Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2021 Oct 6;598(7879):103–110. doi: 10.1038/s41586-021-03500-8

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2021

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Extended Data Fig. 8 — a, Heat map showing replicability scores (MetaNeighbor AUROC) at the subclass level of the independent clusterings of seven RNA-seq datasets. High AUROC indicates that the cell-type labels in one dataset can be reliably predicted based on the nearest neighbours of those cells in another dataset, together with the independent cluster analysis of that dataset. b, Scheme for within-dataset and across-dataset cross-validation. c, d Within-dataset cross-validation analysis for each dataset, either using the full set of cells (c) or using a random sample of 5,000 cells (d). In each plot, the black curve shows training error, while the coloured U-shaped curve shows the test set error, with a minimum at the cluster resolution that balances over-fitting and under-fitting. The shaded region shows the s.e.m. based on cross-validation with n = 5 data partitions. e, Transcriptomic platform consistency is assessed by cross-dataset cluster stability analysis (Conos³⁷).