Decoding heart failure subtypes with neural networks via differential explanation analysis

Abstract Single-cell transcriptomics offers critical insights into the molecular mechanisms of heart failure 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 genes signatures among heart failure types. Machine learning, particularly deep neural networks, 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. In this study, we introduce a novel method to identify differentially explained genes (DXGs) based on importance scores derived from custom-built neural networks. We highlight the superiority of DXGs in identifying heart failure subtypes-specific pathways that provide new insights into different types of heart failure. Offering a robust foundation for future research and therapeutic exploration in expanding transcriptome atlases.