scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics.
scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics.
复制标题
scGCN 是一种用于单细胞组学知识转移的图卷积网络算法。
DOI：
10.1038/s41467-021-24172-y
复制
发表时间：
2021-06-22
影响因子：
16.6
通讯作者：
Zhang W
中科院分区：
文献类型：
--
作者：
Song Q;Su J;Zhang W
单细胞组学是文献和公共基因组库中增长最快的基因组学数据类型。利用不断增长的标记数据集存储库，并将标签从现有数据集转移到新生成的数据集，将使单细胞组学数据的探索成为可能。然而，目前的标签转移方法性能有限，主要是由于细胞群体之间的内在异质性和数据集之间的外在差异。在这里，我们提出了一个鲁棒的图形人工智能模型，单细胞图卷积网络（scGCN），以实现跨不同数据集的有效知识转移。通过与其他标记转移方法对30个单细胞组学数据集进行基准测试，scGCN在利用来自不同组织、平台和物种的细胞以及不同分子层的细胞方面始终表现出卓越的准确性。scGCN是作为一个集成工作流作为python软件实现的，该软件可在https://github.com/QSong-github/scGCN上获得。在分析中利用不同数据集的困难限制了快速增长的单细胞组学数据集的意义。在这里，作者提出了scGCN，一个基于图的卷积网络，允许在组学数据集之间有效的知识转移。
Single-cell omics is the fastest-growing type of genomics data in the literature and public genomics repositories. Leveraging the growing repository of labeled datasets and transferring labels from existing datasets to newly generated datasets will empower the exploration of single-cell omics data. However, the current label transfer methods have limited performance, largely due to the intrinsic heterogeneity among cell populations and extrinsic differences between datasets. Here, we present a robust graph artificial intelligence model, single-cell Graph Convolutional Network (scGCN), to achieve effective knowledge transfer across disparate datasets. Through benchmarking with other label transfer methods on a total of 30 single cell omics datasets, scGCN consistently demonstrates superior accuracy on leveraging cells from different tissues, platforms, and species, as well as cells profiled at different molecular layers. scGCN is implemented as an integrated workflow as a python software, which is available at https://github.com/QSong-github/scGCN. Making sense of the rapidly growing single-cell omics datasets available is limited by difficulties in leveraging disparate datasets in analyses. Here, the authors present scGCN, a graph based convolutional network to allow effective knowledge transfer across omics datasets.
登录
查看更多内容
影响因子：
46.9
作者：
Becht, Etienne;McInnes, Leland;Newell, Evan W.
通讯作者：
Newell, Evan W.
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
影响因子：
12.3
作者：
Abdelaal, Tamim;Michielsen, Lieke;Mahfouz, Ahmed
通讯作者：
Mahfouz, Ahmed
影响因子：
48
作者：
Kiselev, Vladimir Yu;Yiu, Andrew;Hemberg, Martin
通讯作者：
Hemberg, Martin
影响因子：
48
作者：
Barkas, Nikolas;Petukhov, Viktor;Kharchenko, Peter V.
通讯作者：
Kharchenko, Peter V.