Introduction

This package provide fast and accurate machine learning models for biochemical applications. Especially, we support very high-dimensional models with sparse inputs, e.g., millions of features and millions of compounds.

The general documentation can be found here.
Documentation about how to retrain a pretrained model can be found here.
Documentation about how to profile GPU memory usage and use mixed precision can be found here.
Documentation about how to use Catalogue Fusion can be found here.

Reference

If you use this software in your work, please cite:

@article{arany2022sparsechem,
  title={SparseChem: Fast and accurate machine learning model for small molecules},
  author={Arany, Adam and Simm, Jaak and Oldenhof, Martijn and Moreau, Yves},
  journal={arXiv preprint arXiv:2203.04676},
  year={2022}
}

melloddy/SparseChem

Introduction

Reference