scAnnotate: An Automated Cell Type Annotation Tool for Single-Cell RNA-Sequencing Data

An entirely data-driven cell type annotation tools, which requires training data to learn the classifier, but not biological knowledge to make subjective decisions. It consists of three steps: preprocessing training and test data, model fitting on training data, and cell classification on test data. See Xiangling Ji,Danielle Tsao, Kailun Bai, Min Tsao, Li Xing, Xuekui Zhang.(2022)<doi:10.1101/2022.02.19.481159> for more details.

Version: 0.0.3
Depends: R (≥ 4.0.0)
Imports: glmnet, stats, MTPS, Seurat (≥ 4.0.5), harmony
Suggests: knitr, testthat (≥ 3.0.0), rmarkdown
Published: 2022-08-09
Author: Xiangling Ji [aut], Danielle Tsao [aut], Kailun Bai [ctb], Min Tsao [aut], Li Xing [aut], Xuekui Zhang [aut, cre]
Maintainer: Xuekui Zhang <xuekui at uvic.ca>
License: GPL-3
URL: https://doi.org/10.1101/2022.02.19.481159
NeedsCompilation: no
Materials: NEWS
CRAN checks: scAnnotate results

Documentation:

Reference manual: scAnnotate.pdf
Vignettes: introduction

Downloads:

Package source: scAnnotate_0.0.3.tar.gz
Windows binaries: r-devel: scAnnotate_0.0.1.zip, r-release: scAnnotate_0.0.2.zip, r-oldrel: scAnnotate_0.0.2.zip
macOS binaries: r-release (arm64): scAnnotate_0.0.1.tgz, r-oldrel (arm64): scAnnotate_0.0.1.tgz, r-release (x86_64): scAnnotate_0.0.1.tgz, r-oldrel (x86_64): scAnnotate_0.0.1.tgz
Old sources: scAnnotate archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=scAnnotate to link to this page.