You are here: Home Software TC3


Temporally Constrained Combinatorial Clustering (TC3)

Temporally Constrained Combinatorial Clustering (TC3) is an unsupervised machine learning method that generates cell morphology class labels in live-cell movies. By combining TC3 with Gaussian mixture models (GMM) and hidden Markov models (HMM), the method yields a spatio-temporal model for cell dynamics. The current Matlab implementation uses multivariate feature time series generated by CecogAnalyzer as input. A Python version fully integrated into the CecogAnalyzer will be released soon. Details about TC3 are described in Zhong et al., Nature Methods (2012). - PubMed

Matlab Source Code (Nature Methods Version): Download Zip File

Document Actions