ACCENSE Automatic Classification of Cellular Expression by Nonlinear Stochastic Embedding


Cell population classification from high-dimensional single-cell data (Mass Cytometry, scRNA-seq etc).  Developed in collaboration with Karthik Shekhar and Arup Chakraborty (Ragon Institute of M.I .T and Harvard) and Mark M. Davis (HHMI,  Stanford University).

The tool is based on Stochastic Neighborhood Embedding (Van der Maaten, et al 2008) for dimensionality reduction and visualization of single-cell data and cell classification based on a variety of clustering algorithms (K-means, Dbscan etc)

Data is exported as single-cell marker expression tables including cell population assignment to allow down-stream statistical analyses.

A python implementation and stand-alone software is developed and maintained by Yang Chen in our lab.