Molecule pretraining has quickly become the go-to schema to boost the performance of AI-
based drug discovery. Naturally, molecules can be represented as 2D topological graphs or …

Coordinate denoising is a promising 3D molecular pre-training method, which has achieved
remarkable performance in various downstream drug discovery tasks. Theoretically, the …

Recent advances in computational modelling of atomic systems, spanning molecules,
proteins, and materials, represent them as geometric graphs with atoms embedded as …

Generating desirable molecular structures in 3D is a fundamental problem for drug
discovery. Despite the considerable progress we have achieved, existing methods usually …

Molecules are frequently represented as graphs, but the underlying 3D molecular geometry
(the locations of the atoms) ultimately determines most molecular properties. However, most …

SMILES, a crucial textual representation of molecular structures, has garnered significant
attention as a foundation for pre-trained language models (LMs). However, most existing pre …

Abstract 3D molecular representation learning has gained tremendous interest and
achieved promising performance in various downstream tasks. A series of recent …