arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.23960q-bio.BMcs.LG
收藏

通过知识引导的表示分解学习蛋白质结构-功能关系

Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition

Shenzhen International Graduate School, Tsinghua University, Shenzhen, China(清华大学深圳国际研究生院);Pengcheng Laboratory, Shenzhen, China(鹏城实验室);School of Electronic and Computer Engineering, Peking University, Shenzhen, China(北京大学电子与计算机工程学院);CAIR, University of Agder, Norway(阿格德大学CAIR);Shanghai Smart Logic Technology Co. Ltd., Shanghai, China(上海智略科技有限公司)

Mingqing Wang, Zhiwei Nie, Athanasios V. Vasilakos, Yonghong He, Zhixiang Ren

AI总结:

提出知识引导的框架ProtDiS,基于信息瓶颈原理分解预训练的蛋白质微环境嵌入,得到更特异、独立和信息高效的结构特征,在12个下游任务上取得一致改进。

摘要:

蛋白质在复杂的三维结构中编码多样功能,然而大多数深度学习表示仍然高度纠缠,掩盖了功能背后的生物物理信号。本文引入ProtDiS,一个知识引导的框架,将预训练的蛋白质微环境嵌入分解为生物学上可解释且任务相关的维度。受信息瓶颈原理启发,ProtDiS学习平衡信息量和压缩的表示,产生更特异、独立和信息高效的结构特征,并在12个下游任务上取得一致改进,在基于结构的分割下提升最大。蛋白质和残基层面的分析进一步表明,ProtDiS能够区分折叠相似但功能不同的蛋白质,并捕捉关键的细粒度生物物理信号。这些发现表明,知识引导的分解为蛋白质结构建模中的潜在空间结构化提供了一种通用且可解释的方法。源代码和实现细节公开于https://github.com/AI-HPC-Research-Team/ProtDiS。

英文摘要:

Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression, yielding structural features that are more specific, independent, and information-efficient, and achieving consistent improvements across twelve downstream tasks, with the largest gains under structure-based splits. Protein- and residue-level analyses further show that ProtDiS differentiates proteins with similar folds but divergent functions and captures fine-grained biophysical signals critical. These findings suggest that knowledge-guided decomposition provides a general and interpretable approach for structuring latent spaces in protein structural modeling. The source code and implementation details are publicly available at https://github.com/AI-HPC-Research-Team/ProtDiS.

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。

↑