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

. 2022 Oct 17;50(22):e131. doi: 10.1093/nar/gkac901

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

© The Author(s) 2022. Published by Oxford University Press on behalf of Nucleic Acids Research.

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. — Systematic parameter optimization and integration of DeepST. (A) The ARI pirate graph of nine GNN types, each of which was evaluated on 12 DLPFC slides, respectively. Spatial domain distributions of slides 151673 and 151507 with various networks (SGCConv, ResGatedGraphConv and GCNConv) are displayed, respectively. (B) ARI boxplots of whether spatial data augmentation is used and whether integrating morphological information in DeepST are shown. (C) The ARI pirate graph of reduced dimensions of ST data in DeepST. (D) ARI boxplots comparing five methods for constructing adjacency matrices in DeepST. (E) Histograms of ARI and Silhouette Coefficients (SC) score for four slides (including 151573, 151574, 151575 and 151576) utilizing spatial algorithms, including DeepST, DeepST (without DAN), SEDR and stLearn. (F) UMAP plots of spatial integrated algorithms. They represent batches, recognition spatial domains, and ground truth labels, respectively.