使用 GenBench3D 对基于结构的三维分子生成模型进行基准测试：配体构象质量至关重要
Benchmarking structure-based three-dimensional molecular generative models using GenBench3D: ligand conformation quality matters
AI总结：
本文提出 GenBench3D 基准及 Validity3D 指标，通过构象有效性评估六种三维分子生成模型，发现仅少数生成分子构象有效，局部弛豫可显著改善构象质量并揭示结合亲和力可能被高估。
摘要：
三维（3D）深度分子生成模型具有基于三维依赖性质（如结合口袋内基于结构设计中的结合亲和力）进行目标导向生成的优势。为评估 SMILES 或分子图生成器而创建的传统基准（如 GuacaMol 或 MOSES）在评估三维生成器方面存在局限，因为它们不评估所生成分子构象的质量。因此，在本工作中，我们开发了 GenBench3D，它为在结合口袋内生成分子的模型实现了一个新的基准。我们的主要贡献是 Validity3D 指标，该指标基于剑桥结构数据库（Cambridge Structural Database）中观测到的参考值，利用键长和键角的似然来评估构象质量。我们对 LiGAN、3D-SBDD、Pocket2Mol、TargetDiff、DiffSBDD 和 ResGen 模型进行了基准测试。我们发现，生成的分子中只有 0% 到 11% 具有有效构象。对口袋中生成的分子进行局部弛豫后，所有模型的 Validity3D 均显著提高，最小增幅为 40%。对于 LiGAN、3D-SBDD 或 TargetDiff，有效弛豫分子集合的平均 Vina 得分（即更差）高于原始生成分子集合，这表明原始生成分子的结合亲和力可能被高估。使用其他更强调配体应变的评分函数时，只有在使用有效弛豫分子时才能获得改善的得分。使用有效弛豫分子时，TargetDiff 和 Pocket2Mol 显示出比其他模型更好的中位 Vina、Glide 和 Gold PLP 得分。我们已在 GitHub 上公开发布 GenBench3D 以供更广泛使用：https://github.com/bbaillif/genbench3d
英文摘要：
Three-dimensional (3D) deep molecular generative models offer the advantage of goal-directed generation based on 3D-dependent properties, such as binding affinity for structure-based design within binding pockets. Traditional benchmarks created to evaluate SMILES or molecular graphs generators, such as GuacaMol or MOSES, are limited to evaluate 3D generators as they do not assess the quality of the generated molecular conformation. In this work, we hence developed GenBench3D, which implements a new benchmark for models producing molecules within a binding pocket. Our main contribution is the Validity3D metric, evaluating the conformation quality using the likelihood of bond lengths and valence angles based on reference values observed in the Cambridge Structural Database. The LiGAN, 3D-SBDD, Pocket2Mol, TargetDiff, DiffSBDD and ResGen models were benchmarked. We show that only between 0% and 11% of generated molecules have valid conformations. Performing local relaxation of generated molecules in the pocket considerably improved the Validity3D for all models by a minimum increase of 40%. For LiGAN, 3D-SBDD, or TargetDiff, the set of valid relaxed molecules shows on average higher Vina score (i.e. worse) than the set of raw generated molecules, indicating that the binding affinity of raw generated molecules might be overestimated. Using the other scoring functions, that give higher importance to ligand strain, only yield improved scores when using valid relaxed molecules. Using valid relaxed molecules, TargetDiff and Pocket2Mol show better median Vina, Glide and Gold PLP scores than other models. We have publicly released GenBench3D on GitHub for broader use: https://github.com/bbaillif/genbench3d
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
