scFeatures: Multi-view representations of single-cell and spatial data for disease outcome prediction
scFeatures is a tool that generates multi-view representations of single-cell and spatial data through the construction of a total of 17 feature types belonging to the following six categories.
- cell type proportions
- cell type specific gene expressions
- cell type specific pathway expressions
- cell type specific cell-cell interaction (CCI) scores
- overall aggregated gene expressions
- spatial metrics
Installation
The latest scFeatures can be installed using devtools:
library(devtools)
devtools::install_github("SydneyBioX/scFeatures")
Vignettes
Please see https://sydneybiox.github.io/scFeatures/articles/scFeatures_overview.html.
Reference
Cao, Y., Lin, Y., Patrick, E., Yang, P., & Yang, J. Y. H. (2022). scFeatures: multi-view representations of single-cell and spatial data for disease outcome prediction. In O. Vitek (Ed.), Bioinformatics (Vol. 38, Issue 20, pp. 4745–4753). Oxford University Press (OUP). https://doi.org/10.1093/bioinformatics/btac590