Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learning

The SIMLR software identifies similarities between cells across a range of single-cell RNA-seq data, enabling effective dimension reduction, clustering and visualization. We present single-cell interpretation via multikernel learning (SIMLR), an analytic framework and software which learns a similarity measure from single-cell RNA-seq data in order to perform dimension reduction, clustering and visualization. On seven published data sets, we benchmark SIMLR against state-of-the-art methods. We show that SIMLR is scalable and greatly enhances clustering performance while improving the visualization and interpretability of single-cell sequencing data.