https://github.com/brain-to/gecs

https://github.com/brain-to/gecs

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: BRAIN-TO
  • Language: Python
  • Default Branch: main
  • Size: 48.8 KB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

Codes for Generative Embedding (using DCM-based connectivity features) with Clustering Solution (GECS). In this repository, we specifically use P-DCM [1] which is a state-of-the-art DCM framework.

The overall generative embedding process comprises of:

Step 1. Computation of connectivity features for task-fMRI data of several subjects in an iterative manner using the DCM framework(s).

P-DCM was initially developed on Matlab. For S-DCM [2], one may refer to the standard SPM package which involves the code for running S-DCM on task fMRI data.

Alternatively, one may also use the python implementation of both P-DCM and S-DCM which are available in the src/utilities folder in this repository.

Step 2. Obtain the clusters based on the estimated connectivity features.

Once, the connectivity estimates are obtained it is recommended to store them in a pandas dataframe as a '.pt' file with subjects in rows and connectivity between different regions in the columns.

This dataframe is to be used in the src/EC_cluster.py script to obtain the clusters by utilizing k-means and leave-one-out-cross validation strategy.

The Accuracy and Cluster Membership Index (CMI) scores are also computed simultaneously.

References:

``` [1] Havlicek, M., Roebroeck, A., Friston, K., Gardumi, A., Ivanov, D., & Uludag, K. (2015). Physiologically informed dynamic causal modeling of fMRI data. Neuroimage, 122, 355-372.

[2] Friston, K. J., Harrison, L., & Penny, W. (2003). Dynamic causal modelling. Neuroimage, 19(4), 1273-1302. ```

Owner

  • Name: Brain Research in Advanced Imaging and Neuromodeling - Toronto
  • Login: BRAIN-TO
  • Kind: organization

GitHub Events

Total
  • Public event: 1
  • Push event: 3
Last Year
  • Public event: 1
  • Push event: 3

Dependencies

requirements.txt pypi
  • pipinstallnetworkx *