@article {{\v Z}urauskiene026385, author = {Justina {\v Z}urauskiene and Christopher Yau}, title = {pcaReduce: Hierarchical Clustering of Single Cell Transcriptional Profiles}, elocation-id = {026385}, year = {2015}, doi = {10.1101/026385}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Motivation: Advances in single cell genomics provides a way of routinely generating transcriptomics data at the single cell level. A frequent requirement of single cell expression experiments is the identification of novel patterns of heterogeneity across single cells that might explain complex cellular states or tissue composition. To date, classical statistical analysis tools have being routinely applied to single cell data, but there is considerable scope for the development of novel statistical approaches that are better adapted to the challenges of inferring cellular hierarchies.Results: Here, we present a novel integration of principal components analysis and hierarchical clustering to create a framework for characterising cell state identity. Our methodology uses agglomerative clustering to generate a cell state hierarchy where each cluster branch is associated with a principal component of variation that can be used to differentiate two cellular states. We demonstrate that using real single cell datasets this approach allows for consistent clustering of single cell transcriptional profiles across multiple scales of interpretation.Availability: R implementation of pcaReduce algorithm is available from https://github.com/JustinaZ/pcaReduce}, URL = {https://www.biorxiv.org/content/early/2015/09/08/026385}, eprint = {https://www.biorxiv.org/content/early/2015/09/08/026385.full.pdf}, journal = {bioRxiv} }