CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation

TL;DR

CAGenMol is a novel condition-aware discrete diffusion model for goal-directed molecular generation, integrating reinforcement learning to optimize multiple objectives while maintaining chemical validity.

Contribution

It introduces a diffusion-based framework that combines conditional denoising with reinforcement learning for multi-objective molecular design.

Findings

Outperforms state-of-the-art in binding affinity and drug-likeness.

Maintains high chemical validity and diversity.

Effective in structure, property, and dual-conditioned tasks.

Abstract

Goal-directed molecular generation requires satisfying heterogeneous constraints such as protein--ligand compatibility and multi-objective drug-like properties, yet existing methods often optimize these constraints in isolation, failing to reconcile conflicting objectives (e.g., affinity vs. safety), and struggle to navigate the non-differentiable chemical space without compromising structural validity. To address these challenges, we propose CAGenMol, a condition-aware discrete diffusion framework over molecular sequences that formulates molecular design as conditional denoising guided by heterogeneous structural and property signals. By coupling discrete diffusion with reinforcement learning, the model aligns the generation trajectory with non-differentiable objectives while preserving chemical validity and diversity. The non-autoregressive nature of diffusion language model further enables iterative refinement of molecular fragments at inference time. Experiments on structure-conditioned, property-conditioned, and dual-conditioned benchmarks demonstrate consistent improvements over state-of-the-art methods in binding affinity, drug-likeness, and success rate, highlighting the effectiveness of our framework.