Skip to content

Rare cells detection using gap information between minor cluster and neighboring clusters

Notifications You must be signed in to change notification settings

fabotao/GapClust

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GapClust

Detecting rare cells from expression profiles by single cell RNA-seq.

Introduction

GapClust takes advantage of the gap between minor cluster and neighbouring abundant cluster to let rare cells within minor cluster stand out through delicately designed statistics. Meanwhile, GapClust does not struggle to search for rare cell informative genes like most of the competitors, but learns the cluster size as well as rare cells using simple arithmetic calculation.

Installation

Required R modules

R >= 3.4.0

R users can easily install GapClust by running following code in R console.

# Install devtools first if it has not been installed on your R environment. Please try "install.packages("devtools")" in R console.
devtools::install_github("fabotao/GapClust")

R packages prerequisites

Seurat >=  3.1.0
rflann >=1.8.4 (GitHub: YeeJeremy/rflann)
irlba >=2.3.3
e1071 >= 1.7-0.1

Performance evaluation

In terms of rare cell detection, GapClust offers best performance compared with other methods, quantified by F1 score.

As to compuation time and memory utilization, GapClust also displays unrivaled speed and memory efficiency, in comparison with other methods.

Publications

Copyright

This software package is distributed under MIT license.

This work is free to use for academic and research purposes. Please contact maintainer for commercial use of this work.

About

Rare cells detection using gap information between minor cluster and neighboring clusters

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages