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

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Molecular Property Prediction BACE ChemRL-GEM ROC-AUC 85.6 # 3
Molecular Property Prediction BBBP ChemRL-GEM ROC-AUC 72.4 # 6
Molecular Property Prediction ClinTox ChemRL-GEM ROC-AUC 90.1 # 6
Molecules (M) 20 # 2
Molecular Property Prediction ESOL ChemRL-GEM RMSE 0.798 # 2
Molecular Property Prediction FreeSolv ChemRL-GEM RMSE 1.877 # 3
Molecular Property Prediction Lipophilicity ChemRL-GEM RMSE 0.66 # 2
Molecular Property Prediction QM7 ChemRL-GEM MAE 58.9 # 2
Molecular Property Prediction QM8 ChemRL-GEM MAE 0.0171 # 2
Molecular Property Prediction QM9 ChemRL-GEM MAE 0.00746 # 2
Molecular Property Prediction SIDER ChemRL-GEM ROC-AUC 67.2 # 2
Molecular Property Prediction Tox21 ChemRL-GEM ROC-AUC 78.1 # 3
Molecular Property Prediction ToxCast ChemRL-GEM ROC-AUC 69.2 # 2


No methods listed for this paper. Add relevant methods here