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

• URL: http://arxiv.org/abs/2604.11483v1
• Date: Mon, 13 Apr 2026 13:49:23 GMT
• Title: CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation
• Abstract summary: We propose CAGenMol, a condition-aware discrete diffusion framework over molecular sequences.<n>By coupling discrete diffusion with reinforcement learning, the model aligns the generation trajectory with non-differentiable objectives.<n> Experiments on structure-conditioned, property-conditioned, and dual-conditioned benchmarks demonstrate consistent improvements.
• Score: 14.125369423416275
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Autoregressive latent diffusion for 3D molecule generation [11.599617045790517]
  KRONOS is a latent autoregressive diffusion framework that generates molecules in the latent space of a pre-trained autoencoder.<n>Experiments on QM9 and GEOM-Drugs demonstrate that KRONOS achieves leading unconditional generation performance among autoregressive methods.
  arXiv  Detail & Related papers  (2026-07-10T10:47:11Z)
• Controllable protein design through Feynman-Kac steering [5.477297165738714]
  We extend the Feynman-Kac steering framework, an inference-time control approach, to diffusion-based protein design.<n>This work demonstrates that inference-time FK control generalizes diffusion-based protein design to arbitrary, non-differentiable, and reward-agnostic objectives.
  arXiv  Detail & Related papers  (2025-11-12T11:23:44Z)
• DEMO:Diffusion-based Evolutionary Optimization for 3D Multi-Objective Molecular Generation [25.82864719790724]
  optimizing multiple objective properties while satisfying structural constraints is a major challenge in 3D molecular discovery.<n>We propose a novel 3D molecular multi-objective evolutionary algorithm that leverages the generative power of a pretrained diffusion model.<n>Our method performs crossover operations in the noise space defined by the diffusion model's forward process, thereby enabling parental features or desired fragments to be fused into offspring.
  arXiv  Detail & Related papers  (2025-05-16T09:32:40Z)
• Molecule Generation for Target Protein Binding with Hierarchical Consistency Diffusion Model [17.885767456439215]
  Atom-Motif Consistency Diffusion Model (AMDiff) is a hierarchical diffusion architecture that integrates both atom- and motif-level views of molecules.<n>Compared to existing approaches, AMDiff exhibits superior validity and novelty in generating molecules tailored to fit various protein pockets.
  arXiv  Detail & Related papers  (2025-03-02T17:54:30Z)
• Conditional Synthesis of 3D Molecules with Time Correction Sampler [58.0834973489875]
  Time-Aware Conditional Synthesis (TACS) is a novel approach to conditional generation on diffusion models. It integrates adaptively controlled plug-and-play "online" guidance into a diffusion model, driving samples toward the desired properties.
  arXiv  Detail & Related papers  (2024-11-01T12:59:25Z)
• Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design [81.95343363178662]
  atoms must maintain a minimum pairwise distance to avoid separation violations. NucleusDiff models the interactions between atomic nuclei and their surrounding electron clouds by enforcing the distance constraint. It reduces violation rate by up to 1000% and enhances binding affinity by up to 22.16%, surpassing state-of-the-art models for structure-based drug design.
  arXiv  Detail & Related papers  (2024-09-16T08:42:46Z)
• Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization [147.7899503829411]
  AliDiff is a novel framework to align pretrained target diffusion models with preferred functional properties. It can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score.
  arXiv  Detail & Related papers  (2024-07-01T06:10:29Z)
• LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models [55.5427001668863]
  We present a novel latent diffusion model dubbed LDMol for text-conditioned molecule generation.<n> Experiments show that LDMol outperforms the existing autoregressive baselines on the text-to-molecule generation benchmark.<n>We show that LDMol can be applied to downstream tasks such as molecule-to-text retrieval and text-guided molecule editing.
  arXiv  Detail & Related papers  (2024-05-28T04:59:13Z)
• AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design [16.946648071157618]
  We propose a diffusion-based fragment-wise autoregressive generation model for structure-based drug design (SBDD) We design a novel molecule assembly strategy named conformal motif that preserves the conformation of local structures of molecules first. We then encode the interaction of the protein-ligand complex with an SE(3)-equivariant convolutional network and generate molecules motif-by-motif with diffusion modeling.
  arXiv  Detail & Related papers  (2024-04-02T14:44:02Z)
• 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)
• Molecular Attributes Transfer from Non-Parallel Data [57.010952598634944]
  We formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data. Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-30T06:10:22Z)

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.