An ensemble learning method for discovering disease-associated modules from genomic profiling data.
Grand Forest is provided as a comprehensive online analysis workflow. Please select the type of analysis you want to carry out below.
See the accompanied user guide for step-by-step instructions on how to use the online platform. A description of supported file formats can be found here.
Grand Forest is a graph-guided ensemble learning method based on the Random Forest algorithm. It incorporates secondary graph-structed data, modelling the relationship between features, in order discover stable and biologically relevant genetic modules.
Discover connected subnetworks of genes differentially regulated between known or unknown subgroups.
Separate samples into clusters based on differentially expressed pathways.
Cluster patients and compare survival rates to existing classification.
Search for enriched GO terms, pathways or disease terms among the identified genes.
Discover drugs and miRNAs targeting important genes and visualize them as a network.
Evaluate the performance and stability of trained models through cross-validation.
Grand Forest is available as a package for the R programming language. To install the latest development version from GitHub using devtools run:
- Reference manual
If you use Grand Forest in your research, we kindly ask you to cite the following publication:
Citation details to be announced.
If you want to contact us regarding Grand Forest, please contact us in the following order: