tl;dr: We provably improve GNN expressivity by enhancing message passing with substructure encodings. Our method allows incorporating domain specific prior knowledge and can be used as a drop-in ...

smiles-encoder is a Python package used to generate one-hot vectors representing SMILES strings (each string element is a one-hot vector). To contribute to smiles-encoder, make a pull request.

Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we ...

Climate forecasts, both experimental and operational, are often made by calibrating Global Climate Model (GCM) outputs with observed climate variables using statistical and machine learning models.