用电子密度指导生成药物分子，更贴近真实结合环境。
From Holo Pockets to Electron Density: GPT-style Drug Design with Density
- 以低分辨率电子密度为条件生成新分子，替代传统空口袋表示。
- 在101个靶点上验证，生成分子三维结构更合理且有活性。
- 适合药物设计、生成模型研究者，尤其关注物理可解释性的人。
生成模型的进步推动了基于结构的药物设计发展。现有方法通常以完整复合物中的空结合口袋为条件生成分子，忽略了配体和溶剂等填充物所携带的信息。本文利用来自填充物的低分辨率电子密度（ED）作为从头药物设计的物理基础条件，涵盖计算和实验来源的两种类型ED（如冷冻电镜/晶体学数据），支持统一预训练与实验整合。相比刚性口袋表示，实验获取的电子密度自然反映构象灵活性，更真实描述结合环境。为此，我们提出EDMolGPT——一种仅解码器的自回归框架，从低分辨率电子密度点云生成分子。通过在物理意义明确的密度信号上进行生成，缓解了结构偏差问题，产出具有合理3D构象的分子。在101个生物靶点上的评估验证了其有效性。
原文摘要 · Abstract (English)
Recent advances in generative modeling have enabled significant progress in structure-based drug design (SBDD). Existing methods typically condition molecule generation on empty binding pockets from holo complexes, overlooking informative components such as the filler (ligands and solvent). Here, we leverage low-resolution electron density (ED) derived from the filler as a physically grounded condition for \textit{de novo} drug design. We consider two types of ED, calculated and cryo-EM/X-ray, obtainable from computational or experimental sources, supporting unified pre-training and experimental integration. Compared with rigid pocket representations, experimental ED naturally captures conformational flexibility and provides a more faithful description of the binding environment. Based on this, we introduce EDMolGPT, a decoder-only autoregressive framework that generates molecules from low-resolution ED point clouds. By grounding generation in physically meaningful density signals, EDMolGPT mitigates structural bias and produces molecules with 3D conformations. Evaluations on 101 biological targets verify the effectiveness. Our project page: https://jiahaochen1.github.io/EDMolGPT_Page/.
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。