改进的SE(3)流匹配基序支架设计
Improved motif-scaffolding with SE(3) flow matching
AI总结：
本研究扩展FrameFlow模型，通过基序摊销和基序引导两种方法实现基序支架设计，在24个生物学基序基准上使可设计且独特的支架数量提升2.5倍。
摘要：
蛋白质设计通常始于对基序所期望功能的了解，基序支架设计旨在围绕该基序构建功能性蛋白质。近年来，生成模型在为一系列基序设计支架方面取得了突破性成功。然而，生成的支架往往缺乏结构多样性，这可能阻碍湿实验验证的成功。在本工作中，我们扩展了FrameFlow——一种用于蛋白质主链生成的SE(3)流匹配模型——通过两种互补方法进行基序支架设计。第一种是基序摊销，即使用数据增强策略，以基序作为输入来训练FrameFlow。第二种是基序引导，即利用FrameFlow的条件分数估计进行支架设计，无需额外训练。在包含24个具有生物学意义的基序的基准测试上，我们展示了我们的方法相比最先进技术，可设计且独特的基序支架数量提高了2.5倍。代码：https://github.com/microsoft/protein-frame-flow
英文摘要：
Protein design often begins with the knowledge of a desired function from a motif which motif-scaffolding aims to construct a functional protein around. Recently, generative models have achieved breakthrough success in designing scaffolds for a range of motifs. However, generated scaffolds tend to lack structural diversity, which can hinder success in wet-lab validation. In this work, we extend FrameFlow, an SE(3) flow matching model for protein backbone generation, to perform motif-scaffolding with two complementary approaches. The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy. The second is motif guidance, which performs scaffolding using an estimate of the conditional score from FrameFlow without additional training. On a benchmark of 24 biologically meaningful motifs, we show our method achieves 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art. Code: https://github.com/microsoft/protein-frame-flow
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。
