A New Deep Learning and XAI-Based Algorithm for Features Selection in Genomics

TL;DR

This paper introduces a novel deep learning and explainability-based algorithm for feature selection in genomics, enhancing disease diagnosis and prognosis by identifying key genes from large-scale gene expression data.

Contribution

It presents a new algorithm combining autoencoders and XAI scores for effective feature selection in genomic data, improving interpretability and medical relevance.

Findings

Successfully identified meaningful genes in leukemia data

Demonstrated effectiveness in gene selection for medical insights

Enhanced interpretability of gene expression analysis

Abstract

In the field of functional genomics, the analysis of gene expression profiles through Machine and Deep Learning is increasingly providing meaningful insight into a number of diseases. The paper proposes a novel algorithm to perform Feature Selection on genomic-scale data, which exploits the reconstruction capabilities of autoencoders and an ad-hoc defined Explainable Artificial Intelligence-based score in order to select the most informative genes for diagnosis, prognosis, and precision medicine. Results of the application on a Chronic Lymphocytic Leukemia dataset evidence the effectiveness of the algorithm, by identifying and suggesting a set of meaningful genes for further medical investigation.