@article{Chamberlin01022024,
author = {Chamberlin, John T. and Lee, Younghee and Marth, Gabor T. and Quinlan, Aaron R.}, 
title = {Differences in molecular sampling and data processing explain variation among single-cell and single-nucleus RNA-seq experiments},
volume = {34}, 
number = {2}, 
pages = {179-188}, 
year = {2024}, 
doi = {10.1101/gr.278253.123}, 
abstract ={A mechanistic understanding of the biological and technical factors that impact transcript measurements is essential to designing and analyzing single-cell and single-nucleus RNA sequencing experiments. Nuclei contain the same pre-mRNA population as cells, but they contain a small subset of the mRNAs. Nonetheless, early studies argued that single-nucleus analysis yielded results comparable to cellular samples if pre-mRNA measurements were included. However, typical workflows do not distinguish between pre-mRNA and mRNA when estimating gene expression, and variation in their relative abundances across cell types has received limited attention. These gaps are especially important given that incorporating pre-mRNA has become commonplace for both assays, despite known gene length bias in pre-mRNA capture. Here, we reanalyze public data sets from mouse and human to describe the mechanisms and contrasting effects of mRNA and pre-mRNA sampling on gene expression and marker gene selection in single-cell and single-nucleus RNA-seq. We show that pre-mRNA levels vary considerably among cell types, which mediates the degree of gene length bias and limits the generalizability of a recently published normalization method intended to correct for this bias. As an alternative, we repurpose an existing post hoc gene length–based correction method from conventional RNA-seq gene set enrichment analysis. Finally, we show that inclusion of pre-mRNA in bioinformatic processing can impart a larger effect than assay choice itself, which is pivotal to the effective reuse of existing data. These analyses advance our understanding of the sources of variation in single-cell and single-nucleus RNA-seq experiments and provide useful guidance for future studies.}, 
URL = {http://genome.cshlp.org/content/34/2/179.abstract}, 
eprint = {http://genome.cshlp.org/content/34/2/179.full.pdf+html}, 
journal = {Genome Research} 
}