GraphVar 2.0: 'Machine Learning' released

GraphVar 2.0: A user-friendly toolbox for machine learning on
functional connectivity measures
Background: We previously presented GraphVar as a user-friendly
MATLAB toolbox for comprehensive graph analyses of functional
brain connectivity. Here we introduce a comprehensive extension of
the toolbox allowing users to seamlessly explore easily customizable
decoding models across functional connectivity measures as
well as additional features.
New Method: GraphVar 2.0 provides machine learning (ML)
model construction, validation and exploration. Machine learning
can be performed across any combination of network measures
and additional variables, allowing for a flexibility in neuroimaging
Results: In addition to previously integrated functionalities, such
as network construction and graph-theoretical analyses of brain
connectivity with a high-speed general linear model (GLM), users
can now perform customizable ML across connectivity matrices,
network metrics and additionally imported variables. The new
extension also provides parametric and nonparametric testing of
classifier and regressor performance, data export, figure generation
and high quality export.
Comparison with existing methods: Compared to other existing
toolboxes, GraphVar 2.0 offers (1) comprehensive customization,
(2) an all-in-one user friendly interface, (3) customizable model
design and manual hyperparameter entry, (4) interactive results
exploration and data export, (5) automated cueing for modelling
multiple outcome variables within the same session, (6) an easy to
follow introductory review.
Conclusions: GraphVar 2.0 allows comprehensive, user-friendly
exploration of encoding (GLM) and decoding (ML) modelling
approaches on functional connectivity measures making big data
neuroscience readily accessible to a broader audience of neuroimaging


Congratulations Johann!

Could you have a short introduction on what kind of ML algorithms you included?

Hi Chao-Gan,

we have included a preprint of the upcoming paper in the GraphVar zip file for download, where we explain everything in detail. This preprint should also be up on within the next 24 hours.
However, here is short passage from the manuscript:
Depending on the outcome variable type (i.e. categorical or continuous), the user may select between building a classification or regression model. Support Vector (SV) or Elastic Net model learning approaches are possible.
GraphVar ML allows users to customize the model validation algorithm using a standard or nested K-fold cross-validation design. The nested cross- validation option offers a 3-step nested cross-validation structure (Whelan 2014) with in-built model selection.
Within GraphVar ML, The SV algorithm is implemented using the established LIBSVM package (Hsu et al. 2003; Chang et Lin 2011) while Elastic Net relies on the widely- used implementation Glmnet (Friedman et al. 2010). Users may select between support vector classification (SVC),  probabilistic support vector classification, support vector Regression (SVR), Elastic Net classification and Elastic Net Regression. Furthermore, the GraphVar ML framework allows a straightforward extension to any other regularization method by an advanced user.
Anastasia Brovkin (on behalf of the GraphVar team)


A pre-print of our new paper for GraphVar 2.0 is now available online:


Anastasia Brovkin (on behalf of the GraphVar team)