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

TL;DR

OMTRA introduces a unified multi-task generative model for structure-based drug design, leveraging large-scale 3D molecular data to improve ligand design and docking, with modest gains from extensive pretraining.

Contribution

It presents OMTRA, a novel multi-modal flow matching model that unifies various SBDD tasks and introduces a large curated 3D molecular dataset for training.

Findings

State-of-the-art performance on de novo design and docking.

Large-scale pretraining and multi-task training have modest effects.

Provides open-source code, models, and dataset for reproducibility.

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