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

. 2024 Dec 4;6(4):lqae166. doi: 10.1093/nargab/lqae166

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

© The Author(s) 2024. Published by Oxford University Press on behalf of NAR Genomics and Bioinformatics.

This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.

PMC Copyright notice

Figure 3. — Starting from the remaining cells in , the unsupervised block constructs a k-Nearest Neighbors (kNN) graph, where edges are created between samples that are among the k-nearest neighbors of each other. To exploit the local neighborhoods and cell-to-cell similarities, the kNN graph is fed to a graph encoder model, Deep Graph Infomax (DGI) in our case, to learn node representations in an unsupervised manner. Using the latent representations learned from DGI, a Dirichlet Process Mixture Model is used to automatically infer the number of novel classes of cell types and perform clustering.

Inline graphic — Starting from the remaining cells in , the unsupervised block constructs a k-Nearest Neighbors (kNN) graph, where edges are created between samples that are among the k-nearest neighbors of each other. To exploit the local neighborhoods and cell-to-cell similarities, the kNN graph is fed to a graph encoder model, Deep Graph Infomax (DGI) in our case, to learn node representations in an unsupervised manner. Using the latent representations learned from DGI, a Dirichlet Process Mixture Model is used to automatically infer the number of novel classes of cell types and perform clustering.