近日，军事医学研究院应晓敏等研究人员合作利用MIDAS，对单细胞多模态数据进行镶嵌式整合和知识转移。该研究于2024年1月23日在线发表于国际一流学术期刊《自然—生物技术》。

研究人员提出了一种深度概率框架，用于单细胞多模态数据的镶嵌式整合和知识转移（MIDAS）。MIDAS通过使用自监督模态配准和信息论潜差法，同时实现了镶嵌数据的降维、估算和批量校正。研究人员通过评估其在三模态和镶嵌式整合任务中的性能，证明了它优于其他19种方法的可靠性。

研究人员还构建了人类外周血单核细胞的单细胞三模态图集，并定制了迁移学习和互惠参考映射方案，以实现从图集到新数据的灵活而准确的知识转移。骨髓镶嵌数据集的镶嵌式整合、拟时序分析和跨组织知识转移应用证明了MIDAS的多功能性和优越性。MIDAS可在https://github.com/labomics/midas处获取。

据悉，整合多种组学技术产生的单细胞数据集对于定义细胞异质性至关重要。镶嵌式整合（不同数据集仅共享部分测量模式）带来了重大挑战，尤其是在模式对齐和批量效应去除方面。

附：英文原文

Title: Mosaic integration and knowledge transfer of single-cell multimodal data with MIDAS

Author: He, Zhen, Hu, Shuofeng, Chen, Yaowen, An, Sijing, Zhou, Jiahao, Liu, Runyan, Shi, Junfeng, Wang, Jing, Dong, Guohua, Shi, Jinhui, Zhao, Jiaxin, Ou-Yang, Le, Zhu, Yuan, Bo, Xiaochen, Ying, Xiaomin

Issue&Volume: 2024-01-23

Abstract: Integrating single-cell datasets produced by multiple omics technologies is essential for defining cellular heterogeneity. Mosaic integration, in which different datasets share only some of the measured modalities, poses major challenges, particularly regarding modality alignment and batch effect removal. Here, we present a deep probabilistic framework for the mosaic integration and knowledge transfer (MIDAS) of single-cell multimodal data. MIDAS simultaneously achieves dimensionality reduction, imputation and batch correction of mosaic data by using self-supervised modality alignment and information-theoretic latent disentanglement. We demonstrate its superiority to 19 other methods and reliability by evaluating its performance in trimodal and mosaic integration tasks. We also constructed a single-cell trimodal atlas of human peripheral blood mononuclear cells and tailored transfer learning and reciprocal reference mapping schemes to enable flexible and accurate knowledge transfer from the atlas to new data. Applications in mosaic integration, pseudotime analysis and cross-tissue knowledge transfer on bone marrow mosaic datasets demonstrate the versatility and superiority of MIDAS. MIDAS is available at https://github.com/labomics/midas.

DOI: 10.1038/s41587-023-02040-y

Source: https://www.nature.com/articles/s41587-023-02040-y