Warp: a method for neural network interpretability applied to gene expression profiles

TL;DR

This paper introduces 'warping', a novel method for interpreting neural networks in gene expression analysis, demonstrating its effectiveness in revealing meaningful class-specific information in biological data.

Contribution

The paper presents 'warping', a new approach for neural network interpretability tailored to gene expression data, showing its ability to recover class-specific insights in various datasets.

Findings

Warping effectively recovers meaningful class information.

Works well on both linear and nonlinear datasets.

Potential to enhance neural network interpretability in biology.

Abstract

We show a proof of principle for warping, a method to interpret the inner working of neural networks in the context of gene expression analysis. Warping is an efficient way to gain insight to the inner workings of neural nets and make them more interpretable. We demonstrate the ability of warping to recover meaningful information for a given class on a samplespecific individual basis. We found warping works well in both linearly and nonlinearly separable datasets. These encouraging results show that warping has a potential to be the answer to neural networks interpretability in computational biology.