GenDMR: A dynamic multimodal role-swapping network for identifying risk gene phenotypes

2025-06-02

AI Summary

To address the weak expressiveness and frequent suppression of genetic features by dominant imaging modalities in multimodal Alzheimer’s disease (AD) analysis, this paper proposes a genetics–imaging bidirectional collaborative fusion framework. We introduce a novel dynamic primary–auxiliary modality role-switching mechanism and a SNP genomic spatial encoding module, integrated with multi-instance attention and contrastive self-distillation to enable interpretable cross-modal risk quantification and complementary feature refinement. Evaluated on the ADNI dataset, our model achieves state-of-the-art performance. It successfully identifies 12 AD-associated high-risk genes—including the well-established APOE and several novel candidate genes—demonstrating both high predictive accuracy and strong biological interpretability. This work establishes a new paradigm for elucidating AD etiology and enabling precision prediction through synergistic multimodal integration.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent studies have shown that integrating multimodal data fusion techniques for imaging and genetic features is beneficial for the etiological analysis and predictive diagnosis of Alzheimer's disease (AD). However, there are several critical flaws in current deep learning methods. Firstly, there has been insufficient discussion and exploration regarding the selection and encoding of genetic information. Secondly, due to the significantly superior classification value of AD imaging features compared to genetic features, many studies in multimodal fusion emphasize the strengths of imaging features, actively mitigating the influence of weaker features, thereby diminishing the learning of the unique value of genetic features. To address this issue, this study proposes the dynamic multimodal role-swapping network (GenDMR). In GenDMR, we develop a novel approach to encode the spatial organization of single nucleotide polymorphisms (SNPs), enhancing the representation of their genomic context. Additionally, to adaptively quantify the disease risk of SNPs and brain region, we propose a multi-instance attention module to enhance model interpretability. Furthermore, we introduce a dominant modality selection module and a contrastive self-distillation module, combining them to achieve a dynamic teacher-student role exchange mechanism based on dominant and auxiliary modalities for bidirectional co-updating of different modal data. Finally, GenDMR achieves state-of-the-art performance on the ADNI public dataset and visualizes attention to different SNPs, focusing on confirming 12 potential high-risk genes related to AD, including the most classic APOE and recently highlighted significant risk genes. This demonstrates GenDMR's interpretable analytical capability in exploring AD genetic features, providing new insights and perspectives for the development of multimodal data fusion techniques.

Problem

• Improving genetic feature encoding for Alzheimer's disease analysis
• Balancing imaging and genetic feature learning in multimodal fusion
• Identifying high-risk AD genes with interpretable deep learning

Innovation

• Encodes SNP spatial organization for genomic context
• Uses multi-instance attention for disease risk quantification
• Implements dynamic teacher-student role exchange mechanism