Multi-Domain Distribution Learning for De Novo Drug Design
Abstract
We introduce DrugFlow, a generative model for structure-based drug design that integrates continuous flow matching with discrete Markov bridges, demonstrating state-of-the-art performance in learning chemical, geometric, and physical aspects of three-dimensional protein-ligand data. We endow DrugFlow with an uncertainty estimate that is able to detect out-of-distribution samples. To further enhance the sampling process towards distribution regions with desirable metric values, we propose a joint preference alignment scheme applicable to both flow matching and Markov bridge frameworks. Furthermore, we extend our model to also explore the conformational landscape of the protein by jointly sampling side chain angles and molecules.
Cite
Text
Schneuing et al. "Multi-Domain Distribution Learning for De Novo Drug Design." International Conference on Learning Representations, 2025.Markdown
[Schneuing et al. "Multi-Domain Distribution Learning for De Novo Drug Design." International Conference on Learning Representations, 2025.](https://mlanthology.org/iclr/2025/schneuing2025iclr-multidomain/)BibTeX
@inproceedings{schneuing2025iclr-multidomain,
title = {{Multi-Domain Distribution Learning for De Novo Drug Design}},
author = {Schneuing, Arne and Igashov, Ilia and Dobbelstein, Adrian W. and Castiglione, Thomas and Bronstein, Michael M. and Correia, Bruno},
booktitle = {International Conference on Learning Representations},
year = {2025},
url = {https://mlanthology.org/iclr/2025/schneuing2025iclr-multidomain/}
}