We provide various examples across 3 applications -- property prediction, generative models and protein-ligand binding affinity prediction.
- MoleculeNet: A Benchmark for Molecular Machine Learning [paper], [website]
- Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models [paper], [github]
- PubChem Aromaticity [paper]
- Molecular graph convolutions: moving beyond fingerprints (Weave) [paper], [github]
- Semi-Supervised Classification with Graph Convolutional Networks (GCN) [paper], [github]
- Graph Attention Networks (GAT) [paper], [github]
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions [paper], [github]
- Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective (MGCN) [paper]
- Neural Message Passing for Quantum Chemistry (MPNN) [paper], [github]
- Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism (AttentiveFP) [paper]
- Learning Deep Generative Models of Graphs (DGMG) [paper]
- Junction Tree Variational Autoencoder for Molecular Graph Generation (JTNN) [paper]
- Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity (ACNN) [paper], [github]
- A graph-convolutional neural network model for the prediction of chemical reactivity [paper], [github]
- An earlier version was published in NeurIPS 2017 as "Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network" [paper]
- WLN with DGL for Reaction Center Prediction
- Example Script