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

2025/12/04 by Ian Dunn, Dunn, Ian, Liv Toft +10
Biochemistry, Genetics and Molecular Biology · Computer Science · #Cell Image Analysis Techniques #Computational Drug Discovery Methods #FOS: Computer and information sciences #Machine Learning (cs.LG) #Protein Structure and Dynamics

paper · pdf · doi:10.48550/arxiv.2512.05080

openalex publication_date 2025/12/04 · openalex created_date 2025/12/06 · openalex updated_date 2026/07/28

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

Citations

• Multi-domain Distribution Learning for De Novo Drug Design
• FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
• Applications of Modular Co-Design for De Novo 3D Molecule Generation
• GEOM-Drugs Revisited: Toward More Chemically Accurate Benchmarks for 3D Molecule Generation
• FLOWR: Flow Matching for Structure-Aware De Novo, Interaction- and Fragment-Based Ligand Generation
• All-atom Diffusion Transformers: Unified generative modelling of molecules and materials
• FlowDock: Geometric Flow Matching for Generative Protein-Ligand Docking and Affinity Prediction
• DeFoG: Discrete Flow Matching for Graph Generation
• Discrete Flow Matching
• Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
• PILOT: Equivariant diffusion for pocket conditioned de novo ligand generation with multi-objective guidance via importance sampling
• Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
• Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
• Benchmarking Generated Poses: How Rational is Structure-based Drug Design with Generative Models?
• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
• 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
• Improving and generalizing flow-based generative models with minibatch optimal transport
• Structure-based Drug Design with Equivariant Diffusion Models
• Flow Matching for Generative Modeling
• DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
• A 3D Generative Model for Structure-Based Drug Design
• Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Models
• Equivariant Graph Neural Networks for 3D Macromolecular Structure
• Score-Based Generative Modeling through Stochastic Differential Equations
• Denoising Diffusion Probabilistic Models
• Attention Is All You Need
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Related

• Structure-aware generation of drug-like molecules
• MolFORM: Multi-modal Flow Matching for Structure-Based Drug Design
• Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?
• CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
• Generative molecule evolution using 3D pharmacophore for efficient Structure-Based Drug Design