scBIT: Integrating Single-cell Transcriptomic Data into fMRI-based Prediction for Alzheimer's Disease Diagnosis

2025-02-04

AI Summary

This study addresses the challenge of improving both predictive performance and biological interpretability in multimodal Alzheimer’s disease (AD) diagnosis. We propose the first framework integrating single-nucleus RNA sequencing (snRNA-seq) as an auxiliary modality into fMRI-based prediction, constructing a cell-type-specific brain-region–gene joint graph model. We design a self-explaining graph neural network that automatically identifies discriminative brain-region–gene subgraphs, and introduce a cross-subject, cross-modal alignment strategy grounded in genetic and demographic similarity. Evaluated on the ADNI dataset, our method achieves a 3.39% improvement in binary classification accuracy and a 26.59% gain in five-class classification accuracy over prior multimodal baselines. Importantly, it provides the first systematic, fine-grained characterization of associations between AD-implicated brain regions and gene modules specific to distinct neural cell types. The implementation is publicly available on GitHub and Zenodo.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Brain-Sensing and Analysis

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

Functional MRI (fMRI) and single-cell transcriptomics are pivotal in Alzheimer's disease (AD) research, each providing unique insights into neural function and molecular mechanisms. However, integrating these complementary modalities remains largely unexplored. Here, we introduce scBIT, a novel method for enhancing AD prediction by combining fMRI with single-nucleus RNA (snRNA). scBIT leverages snRNA as an auxiliary modality, significantly improving fMRI-based prediction models and providing comprehensive interpretability. It employs a sampling strategy to segment snRNA data into cell-type-specific gene networks and utilizes a self-explainable graph neural network to extract critical subgraphs. Additionally, we use demographic and genetic similarities to pair snRNA and fMRI data across individuals, enabling robust cross-modal learning. Extensive experiments validate scBIT's effectiveness in revealing intricate brain region-gene associations and enhancing diagnostic prediction accuracy. By advancing brain imaging transcriptomics to the single-cell level, scBIT sheds new light on biomarker discovery in AD research. Experimental results show that incorporating snRNA data into the scBIT model significantly boosts accuracy, improving binary classification by 3.39% and five-class classification by 26.59%. The codes were implemented in Python and have been released on GitHub (https://github.com/77YQ77/scBIT) and Zenodo (https://zenodo.org/records/11599030) with detailed instructions.

Problem

• Integrate single-cell transcriptomics with fMRI
• Enhance Alzheimer's Disease diagnosis accuracy
• Develop cross-modal learning model scBIT

Innovation

• Combines fMRI with single-nucleus RNA data
• Uses graph neural networks for subgraph extraction
• Enhances Alzheimer's diagnostic prediction accuracy