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

• URL: http://arxiv.org/abs/2507.07201v1
• Date: Wed, 09 Jul 2025 18:19:50 GMT
• Title: MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation
• Authors: Dong Xu, Zhangfan Yang, Sisi Yuan, Jenna Xinyi Yao, Jiangqiang Li, Junkai Ji,
• Abstract summary: We introduce MODA, a diffusion framework that unifies fragment growing, linker design, scaffold hopping, and side-chain decoration with a Bayesian mask scheduler.<n>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.
• Score: 16.07694748790297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion [60.186310080523135]
  Bifurcation of generative modeling into autoregressive approaches for discrete data (text) and diffusion approaches for continuous data (images) hinders development of truly unified multimodal systems.<n>We propose textbfCoM-DAD, a novel probabilistic framework that reformulates multimodal generation as a hierarchical dual-process.<n>Our method demonstrates superior stability over standard masked modeling, establishing a new paradigm for scalable, unified text-image generation.
  arXiv  Detail & Related papers  (2026-01-07T16:21:19Z)
• OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design [0.2578364360202627]
  We propose a unified approach in OMTRA, which flexibly performs many tasks relevant to drug design (SBDD)<n>We curate a dataset of 500M 3D molecular conformers, complementing protein-ligand data and expanding the chemical diversity available for training.<n>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.
  arXiv  Detail & Related papers  (2025-12-04T18:46:35Z)
• Cross-Modality Controlled Molecule Generation with Diffusion Language Model [14.435311248340824]
  Cross-Modality Controlled Molecule Generation with Diffusion Language Model (CMCM-DLM)<n>Our approach builds upon a pre-trained diffusion model, incorporating two trainable modules, the Structure Control Module (SCM) and the Property Control Module (PCM)<n>Phase I employs the SCM to inject structural constraints during the early diffusion steps, effectively anchoring the molecular backbone.<n>Phase II builds on this by further introducing PCM to guide the later stages of inference to refine the generated molecules, ensuring their chemical properties match the specified targets.
  arXiv  Detail & Related papers  (2025-08-20T14:48:44Z)
• Evolutionary training-free guidance in diffusion model for 3D multi-objective molecular generation [13.140891054725962]
  EGD is a training-free framework that embeds evolutionary operators directly into the diffusion sampling process.<n>On both single- and multi-target 3D conditional generation tasks EGD outperforms state-of-the-art conditional diffusion methods in accuracy and runs up to five times faster per generation.<n> EGD can embed arbitrary 3D fragments into the generated molecules while optimizing multiple conflicting properties in one unified process.
  arXiv  Detail & Related papers  (2025-05-16T09:32:40Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [77.26556208024633]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Adding Additional Control to One-Step Diffusion with Joint Distribution Matching [58.37264951734603]
  JDM is a novel approach that minimizes the reverse KL divergence between image-condition joint distributions.<n>By deriving a tractable upper bound, JDM decouples fidelity learning from condition learning.<n>This asymmetric distillation scheme enables our one-step student to handle controls unknown to the teacher model.
  arXiv  Detail & Related papers  (2025-03-09T15:06:50Z)
• Exploring Discrete Flow Matching for 3D De Novo Molecule Generation [0.0]
  Flow matching is a recently proposed generative modeling framework that has achieved impressive performance on a variety of tasks. We present FlowMol-CTMC, an open-source model that achieves state of the art performance for 3D de novo design with fewer learnable parameters than existing methods.
  arXiv  Detail & Related papers  (2024-11-25T18:27:39Z)
• DPLM-2: A Multimodal Diffusion Protein Language Model [75.98083311705182]
  We introduce DPLM-2, a multimodal protein foundation model that extends discrete diffusion protein language model (DPLM) to accommodate both sequences and structures. DPLM-2 learns the joint distribution of sequence and structure, as well as their marginals and conditionals. Empirical evaluation shows that DPLM-2 can simultaneously generate highly compatible amino acid sequences and their corresponding 3D structures.
  arXiv  Detail & Related papers  (2024-10-17T17:20:24Z)
• PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation [51.509573838103854]
  We propose a semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation. Our PMT generates high-fidelity pseudo labels by learning robust and diverse features in the training process. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches.
  arXiv  Detail & Related papers  (2024-09-08T15:02:25Z)
• UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning [31.445533039355166]
  We propose a novel pre-training framework, named UniCorn, depicting molecular views in three different levels. SOTA performance across quantum, physicochemical, and biological tasks, along with comprehensive ablation study, validate the universality and effectiveness of UniCorn.
  arXiv  Detail & Related papers  (2024-05-15T09:20:02Z)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design [62.68420322996345]
  Existing structured-based drug design methods treat all ligand atoms equally. We propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold. Our approach achieves state-of-the-art performance in generating high-affinity molecules.
  arXiv  Detail & Related papers  (2024-02-26T05:21:21Z)
• Scaffold-constrained molecular generation [0.0]
  We build on the well-known SMILES-based Recurrent Neural Network (RNN) generative model, with a modified sampling procedure to achieve scaffold-constrained generation. We showcase the method's ability to perform scaffold-constrained generation on various tasks.
  arXiv  Detail & Related papers  (2020-09-15T15:41:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.