Mapping single-cell data to reference atlases by transfer learning.

Mapping single-cell data to reference atlases by transfer learning.
复制标题

DOI:
10.1038/s41587-021-01001-7
复制
发表时间:
2022-01
影响因子:
46.9
通讯作者:
Theis FJ
Theis FJ
中科院分区:
工程技术1区
文献类型:
--
作者:
Lotfollahi M;Naghipourfar M;Luecken MD;Khajavi M;Büttner M;Wagenstetter M;Avsec Ž;Gayoso A;Yosef N;Interlandi M;Rybakov S;Misharin AV;Theis FJ

文献摘要

参考文献

被引文献

相似文献

现在常规生成大型单细胞图谱,作为小规模研究分析的参考。然而,从参考数据中学习由于数据集之间的批量效应、有限的计算资源可用性和对原始数据的共享限制而变得复杂。在这里,我们介绍了一种深度学习策略,用于在称为单细胞架构手术(scArches)的参考之上映射查询数据集。scArches使用迁移学习和参数优化来实现高效,分散,迭代的参考构建和新数据集与现有参考的上下文化,而无需共享原始数据。使用的例子从小鼠大脑,胰腺,免疫和整个有机体的图集,我们表明,scArches保留生物状态信息,同时消除批量效应,尽管使用四个数量级的参数比从头整合。scArches可推广到多模态参考标测,允许对缺失模态进行插补。最后,scArches在映射到健康参考时保留了2019冠状病毒病(COVID-19)疾病变异,从而能够发现疾病特异性细胞状态。scArches将通过实现参考地图集的迭代构建、更新、共享和有效使用来促进合作项目。单细胞数据很容易使用scArches与细胞图谱集成。
Large single-cell atlases are now routinely generated to serve as references for analysis of smaller-scale studies. Yet learning from reference data is complicated by batch effects between datasets, limited availability of computational resources and sharing restrictions on raw data. Here we introduce a deep learning strategy for mapping query datasets on top of a reference called single-cell architectural surgery (scArches). scArches uses transfer learning and parameter optimization to enable efficient, decentralized, iterative reference building and contextualization of new datasets with existing references without sharing raw data. Using examples from mouse brain, pancreas, immune and whole-organism atlases, we show that scArches preserves biological state information while removing batch effects, despite using four orders of magnitude fewer parameters than de novo integration. scArches generalizes to multimodal reference mapping, allowing imputation of missing modalities. Finally, scArches retains coronavirus disease 2019 (COVID-19) disease variation when mapping to a healthy reference, enabling the discovery of disease-specific cell states. scArches will facilitate collaborative projects by enabling iterative construction, updating, sharing and efficient use of reference atlases. Single-cell data are readily integrated with cell atlases using scArches.
DOI: 10.1016/j.cels.2016.08.011
发表时间: 2016-10-26
期刊: Cell systems
影响因子: 9.3
作者:
Baron M;Veres A;Wolock SL;Faust AL;Gaujoux R;Vetere A;Ryu JH;Wagner BK;Shen-Orr SS;Klein AM;Melton DA;Yanai I
通讯作者: Yanai I
DOI: 10.1242/dev.173849
发表时间: 2019-06-01
期刊: DEVELOPMENT
影响因子: 4.6
作者:
Bastidas-Ponce, Aimee;Tritschler, Sophie;Bakhti, Mostafa
通讯作者: Bakhti, Mostafa
DOI: 10.12688/f1000research.16613.1
发表时间: 2018-01-01
期刊: F1000Research
影响因子: --
作者:
Andrews, Tallulah S;Hemberg, Martin
通讯作者: Hemberg, Martin
DOI: 10.1186/s13059-019-1795-z
发表时间: 2019-09-09
期刊: GENOME BIOLOGY
影响因子: 12.3
作者:
Abdelaal, Tamim;Michielsen, Lieke;Mahfouz, Ahmed
通讯作者: Mahfouz, Ahmed
DOI: 10.1038/s41592-019-0466-z
发表时间: 2019-08-01
期刊: NATURE METHODS
影响因子: 48
作者:
Barkas, Nikolas;Petukhov, Viktor;Kharchenko, Peter V.
通讯作者: Kharchenko, Peter V.