Cross-Modality Controlled Molecule Generation with Diffusion Language Model

TL;DR

This paper introduces CMCM-DLM, a diffusion-based molecule generation model that supports cross-modality constraints like structure and properties without retraining, enabling flexible and efficient molecule design.

Contribution

It proposes a novel framework with trainable modules for cross-modality control in pre-trained diffusion models, allowing dynamic constraint incorporation during molecule generation.

Findings

Effective structural anchoring during early diffusion stages

Guided property refinement in later inference steps

Demonstrated adaptability across multiple datasets

Abstract

Current SMILES-based diffusion models for molecule generation typically support only unimodal constraint. They inject conditioning signals at the start of the training process and require retraining a new model from scratch whenever the constraint changes. However, real-world applications often involve multiple constraints across different modalities, and additional constraints may emerge over the course of a study. This raises a challenge: how to extend a pre-trained diffusion model not only to support cross-modality constraints but also to incorporate new ones without retraining. To tackle this problem, we propose the Cross-Modality Controlled Molecule Generation with Diffusion Language Model (CMCM-DLM), demonstrated by two distinct cross modalities: molecular structure and chemical properties. Our approach builds upon a pre-trained diffusion model, incorporating two trainable modules, the Structure Control Module (SCM) and the Property Control Module (PCM), and operates in two distinct phases during the generation process. In Phase I, we employs the SCM to inject structural constraints during the early diffusion steps, effectively anchoring the molecular backbone. 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. Experimental results on multiple datasets demonstrate the efficiency and adaptability of our approach, highlighting CMCM-DLM's significant advancement in molecular generation for drug discovery applications.