Home

Deep unsupervised single-cell clustering (DUSC), is a hybrid approach that integrates feature-selection based on a deep learning architecture with a clustering algorithm to find a compressed and informative representation of single-cell transcriptomic data. DUSC is resilient to biological and technical variations in single-cell experiments and is used to generate cell clusters corresponding to cell types and sub-types. We also include a technique to estimate an efficient number of latent features in the deep learning model.