This clustering approach was developed to identify and categorize cell populations within single-cell RNA-seq data. It leverages this subspace structure and learns a cell-to-cell affinity matrix based on notions of subspace similarity. It also faciliates recovery of information on developmental time.
Questions: Contact huanga1@seas.upenn.edu
This repo contains the following:
All code needed to run the algorithm. The main clustering function is found in 'subspaceClustering.m'.
MATLAB v. R2017b (and >)