MARS: discovering novel cell types across heterogeneous single-cell experiments
MARS: discovering novel cell types across heterogeneous single-cell experiments
复制标题
DOI：
10.1038/s41592-020-00979-3
复制
发表时间：
2020-10-19
期刊：
影响因子：
48
通讯作者：
Leskovec, Jure
中科院分区：
文献类型：
--
作者：
Brbic, Maria;Zitnik, Marinka;Leskovec, Jure
MARS使用元学习策略来标注已知的细胞类型，并在单细胞RNA-seq数据集中识别新的细胞类型。尽管已经在细胞类型标注上投入了巨大的努力，但在异质单细胞RNA-seq数据中识别以前未表征的细胞类型仍然是一个挑战。在这里，我们介绍了MARS，这是一种元学习方法，用于识别和注释已知的以及新的细胞类型。MARS通过跨多个数据集传输潜在的细胞表示，克服了细胞类型的异质性。MARS使用深度学习来学习细胞嵌入函数以及细胞嵌入空间中的一组地标。这种方法有一种独特的能力，可以发现以前从未见过的细胞类型，并对尚未注释的实验进行注释。我们将MARS应用于一个大型的小鼠细胞图谱，并展示了它准确识别细胞类型的能力，即使它以前从未见过细胞类型。此外，MARS通过在嵌入空间中以概率方式定义单元类型，自动为新单元类型生成可解释的名称。
MARS uses a meta-learning strategy for annotating known cell types and identifying novel ones across single-cell RNA-seq datasets.Although tremendous effort has been put into cell-type annotation, identification of previously uncharacterized cell types in heterogeneous single-cell RNA-seq data remains a challenge. Here we present MARS, a meta-learning approach for identifying and annotating known as well as new cell types. MARS overcomes the heterogeneity of cell types by transferring latent cell representations across multiple datasets. MARS uses deep learning to learn a cell embedding function as well as a set of landmarks in the cell embedding space. The method has a unique ability to discover cell types that have never been seen before and annotate experiments that are as yet unannotated. We apply MARS to a large mouse cell atlas and show its ability to accurately identify cell types, even when it has never seen them before. Further, MARS automatically generates interpretable names for new cell types by probabilistically defining a cell type in the embedding space.