用化学语法生成精准3D分子结构，提升药物设计效率
MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
- 通过可学习查询提取1D模型中的化学知识
- 在QM9和GEOM-DRUGS上实现顶尖3D生成效果
- 适合分子生成与药物发现领域研究者
生成精确的3D分子几何结构对药物发现和材料科学至关重要。现有方法虽利用如SELFIES等一维表示确保分子有效性，但未能充分挖掘一维模型中蕴含的丰富化学知识，导致一维语法生成与三维几何实现之间存在脱节。为此，我们提出MolSculpt，一种从化学语法“雕刻”三维分子结构的新框架。该框架基于冻结的一维分子基础模型与三维分子扩散模型，引入可学习查询以提取基础模型中的内在化学知识，并通过可训练投影器将此跨模态信息注入扩散模型的条件空间，引导三维几何生成。由此，模型通过端到端优化，深度整合了一维潜在化学知识至三维生成过程。实验表明，MolSculpt在分子生成和条件生成任务上均达到当前最优性能，在QM9和GEOM-DRUGS数据集上展现出更优的三维保真度与稳定性。代码已开源。
原文摘要 · Abstract (English)
Generating precise 3D molecular geometries is crucial for drug discovery and material science. While prior efforts leverage 1D representations like SELFIES to ensure molecular validity, they fail to fully exploit the rich chemical knowledge entangled within 1D models, leading to a disconnect between 1D syntactic generation and 3D geometric realization. To bridge this gap, we propose MolSculpt, a novel framework that "sculpts" 3D molecular geometries from chemical syntax. MolSculpt is built upon a frozen 1D molecular foundation model and a 3D molecular diffusion model. We introduce a set of learnable queries to extract inherent chemical knowledge from the foundation model, and a trainable projector then injects this cross-modal information into the conditioning space of the diffusion model to guide the 3D geometry generation. In this way, our model deeply integrates 1D latent chemical knowledge into the 3D generation process through end-to-end optimization. Experiments demonstrate that MolSculpt achieves state-of-the-art (SOTA) performance in \textit{de novo} 3D molecule generation and conditional 3D molecule generation, showing superior 3D fidelity and stability on both the GEOM-DRUGS and QM9 datasets. Code is available at https://github.com/SakuraTroyChen/MolSculpt.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。