Algebraic graph-assisted bidirectional transformers for molecular property prediction

TLDR

Molecular property prediction is crucial for drug discovery, health, and environmental protection, yet accurate quantitative prediction remains challenging. The study proposes an algebraic graph‑assisted bidirectional transformer framework that fuses algebraic graph and transformer representations with various machine learning algorithms. The framework combines a bidirectional transformer with an element‑specific multiscale weighted colored algebraic graph to embed 3D stereochemical information, and is validated on eight datasets covering toxicity, physical chemistry, and physiology. Experiments demonstrate that AGBT achieves state‑of‑the‑art performance in molecular property prediction.

Abstract

Abstract 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.