用扩散模型生成3D分子，能准确补氢并跨类别生成。
D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation
- 结合扩散变换器与多头等变自注意力，学习去氢后分子表征。
- 在多个指标上达到顶尖性能，可同时生成多类分子结构。
- 适合药物设计早期大规模生成，后续可筛选特定功能分子。
理解并预测分子的多种构象状态对化学、材料科学和药物研发至关重要。尽管生成模型取得显著进展，但准确生成复杂且具有生物或材料相关性的分子结构仍是重大挑战。本文提出一种用于三维分子生成的扩散模型，融合可分类扩散模型与扩散变换器，并引入多头等变自注意力机制。该方法解决了两个关键问题：通过学习去除氢原子后的分子表征，准确还原氢原子；克服现有模型无法同时生成多类分子的局限。实验结果表明，该模型在多个核心指标上达到当前最优表现，具备强鲁棒性与通用性，适用于分子设计中的早期大规模生成过程，后续可进行验证与筛选，以获得具有特定性质的分子。
原文摘要 · Abstract (English)
Understanding and predicting the diverse conformational states of molecules is crucial for advancing fields such as chemistry, material science, and drug development. Despite significant progress in generative models, accurately generating complex and biologically or material-relevant molecular structures remains a major challenge. In this work, we introduce a diffusion model for three-dimensional (3D) molecule generation that combines a classifiable diffusion model, Diffusion Transformer, with multihead equivariant self-attention. This method addresses two key challenges: correctly attaching hydrogen atoms in generated molecules through learning representations of molecules after hydrogen atoms are removed; and overcoming the limitations of existing models that cannot generate molecules across multiple classes simultaneously. The experimental results demonstrate that our model not only achieves state-of-the-art performance across several key metrics but also exhibits robustness and versatility, making it highly suitable for early-stage large-scale generation processes in molecular design, followed by validation and further screening to obtain molecules with specific properties.
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。