Tetrahedral molecular pretraining for enhanced property prediction

• Novel tetrahedra-centric pretraining for 3D molecular representation learning. • Geometric patterns and chemical prior introduced in modeling and pretraining proves beneficial. • Consistent performance gains across biochemical and quantum property predictions. • Scalable to complex protein-ligand systems with robust performance. • Improved interpretability validated by a probing task and embedding visualization. Self-supervised learning on 3D molecular structures has emerged as a promising direction in data-driven scientific research, addressing the significant challenge of limited annotated biochemical data. While the identification of semantic units for pretraining has been well-established in natural language processing and computer vision, determining optimal building blocks for characterizing 3D molecular architectures remains underexplored. We present Tetrahedral Molecular Pretraining (TMP), a novel approach that recognizes tetrahedrons as fundamental building blocks, leveraging their geometric simplicity and recurring presence across chemical functional groups. Through systematic perturbation and reconstruction of tetrahedral substructures, TMP implements a self-supervised learning strategy that recovers both their global arrangements and local patterns, learning rich molecular representations that encode multi-scale structural information. Extensive evaluations on 24 benchmark datasets demonstrate that TMP consistently outperforms existing methods in tasks ranging from biochemical property prediction to quantum property prediction. Notably, the tetrahedra-based modeling successfully scales from small molecules to complex protein-ligand systems, achieving new state-of-the-art results in binding affinity prediction. Our findings highlight how the identification of representative structural patterns can lead to more expressive and interpretable neural networks for scientific applications.