Algebraic graph-assisted bidirectional transformers for molecular property prediction

• Published in: Nature communications Vol. 12; no. 1; pp. 3521 - 9
• Main Authors: Chen, Dong, Gao, Kaifu, Nguyen, Duc Duy, Chen, Xin, Jiang, Yi, Wei, Guo-Wei, Pan, Feng
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 10.06.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/92/606; 631/92/96; Algebra; Algorithms; Artificial neural networks; Blood-Brain Barrier - drug effects; Coders; Computer Simulation; Databases, Chemical; Datasets; Decision trees; Drug Discovery - methods; Drug-Related Side Effects and Adverse Reactions; Environmental protection; Graphical representations; Humanities and Social Sciences; Hydrophobic and Hydrophilic Interactions; Learning algorithms; Machine Learning; Molecular Conformation; Molecular properties; multidisciplinary; Neural networks; Neural Networks, Computer; Pharmaceutical Preparations - chemistry; Physical chemistry; Predictions; Science; Science (multidisciplinary); Toxicity; Transformers
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-021-23720-w

The ability of molecular property prediction is of great significance to drug discovery, human health, and environmental protection. Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Although some machine learning models, such as bidirectional encoder from transformer, can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy, it neglects three-dimensional (3D) stereochemical information. Algebraic graph, specifically, element-specific multiscale weighted colored algebraic graph, embeds complementary 3D molecular information into graph invariants. We propose an algebraic graph-assisted bidirectional transformer (AGBT) framework by fusing representations generated by algebraic graph and bidirectional transformer, as well as a variety of machine learning algorithms, including decision trees, multitask learning, and deep neural networks. We validate the proposed AGBT framework on eight molecular datasets, involving quantitative toxicity, physical chemistry, and physiology datasets. Extensive numerical experiments have shown that AGBT is a state-of-the-art framework for molecular property prediction. Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Here, the authors propose an algebraic graph-assisted bidirectional transformer, which can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy and assisted with 3D stereochemical information from graphs.