DUBStepR is a scalable correlation-based feature selection method for accurately clustering single-cell data
Open Access
- 6 October 2021
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-12
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 theUnderlyingBasis usingStepwiseRegression), 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.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- Gene expression variability in mammalian embryonic stem cells using single cell RNA-seq dataComputational Biology and Chemistry, 2016
- Spatial reconstruction of single-cell gene expression dataNature Biotechnology, 2015
- Novel Insights into the Regulatory Architecture of CD4+ T Cells in Rheumatoid ArthritisPLOS ONE, 2014
- Reconstructing lineage hierarchies of the distal lung epithelium using single-cell RNA-seqNature, 2014
- Functional consequences of platelet binding to T lymphocytes in inflammationJournal of Leukocyte Biology, 2013
- Collection and processing of whole blood for transformation of peripheral blood mononuclear cells and extraction of DNA: the Type 1 Diabetes Genetics ConsortiumClinical Trials, 2010
- Guilt-by-association feature selection: Identifying biomarkers from proteomic profilesJournal of Biomedical Informatics, 2008
- Overlapping of Genes in the Human GenomeInternational Journal of Biomedical Science, 2007
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987