CCA/PLS Toolkit



This is a MATLAB toolkit to incorporate Canonical Correlation Analysis (CCA), Partial Least Squares (PLS) and their different variants to investigate multivariate associations between multiple modalities of data, e.g., brain imaging and behaviour. The toolkit includes various options for CCA/PLS models (e.g., CCA, PLS, regularized CCA, sparse PLS) and analysis frameworks (e.g., statistical framework, machine learning framework). It can also perform Principal Component Analysis (PCA) to reduce the dimensionality of the data before entering them into CCA analysis (PCA-CCA). Depending on the data being analysed the toolkit might need an installed version of the following toolboxes: PALM, SPM12, BrainNet Viewer and AAL2 to work.


News

  • The toolkit was released on the 25th of March 2022.

Contributors

  • Agoston Mihalik – main developer (former at UCL, now at University of Cambridge, UK)
  • Nils Winter (University of Münster, Germany)
  • Fabio Ferreira (former at UCL, now at Imperial College London, UK)
  • James Chapman (UCL, UK)
  • Janaina Mourao-Miranda - Principal Investigator (UCL, UK)
Some of the code used in the toolkit was developed by Joao Monteiro who was a PhD student at UCL (currently a data scientist at Heni). We wish to thank members and collaborators of the Machine Learning & Neuroimaging Laboratory for testing the toolkit and providing invaluable feedback. We would particularly like to acknowledge Eliana Nicolaisen, Cemre Zor, Konstantinos Tsirlis, Taiane Ramos and Richard Nguyen.

Feel free to report any bugs under  cca-pls-toolkit@cs.ucl.ac.uk, however please keep in mind that currently we do not have the resources to provide general user support.


Citations

  • The CCA/PLS toolkit was used in the analyses of the tutorial paper: Mihalik A, Chapman J, Adams RA, Winter N, Ferreira FS, Shawe-Taylor J, Mourao-Miranda J. Canonical Correlation Analysis and Partial Least Squares for identifying brain-behaviour associations: a tutorial and a comparative study. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 2022. Available here.
  • The CCA/PLS toolkit is also available here on Zenodo.

Acknowledgements

The CCA/PLS toolkit was developed at the Machine Learning & Neuroimaging Laboratory, Centre for Medical Imaging Computing, Computer Science Department, University College London, UK. The development of the toolkit was supported by the Wellcome Trust (grant number WT102845/Z/13/Z).


Download

  • The toolkit can be downloaded from here.
  • A detailed documentation of the toolkit can be found here.
  • And finally, a complete demonstration of how to install the toolkit and generate some of the results that are presented in the accompanying tutorial paper (Mihalik et al. 2022) can be found here.

Licence

This project is licensed under the terms of the GNU General Public License v3.0 license.