Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science.
Ranked #4 on Graph Regression on ZINC-500k
In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets.
Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training.
Ranked #2 on Drug Discovery on SIDER
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.
Ranked #6 on Graph Regression on Lipophilicity
There are also some recent methods based on language models (e. g. graph2vec) but they tend to only consider certain substructures (e. g. subtrees) as graph representatives.
Ranked #17 on Graph Classification on IMDb-B
GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction.
Here we develop the MoleculeKit, a suite of comprehensive machine learning tools spanning different computational models and molecular representations for molecular property prediction and drug discovery.
Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic information.
Ranked #1 on Graph Regression on Lipophilicity