模块化协同设计在从头三维分子生成中的应用
Applications of Modular Co-Design for De Novo 3D Molecule Generation
AI总结：
本文提出可扩展Transformer模型家族Megalodon，通过等变层和联合去噪协同设计目标，在三维分子生成基准上达到最先进性能，参数翻倍至40M可生成49倍更多有效大分子且能量低2-10倍。
摘要：
从头三维分子生成是药物发现中的一项关键任务。然而，许多近期的几何生成模型即使能保持二维有效性和拓扑稳定性，也难以生成高质量的三维结构。为解决这一问题并增强有效分子生成动力学的学习，我们提出了Megalodon——一个可扩展的Transformer模型家族。这些模型通过基本的等变层进行增强，并使用联合连续和离散去噪协同设计目标进行训练。我们在已建立的分子生成基准上评估了Megalodon的性能，并引入了新的三维结构基准，这些基准评估模型生成真实分子结构的能力，特别关注能量学。我们展示了Megalodon在三维分子生成、条件结构生成和结构能量基准上使用扩散和流匹配达到了最先进的结果。此外，将Megalodon的参数数量翻倍至4000万显著提升了其性能，生成了多达49倍更多的有效大分子，并实现了比先前最佳生成模型低2-10倍的能量水平。
英文摘要：
De novo 3D molecule generation is a pivotal task in drug discovery. However, many recent geometric generative models struggle to produce high-quality 3D structures, even if they maintain 2D validity and topological stability. To tackle this issue and enhance the learning of effective molecular generation dynamics, we present Megalodon-a family of scalable transformer models. These models are enhanced with basic equivariant layers and trained using a joint continuous and discrete denoising co-design objective. We assess Megalodon's performance on established molecule generation benchmarks and introduce new 3D structure benchmarks that evaluate a model's capability to generate realistic molecular structures, particularly focusing on energetics. We show that Megalodon achieves state-of-the-art results in 3D molecule generation, conditional structure generation, and structure energy benchmarks using diffusion and flow matching. Furthermore, doubling the number of parameters in Megalodon to 40M significantly enhances its performance, generating up to 49x more valid large molecules and achieving energy levels that are 2-10x lower than those of the best prior generative models.
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。
