# Interpretable integration of unpaired multi-omics for Alzheimer’s diagnosis via cross-modal transformer reconstruction

## TL;DR

AE-Trans is a new AI tool that combines gene and epigenetic data to improve Alzheimer’s diagnosis and identify key biological markers.

## Contribution

AE-Trans introduces an interpretable dual-channel Transformer for integrating unpaired multi-omics data in Alzheimer’s diagnosis.

## Key findings

- AE-Trans achieves high accuracy (0.9736) and AUC (0.9910) on prefrontal cortex datasets.
- The model generalizes well to external datasets and identifies biologically relevant biomarkers via explainable AI methods.
- Latent representations from AE-Trans improve classification and enable patient stratification with different prognoses.

## Abstract

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder with limited diagnostic tools and poorly understood molecular underpinnings. Although multi-omics technologies hold promise for early detection, integrating unpaired transcriptomic and epigenetic data remains a major challenge due to modality heterogeneity and small sample sizes. We present AE-Trans, an interpretable dual-channel Transformer framework that aligns RNA and DNA methylation data through cross-modal reconstruction and multi-head attention. AE-Trans achieves superior performance on prefrontal cortex datasets (accuracy = 0.9736, AUC = 0.9910) and demonstrates strong generalizability to external regions temporal cortex cohorts across brain regions (accuracy = 0.7389, AUC = 0.8432). To validate the performance within the same brain region, we tested AE-Trans on an external unpaired multi-omics dataset from the prefrontal cortex. Additionally, we validated the model on a paired multi-omics dataset to assess whether it could achieve good results in real-world scenarios. In the unpaired dataset from the external same brain region, AE-Trans achieved an accuracy of (accuracy = 0.87) and AUC of (AUC = 0.94), while in the real-world paired multi-omics dataset, the accuracy was (accuracy = 0.88) and AUC was (AUC = 0.93). These results demonstrate that AE-Trans not only validates well on external unpaired datasets, but also generalizes effectively to real-world multi-omics paired datasets, highlighting its robustness in practical applications. Through counterfactual integrated gradients, we identified key features associated with immune regulation, hormonal signaling, and neuronal metabolism. These were validated via pathway enrichment and logistic regression (AUC = 0.9749), confirming the biological relevance of model-derived markers. Furthermore, AE-Trans generalized well to two independent RNA datasets, where latent representations not only improved classification (AUCs = 0.92 and 0.89) but also stratified patients into subgroups with significantly different prognoses. These results highlight AE-Trans as a robust and explainable tool for multi-omics integration, supporting early diagnosis, biomarker discovery, and individualized risk prediction in Alzheimer’s disease.

With the increasing adoption of omics technologies in biomedical research, integrating multi-modal data from diverse sources has become crucial for understanding complex diseases and enabling precision diagnosis and treatment. We present AE-Trans, an interpretable dual-channel Transformer framework that integrates unpaired transcriptomic and epigenomic data to enhance Alzheimer’s disease diagnosis. The model demonstrates robust performance across brain regions and datasets, achieving high accuracy on both paired and unpaired multi-omics data. Through explainable AI methods, AE-Trans identifies biologically relevant biomarkers associated with immune and metabolic pathways, while its learned representations enable patient stratification and prognostic prediction. This work offers a powerful tool for early diagnosis, biomarker discovery, and personalized risk assessment in neurodegenerative diseases.