Required! Make sure to install Statistical Pattern Recognition Toolbox for Matlab.

CellClassifier was developed to enable cell biologists to apply supervised machine learning in their image-based experiments for the automated classification of single-cell phenotypes. The main features are:

  • An intuitive and easy-to-use graphical user interface developed in MatLab to upload and visualize microscopy images. CellClassifier displays each original image interactively, so that each cell is recognized and made ‘clickable’.
  • Three methods of supervised machine learning: Support Vector Machines (SVM), including multiclass SVMs, multilinear perceptrons, and k-nearest neighbors. Developers can easily add their own methods.
  • Possibility to display fractions of correctly and incorrectly classified cells during the course of training in order to evaluate the classification performance and its improvement through training iterations.
  • Export of classification results at the single-cell level to MatLab-readable files and at the population level to standard spreadsheet programs.



The user interface of CellClassifier. Cell and nucleus segmentation outlines (white lines) and single-cell class annotations (numbers) are shown. Moving the mouse over each cell centroid (white dot) and right-clicking allows manual classification or correction of automatically classified cells. Cells shown are HeLa cells stained with DAPI (blue) to visualize the nucleus and with an antibody against PolyA-binding protein (PABP) (red) to visualise RNA granules.


Publications in which CellClassifier was used:

  1. Wippich, F. et al. Dual Specificity Kinase DYRK3 Couples Stress Granule Condensation/Dissolution to mTORC1 Signaling. Cell 152, 791–805 (2013)
  2. Mercer, J. et al. RNAi Screening Reveals Proteasome- and Cullin3-Dependent Stages in Vaccinia Virus Infection. Cell Reports 2, 1036–1047 (2012)
  3. Snijder, B. et al. Single-cell analysis of population context advances RNAi screening at multiple levels. Molecular Systems Biology 8, (2012)
  4. Misselwitz, B. et al. RNAi screen of Salmonella invasion shows role of COPI in membrane targeting of cholesterol and Cdc42. Molecular Systems Biology 7, 474 (2011)
  5. Rämö, P., Sacher, R., Snijder, B., Begemann, B. & Pelkmans, L. CellClassifier: supervised learning of cellular phenotypes. Bioinformatics 25, 3028–3030 (2009)
  6. Snijder, B. et al. Population context determines cell-to-cell variability in endocytosis and virus infection. Nature 461, 520–523 (2009)