College of Information Science and Engineering and the Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, China
Auto-generated profile, based on publicly available information
Wenzhuo Shen
College of Information Science and Engineering and the Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, China
Complementary information in multi-omics data are crucial for understanding the pathogenesis of Alzheimer’s Disease (AD). However, existing studies face challenges in addressing the high-level noise and heterogeneity in multi-omics data. This article presents a novel approach that combines large foundation models (LFMs) with soft attention mechanisms to enhance, select, and fuse multi-omics features, thereby improving the performance of disease classification. Specifically, we first propose a mathematical model based on soft attention mechanisms. This model employs multi-head attention (MHA) and self-attention (SA) for feature selection, and uses cross-attention (CA) for feature fusion. Then, a multi-way soft attention fusion framework (MSAFF) with LFMs is proposed. In this approach, biomedical LFMs are used to construct low-noise biomedical features. The multi-way soft attention algorithm implements effective feature selection and fusion described in the mathematical model. Experimental results on the public imaging genetics datasets demonstrate the advanced performances of MSAFF in both disease classification and AD-related pathogeny discrimination. This article provides intelligent support for the diagnosis and pathogenesis research of AD. Our code can be accessed at github.com/fmri123456/MSAFF.
27 February 2025 in IEEE Transactions on Neural Networks and Learning Systems
The risk prediction of Alzheimer’s disease (AD) is crucial for its early prevention and treatment. However, current risk prediction methods face challenges in effectively extracting and fusing multiomics features, particularly overlooking the multilevel evolutionary mechanisms of AD. This article combines biomedical large foundation models with the conditional generative adversarial network (GAN) to mine the evolutionary patterns of AD by considering the regulatory effect of genes on brain lesions. Specifically, we first use biomedical large foundation models to effectively construct high-quality imaging genetic features. Next, a conditional probabilistic state transition mathematical model is constructed to describe AD progression as state transitions of brain regions under genetic regulations. Based on the mathematical model, a conditional probabilistic state transition GAN (CPST-GAN) is proposed. This algorithm can mine the dynamic evolutionary patterns of AD by fusing brain imaging and genetic features to achieve risk prediction of AD. Finally, experiments on the public imaging genetics datasets validate the effectiveness and superiority of CPST-GAN in evolutionary pattern mining and risk prediction of AD. This article not only provides a reliable intelligence algorithm for early intervention of AD but also offers new insights for future research on AD pathogenesis. The code has been published at github.com/fmri123456/CPST-GAN.