@article {Lin068775, author = {Peijie Lin and Michael Troup and Joshua W. K. Ho}, title = {CIDR: Ultrafast and accurate clustering through imputation for single-cell RNA-Seq data}, elocation-id = {068775}, year = {2016}, doi = {10.1101/068775}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Most existing dimensionality reduction and clustering packages for single-cell RNA-Seq (scRNA-Seq) data deal with dropouts by heavy modelling and computational machinery. Here we introduce CIDR (Clustering through Imputation and Dimensionality Reduction), an ultrafast algorithm which uses a novel yet very simple {\textquoteleft}implicit imputation{\textquoteright} approach to alleviate the impact of dropouts in scRNA-Seq data in a principled manner. Using a range of simulated and real data, we have shown that CIDR outperforms the state-of-the-art methods, namely t-SNE, ZIFA and RaceID, by at least 50\% in terms of clustering accuracy, and typically completes within seconds for processing a dataset of hundreds of cells.CIDR can be downloaded at https://github.org/VCCRI/CIDR.}, URL = {https://www.biorxiv.org/content/early/2016/08/31/068775}, eprint = {https://www.biorxiv.org/content/early/2016/08/31/068775.full.pdf}, journal = {bioRxiv} }