中国科学技术大学刘海燕等共同合作，近期取得重要工作进展。他们研究利用独立于预训练结构预测模型的去噪扩散网络重新设计蛋白质。相关研究成果2024年10月9日在线发表于《自然—方法学》杂志上。

据介绍，RFdiffusion是一种基于去噪扩散概率模型的蛋白质结构设计方法，其最近的成功依赖于对RoseTTAFold结构预测网络进行微调，以实现蛋白质骨架去噪。

研究人员开发了SCUBA扩散（SCUBA-D），这是一种新训练的蛋白质骨架去噪扩散概率模型，通过考虑序列表示的共扩散来增强模型正则化和对抗损失，以最小化分布误差中的数据。

在与预训练的基于RoseTTAFold的RFdiffusion在生成实验上可实现的蛋白质结构方面的性能相匹配的同时，SCUBA-D很容易生成具有尚未观察到的整体折叠的蛋白质结构，这些折叠与RoseTTAFold可预测的折叠不同。

SCUBA-D的准确性通过16种设计的蛋白质和一种蛋白质复合物的X射线结构，以及验证设计的血红素结合蛋白和Ras结合蛋白的实验得到了证实。

总之，这一研究表明，通过解决分布误差数据等突出问题，图像或文本的深度生成模型可以有效地扩展到蛋白质结构等复杂的物理对象。

附：英文原文

Title: De novo protein design with a denoising diffusion network independent of pretrained structure prediction models

Author: Liu, Yufeng, Wang, Sheng, Dong, Jixin, Chen, Linghui, Wang, Xinyu, Wang, Lei, Li, Fudong, Wang, Chenchen, Zhang, Jiahai, Wang, Yuzhu, Wei, Si, Chen, Quan, Liu, Haiyan

Issue&Volume: 2024-10-09

Abstract: The recent success of RFdiffusion, a method for protein structure design with a denoising diffusion probabilistic model, has relied on fine-tuning the RoseTTAFold structure prediction network for protein backbone denoising. Here, we introduce SCUBA-diffusion (SCUBA-D), a protein backbone denoising diffusion probabilistic model freshly trained by considering co-diffusion of sequence representation to enhance model regularization and adversarial losses to minimize data-out-of-distribution errors. While matching the performance of the pretrained RoseTTAFold-based RFdiffusion in generating experimentally realizable protein structures, SCUBA-D readily generates protein structures with not-yet-observed overall folds that are different from those predictable with RoseTTAFold. The accuracy of SCUBA-D was confirmed by the X-ray structures of 16 designed proteins and a protein complex, and by experiments validating designed heme-binding proteins and Ras-binding proteins. Our work shows that deep generative models of images or texts can be fruitfully extended to complex physical objects like protein structures by addressing outstanding issues such as the data-out-of-distribution errors.

DOI: 10.1038/s41592-024-02437-w

Source: https://www.nature.com/articles/s41592-024-02437-w