Multi-domain Distribution Learning for De Novo Drug Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schneuing, Arne, Igashov, Ilia, Dobbelstein, Adrian W., Castiglione, Thomas, Bronstein, Michael, Correia, Bruno
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909752171167744
author Schneuing, Arne
Igashov, Ilia
Dobbelstein, Adrian W.
Castiglione, Thomas
Bronstein, Michael
Correia, Bruno
author_facet Schneuing, Arne
Igashov, Ilia
Dobbelstein, Adrian W.
Castiglione, Thomas
Bronstein, Michael
Correia, Bruno
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-domain Distribution Learning for De Novo Drug Design
Schneuing, Arne
Igashov, Ilia
Dobbelstein, Adrian W.
Castiglione, Thomas
Bronstein, Michael
Correia, Bruno
Machine Learning
Biomolecules
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.
title Multi-domain Distribution Learning for De Novo Drug Design
topic Machine Learning
Biomolecules
url https://arxiv.org/abs/2508.17815