MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation

TL;DR

MODA introduces a unified 3D diffusion framework that enhances multi-task molecular generation, improving stereochemical fidelity, task alignment, and zero-shot transfer across various molecular design tasks.

Contribution

The paper presents MODA, a novel diffusion-based framework that unifies multiple molecular design tasks into a single multi-task model, surpassing existing baselines and simplifying workflows.

Findings

Outperforms six diffusion baselines and three training paradigms.

Reduces ligand-protein clashes and maintains Lipinski compliance.

Achieves high-quality zero-shot de novo design and lead optimization.

Abstract

Three-dimensional molecular generators based on diffusion models can now reach near-crystallographic accuracy, yet they remain fragmented across tasks. SMILES-only inputs, two-stage pretrain-finetune pipelines, and one-task-one-model practices hinder stereochemical fidelity, task alignment, and zero-shot transfer. We introduce MODA, a diffusion framework that unifies fragment growing, linker design, scaffold hopping, and side-chain decoration with a Bayesian mask scheduler. During training, a contiguous spatial fragment is masked and then denoised in one pass, enabling the model to learn shared geometric and chemical priors across tasks. Multi-task training yields a universal backbone that surpasses six diffusion baselines and three training paradigms on substructure, chemical property, interaction, and geometry. Model-C reduces ligand-protein clashes and substructure divergences while maintaining Lipinski compliance, whereas Model-B preserves similarity but trails in novelty and binding affinity. Zero-shot de novo design and lead-optimisation tests confirm stable negative Vina scores and high improvement rates without force-field refinement. These results demonstrate that a single-stage multi-task diffusion routine can replace two-stage workflows for structure-based molecular design.