# Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease

arXiv: https://arxiv.org/abs/2509.20842 · HTML: https://mlsanity.com/paper/2509.20842/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 119 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)](https://mlsanity.com/paper/2203.12221/) (2022)
- [Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization](https://mlsanity.com/paper/2206.04496/) (2022)
- [Graph Contrastive Learning for Multi-omics Data](https://mlsanity.com/paper/2301.02242/) (2023)
- [Supervised Multiple Kernel Learning approaches for multi-omics data integration](https://mlsanity.com/paper/2403.18355/) (2024)
- [Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification](https://mlsanity.com/paper/2409.17777/) (2024)
- [SGUQ: Staged Graph Convolution Neural Network for Alzheimer's Disease Diagnosis using Multi-Omics Data](https://mlsanity.com/paper/2410.11046/) (2024)
- [MVKTrans: Multi-View Knowledge Transfer for Robust Multiomics Classification](https://mlsanity.com/paper/2411.08703/) (2024)

## Abstract (arXiv)

Multi-omics data capture complex biomolecular interactions and provide insights into metabolism and disease. However, missing modalities hinder integrative analysis across heterogeneous omics. To address this, we present MOIRA (Multi-Omics Integration with Robustness to Absent modalities), an early integration method enabling robust learning from incomplete omics data via representation alignment and adaptive aggregation. MOIRA leverages all samples, including those with missing modalities, by projecting each omics dataset onto a shared embedding space where a learnable weighting mechanism fuses them. Evaluated on the Religious Order Study and Memory and Aging Project (ROSMAP) dataset for Alzheimer's Disease (AD), MOIRA outperformed existing approaches, and further ablation studies confirmed modality-wise contributions. Feature importance analysis revealed AD-related biomarkers consistent with prior literature, highlighting the biological relevance of our approach.