Python-based tutorial on Connectome-based Predictive Modeling (CPM), prepared for Georgetown Methods Lab, December 2019.
This repo contains functional connectivity data for n = 337 subjects in a variety of task conditions from the Human Connectome Project, as well as associated behavioral data. The Jupyter notebook
cpm_tutorial.ipynb demonstrates how to use CPM to predict behavioral measures from whole-brain functional connectivity, with a focus on exploring how rest and different task states differentially predict trait variables.
If you use CPM in your research, please consider citing the following papers:
Finn ES, Shen X, Scheinost D, Rosenberg MD, Huang J, Chun MM, Papademetris X, Constable RT. (2015) Functional connectome fingerprinting: Identifying individuals using patterns of brain connectivity. Nature Neuroscience, 18: 1664–1671. [link]
Shen X, Finn ES, Scheinost D, Rosenberg MD, Chun MM, Papademetris X, Constable RT. (2017). Using connectome-based predictive modeling to predict individual behavior from brain connectivity. Nature Protocols 12: 506-18. [link]