English

OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design

Machine Learning 2025-12-05 v1

Abstract

Structure-based drug design (SBDD) focuses on designing small-molecule ligands that bind to specific protein pockets. Computational methods are integral in modern SBDD workflows and often make use of virtual screening methods via docking or pharmacophore search. Modern generative modeling approaches have focused on improving novel ligand discovery by enabling de novo design. In this work, we recognize that these tasks share a common structure and can therefore be represented as different instantiations of a consistent generative modeling framework. We propose a unified approach in OMTRA, a multi-modal flow matching model that flexibly performs many tasks relevant to SBDD, including some with no analogue in conventional workflows. Additionally, we curate a dataset of 500M 3D molecular conformers, complementing protein-ligand data and expanding the chemical diversity available for training. OMTRA obtains state of the art performance on pocket-conditioned de novo design and docking; however, the effects of large-scale pretraining and multi-task training are modest. All code, trained models, and dataset for reproducing this work are available at https://github.com/gnina/OMTRA

Keywords

Cite

@article{arxiv.2512.05080,
  title  = {OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design},
  author = {Ian Dunn and Liv Toft and Tyler Katz and Juhi Gupta and Riya Shah and Ramith Hettiarachchi and David R. Koes},
  journal= {arXiv preprint arXiv:2512.05080},
  year   = {2025}
}

Comments

Presented at the Machine Learning for Structural Biology Workshop, 2025

R2 v1 2026-07-01T08:10:00.567Z