Decoding heart failure subtypes with neural networks via differential explanation analysis

TL;DR

This paper introduces a new method using neural networks and explainable AI to identify genes linked to different types of heart failure, offering insights into their molecular mechanisms.

Contribution

A novel method to identify differentially explained genes (DXGs) using neural networks and XAI for heart failure subtype analysis.

Findings

DXGs outperform traditional methods in identifying heart failure subtype-specific pathways.

The method provides new insights into molecular mechanisms underlying different types of heart failure.

The approach enhances interpretability of neural networks in single-cell transcriptomics.

Abstract

Single-cell transcriptomics offers critical insights into the molecular mechanisms of heart failure (HF) with reduced or preserved ejection fraction. However, understanding these mechanisms is hindered by the growing complexity of single-cell data and the difficulty in unmasking meaningful differential gene signatures among HF types. Machine learning, particularly deep neural networks (NNs), address these challenges by learning transcriptional patterns, reconstructing expression profiles and effectively classifying cells but often lacks interpretability. Recent advances in explainable AI (XAI) offer tools to clarify model decisions. Yet pinpointing differentially regulated genes with these tools remains challenging. We introduce a novel method to identify differentially explained genes (DXGs) based on importance scores derived from custom-built NNs. We highlight the superiority of DXGs in identifying HF subtypes-specific pathways that provide new insights into different types of HF. Offering a robust foundation for future research and therapeutic exploration in expanding transcriptome atlases.

Figures