用修正流加速蛋白骨架生成，大幅降低计算开销。
Flows, straight but not so fast: Exploring the design space of Rectified Flows in Protein Design
- 引入修正流改进蛋白生成模型，减少采样步骤数
- 发现蛋白生成对耦合机制和退火策略高度敏感
- 针对蛋白质特性优化流模型设计，适合高通量蛋白设计
生成模型如扩散模型和流匹配在生成可设计且多样化的蛋白骨架方面取得了显著成功。然而，许多现有模型计算成本高昂，生成高质量样本需数百甚至上千次函数评估（NFE），在通常每目标生成10⁴至10⁶个设计的实际设计任务中成为瓶颈。在图像生成中，修正流（ReFlow）能显著降低达到目标质量所需的NFE，但在蛋白骨架生成中的应用研究较少。本文将ReFlow应用于预训练的SE(3)流匹配模型，系统研究其在蛋白生成中的设计选择，涵盖数据准备、训练和推理时间设置。特别地，我们发现：(1) 蛋白域中的ReFlow对耦合生成和退火策略的选择极为敏感；(2) 图像领域有效的设计选择并不直接适用于蛋白生成；(3) 提出了针对蛋白质特性的ReFlow方法改进。
原文摘要 · Abstract (English)
Generative modeling techniques such as Diffusion and Flow Matching have achieved significant successes in generating designable and diverse protein backbones. However, many current models are computationally expensive, requiring hundreds or even thousands of function evaluations (NFEs) to yield samples of acceptable quality, which can become a bottleneck in practical design campaigns that often generate $10^4\ -\ 10^6$ designs per target. In image generation, Rectified Flows (ReFlow) can significantly reduce the required NFEs for a given target quality, but their application in protein backbone generation has been less studied. We apply ReFlow to improve the low NFE performance of pretrained SE(3) flow matching models for protein backbone generation and systematically study ReFlow design choices in the context of protein generation in data curation, training and inference time settings. In particular, we (1) show that ReFlow in the protein domain is particularly sensitive to the choice of coupling generation and annealing, (2) demonstrate how useful design choices for ReFlow in the image domain do not directly translate to better performance on proteins, and (3) make improvements to ReFlow methodology for proteins.
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。