substructure information. In comparison to existing popular methods, our proposed method outperforms the state-of-the-art (SOTA) method by 1.2%, 3.0%, 2.4%, 2.7% on BBBP, BACE, ClinTox, MUV datasets for classification task and 0.048, 0.022, 3.8 on FreeSolv, Lipo and QM7 datasets for regression task, respectively. The code will be released soon.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-025-06721-w