Liang Xiao, Ma Wentao, Paquet Eric, Viktor Herna, Michalowski Wojtek
Telfer School of Management, University of Ottawa, Ottawa, K1N 6N5, ON, Canada.
Department of Computer Science, University of Toronto, Toronto, M5S 2E4, ON, Canada.
Comput Struct Biotechnol J. 2025 Aug 5;27:3464-3480. doi: 10.1016/j.csbj.2025.07.045. eCollection 2025.
This work introduces the generative fractional diffusion model for protein generation (ProT-GFDM), a novel generative framework that employs fractional stochastic dynamics for protein backbone structure modeling. This approach builds on the continuous-time score-based generative diffusion modeling paradigm, where data are progressively transformed into noise via a stochastic differential equation and reversed to generate structured samples. Unlike classical methods that rely on standard Brownian motion, ProT-GFDM employs a fractional stochastic process with superdiffusive properties to improve the capture of long-range dependencies in protein structures. By integrating fractional dynamics with computationally efficient sampling, the proposed framework advances generative modeling for structured biological data, with implications for protein design and computational drug discovery.
这项工作介绍了用于蛋白质生成的生成式分数扩散模型（ProT-GFDM），这是一种新颖的生成框架，它采用分数随机动力学进行蛋白质主链结构建模。这种方法建立在基于连续时间得分的生成扩散建模范式之上，在该范式中，数据通过一个随机微分方程逐步转化为噪声，然后反向生成结构化样本。与依赖标准布朗运动的经典方法不同，ProT-GFDM采用具有超扩散特性的分数随机过程来改进对蛋白质结构中长程依赖性的捕捉。通过将分数动力学与计算效率高的采样相结合，所提出的框架推动了结构化生物数据的生成建模，对蛋白质设计和计算药物发现具有重要意义。
