Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease
机器学习
2025-09-26 v1 人工智能
摘要
Multi-omics 数据捕获复杂的生物分子相互作用,提供关于代谢和疾病的见解。然而,缺失的模态阻碍了跨异构 omics 的集成分析。为此,我们提出 MOIRA(Multi-Omics Integration with Robustness to Absent modalities),一种 early 集成方法,通过表示对齐和自适应聚合实现对不完整 omics 数据的稳健学习。MOIRA 利用所有样本(包括缺失模态的样本)将每个 omics 数据集投影到共享嵌入空间,其中包含可学习的加权机制用于融合。我们在 Religious Order Study and Memory and Aging Project(ROSMAP)数据集上评估了 MOIRA 用于阿尔茨海默病(AD)的预测,MOIRA 在已有方法上取得优异成绩,进一步的消除实验确认了各模态的贡献。特征重要性分析揭示了与先前文献一致的 AD 相关生物标志物,凸显了我们方法的生物学相关性。
引用
@article{arxiv.2509.20842,
title = {Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer's Disease},
author = {Sungjoon Park and Kyungwook Lee and Soorin Yim and Doyeong Hwang and Dongyun Kim and Soonyoung Lee and Amy Dunn and Daniel Gatti and Elissa Chesler and Kristen O'Connell and Kiyoung Kim},
journal= {arXiv preprint arXiv:2509.20842},
year = {2025}
}