# forgeNet: A graph deep neural network model using tree-based ensemble classifiers for feature extraction

## TL;DR

forgeNet is a novel deep learning model that constructs task-specific feature graphs using tree-based ensemble classifiers, improving classification accuracy in high-dimensional omics data without relying on external graph information.

## Contribution

The paper introduces forgeNet, a deep neural network that learns feature graphs in a supervised manner, addressing limitations of existing methods dependent on external graphs.

## Key findings

- High classification accuracy on synthetic datasets
- Effective feature graph learning for real omics data
- Robustness without external graph dependence

## Abstract

A unique challenge in predictive model building for omics data has been the small number of samples $(n)$ versus the large amount of features $(p)$. This "$n\ll p$" property brings difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating external gene network information such as the graph-embedded deep feedforward network (GEDFN) model has been a solution to this issue. However, such methods require an existing feature graph, and potential mis-specification of the feature graph can be harmful on classification and feature selection. To address this limitation and develop a robust classification model without relying on external knowledge, we propose a \underline{for}est \underline{g}raph-\underline{e}mbedded deep feedforward \underline{net}work (forgeNet) model, to integrate the GEDFN architecture with a forest feature graph extractor, so that the feature graph can be learned in a supervised manner and specifically constructed for a given prediction task. To validate the method's capability, we experimented the forgeNet model with both synthetic and real datasets. The resulting high classification accuracy suggests that the method is a valuable addition to sparse deep learning models for omics data.