ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction

Abstract

Effective molecular representation learning is of great importance to facilitate molecular property prediction, which is a fundamental task for the drug and material industry. Recent advances in graph neural networks (GNNs) have shown great promise in applying GNNs for molecular representation learning. Moreover, a few recent studies have also demonstrated successful applications of self-supervised learning methods to pre-train the GNNs to overcome the problem of insufficient labeled molecules. However, existing GNNs and pre-training strategies usually treat molecules as topological graph data without fully utilizing the molecular geometry information. Whereas, the three-dimensional (3D) spatial structure of a molecule, a.k.a molecular geometry, is one of the most critical factors for determining molecular physical, chemical, and biological properties. To this end, we propose a novel Geometry Enhanced Molecular representation learning method (GEM) for Chemical Representation Learning (ChemRL). At first, we design a geometry-based GNN architecture that simultaneously models atoms, bonds, and bond angles in a molecule. To be specific, we devised double graphs for a molecule: The first one encodes the atom-bond relations; The second one encodes bond-angle relations. Moreover, on top of the devised GNN architecture, we propose several novel geometry-level self-supervised learning strategies to learn spatial knowledge by utilizing the local and global molecular 3D structures. We compare ChemRL-GEM with various state-of-the-art (SOTA) baselines on different molecular benchmarks and exhibit that ChemRL-GEM can significantly outperform all baselines in both regression and classification tasks. For example, the experimental results show an overall improvement of 8.8% on average compared to SOTA baselines on the regression tasks, demonstrating the superiority of the proposed method.

Nature Machine Intelligence, 2022

References in corpus (3)

• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Self-Supervised Graph Transformer on Large-Scale Molecular Data
• Learn molecular representations from large-scale unlabeled molecules for drug discovery

Cited by in corpus (21)

• polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics
• Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
• Graph Neural Networks for Molecules
• Retention Time Prediction for Chromatographic Enantioseparation by Quantile Geometry-enhanced Graph Neural Network
• HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer
• Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
• HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction
• ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation
• A Large Encoder-Decoder Family of Foundation Models For Chemical Language
• Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• FunQG: Molecular Representation Learning Via Quotient Graphs
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space
• A Bayesian Flow Network Framework for Chemistry Tasks
• Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics
• Dual-Modality Representation Learning for Molecular Property Prediction