GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
This work addresses the need for chemically interpretable models in molecular sciences, offering a novel method for reliable property prediction.
The paper tackles the problem of molecular representation learning by introducing GeoT, a geometry-aware Transformer that improves interpretability and achieves comparable performance to MPNN-based models with reduced computational complexity.
In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks. However, many existing models fail to fully consider the geometric information of molecular structures, resulting in less intuitive representations. Moreover, the widely used message-passing mechanism is limited to provide the interpretation of experimental results from a chemical perspective. To address these challenges, we introduce a novel Transformer-based framework for molecular representation learning, named the Geometry-aware Transformer (GeoT). GeoT learns molecular graph structures through attention-based mechanisms specifically designed to offer reliable interpretability, as well as molecular property prediction. Consequently, GeoT can generate attention maps of interatomic relationships associated with training objectives. In addition, GeoT demonstrates comparable performance to MPNN-based models while achieving reduced computational complexity. Our comprehensive experiments, including an empirical simulation, reveal that GeoT effectively learns the chemical insights into molecular structures, bridging the gap between artificial intelligence and molecular sciences.