@article {Lun119784, author = {Aaron T. L. Lun and Fernando J. Calero-Nieto and Liora Haim-Vilmovsky and Berthold G{\"o}ttgens and John C. Marioni}, title = {Assessing the reliability of spike-in normalization for analyses of single-cell RNA sequencing data}, elocation-id = {119784}, year = {2017}, doi = {10.1101/119784}, publisher = {Cold Spring Harbor Laboratory}, abstract = {By profiling the transcriptomes of individual cells, single-cell RNA sequencing provides unparalleled resolution to study cellular heterogeneity. However, this comes at the cost of high technical noise, including cell-specific biases in capture efficiency and library generation. One strategy for removing these biases is to add a constant amount of spike-in RNA to each cell, and to scale the observed expression values so that the coverage of spike-in RNA is constant across cells. This approach has previously been criticized as its accuracy depends on the precise addition of spike-in RNA to each sample, and on similarities in behaviour (e.g., capture efficiency) between the spike-in and endogenous transcripts. Here, we perform mixture experiments using two different sets of spike-in RNA to quantify the variance in the amount of spike-in RNA added to each well in a plate-based protocol. We also obtain an upper bound on the variance due to differences in behaviour between the two spike-in sets. We demonstrate that both factors are small contributors to the total technical variance and have only minor effects on downstream analyses such as detection of highly variable genes and clustering. Our results suggest that spike-in normalization is reliable enough for routine use in single-cell RNA sequencing data analyses.}, URL = {https://www.biorxiv.org/content/early/2017/03/23/119784}, eprint = {https://www.biorxiv.org/content/early/2017/03/23/119784.full.pdf}, journal = {bioRxiv} }