Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908558368440320 |
|---|---|
| author | Park, Sungjoon Lee, Kyungwook Yim, Soorin Hwang, Doyeong Kim, Dongyun Lee, Soonyoung Dunn, Amy Gatti, Daniel Chesler, Elissa O'Connell, Kristen Kim, Kiyoung |
| author_facet | Park, Sungjoon Lee, Kyungwook Yim, Soorin Hwang, Doyeong Kim, Dongyun Lee, Soonyoung Dunn, Amy Gatti, Daniel Chesler, Elissa O'Connell, Kristen Kim, Kiyoung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20842 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease Park, Sungjoon Lee, Kyungwook Yim, Soorin Hwang, Doyeong Kim, Dongyun Lee, Soonyoung Dunn, Amy Gatti, Daniel Chesler, Elissa O'Connell, Kristen Kim, Kiyoung Machine Learning Artificial Intelligence I.2.1; J.3 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. |
| title | Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease |
| topic | Machine Learning Artificial Intelligence I.2.1; J.3 |
| url | https://arxiv.org/abs/2509.20842 |