Please use this identifier to cite or link to this item: https://doi.org/10.1038/s41467-021-26085-2
Title: DUBStepR is a scalable correlation-based feature selection method for accurately clustering single-cell data
Authors: Ranjan, Bobby
Sun, Wenjie
Park, Jinyu
Mishra, Kunal
Schmidt, Florian
Xie, Ronald
Alipour, Fatemeh
Singhal, Vipul
Joanito, Ignasius
Honardoost, Mohammad Amin
Yong, Jacy Mei Yun
Koh, Ee Tzun
Leong, Khai Pang
Rayan, Nirmala Arul
Lim, Michelle Gek Liang
Prabhakar, Shyam
Issue Date: 6-Oct-2021
Publisher: Nature Research
Citation: Ranjan, Bobby, Sun, Wenjie, Park, Jinyu, Mishra, Kunal, Schmidt, Florian, Xie, Ronald, Alipour, Fatemeh, Singhal, Vipul, Joanito, Ignasius, Honardoost, Mohammad Amin, Yong, Jacy Mei Yun, Koh, Ee Tzun, Leong, Khai Pang, Rayan, Nirmala Arul, Lim, Michelle Gek Liang, Prabhakar, Shyam (2021-10-06). DUBStepR is a scalable correlation-based feature selection method for accurately clustering single-cell data. Nature Communications 12 (1) : 5849. ScholarBank@NUS Repository. https://doi.org/10.1038/s41467-021-26085-2
Rights: Attribution 4.0 International
Abstract: Feature selection (marker gene selection) is widely believed to improve clustering accuracy, and is thus a key component of single cell clustering pipelines. Existing feature selection methods perform inconsistently across datasets, occasionally even resulting in poorer clustering accuracy than without feature selection. Moreover, existing methods ignore information contained in gene-gene correlations. Here, we introduce DUBStepR (Determining the Underlying Basis using Stepwise Regression), a feature selection algorithm that leverages gene-gene correlations with a novel measure of inhomogeneity in feature space, termed the Density Index (DI). Despite selecting a relatively small number of genes, DUBStepR substantially outperformed existing single-cell feature selection methods across diverse clustering benchmarks. Additionally, DUBStepR was the only method to robustly deconvolve T and NK heterogeneity by identifying disease-associated common and rare cell types and subtypes in PBMCs from rheumatoid arthritis patients. DUBStepR is scalable to over a million cells, and can be straightforwardly applied to other data types such as single-cell ATAC-seq. We propose DUBStepR as a general-purpose feature selection solution for accurately clustering single-cell data. © 2021, The Author(s).
Source Title: Nature Communications
URI: https://scholarbank.nus.edu.sg/handle/10635/233484
ISSN: 2041-1723
DOI: 10.1038/s41467-021-26085-2
Rights: Attribution 4.0 International
Appears in Collections:Students Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1038_s41467-021-26085-2.pdf3.19 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

3
checked on Oct 26, 2022

Page view(s)

1
checked on Nov 17, 2022

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons