Analysis and visualization of an ensemble of boolean models for biomarker discovery in cancer cell networks.
The package allows to easily load the simulation data results of the DrugLogics software pipeline that is used to predict synergistic drug combinations in cancer cell lines. It has generic functions that can be used to split a boolean model dataset to model groups with regards to the models predictive performance (number of true positive predictions/Matthews correlation coefficient score) or synergy prediction based on a given set of gold standard synergies and find the average activity difference per network node between all model group pairs. Thus, given user-specific thresholds, important nodes (biomarkers) can be accessed in the sense that they make the models predict specific synergies (synergy biomarkers) or have better performance in general (performance biomarkers).
Lastly, if the boolean models have a specific equation form and differ only in their link operator, link operator biomarkers can also be found.
Check the Get Started guide.
For an earlier example usage of this package (version
0.1.1), see this analysis performed on multiple boolean model datasets.
Please note that the emba project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.