% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{RuzJurado:306179,
      author       = {M. Ruz Jurado and D. Rodriguez Morales and E. Genetzakis
                      and F. B. Ardakani and L. Zanders and A. Fischer and F.
                      Buettner$^*$ and M. H. Schulz and S. Dimmeler and D. John},
      title        = {{D}ecoding heart failure subtypes with neural networks via
                      differential explanation analysis.},
      journal      = {Briefings in bioinformatics},
      volume       = {26},
      number       = {6},
      issn         = {1467-5463},
      address      = {Oxford [u.a.]},
      publisher    = {Oxford University Press},
      reportid     = {DKFZ-2025-02419},
      pages        = {bbaf581},
      year         = {2025},
      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.},
      keywords     = {Heart Failure: genetics / Heart Failure: classification /
                      Heart Failure: metabolism / Humans / Neural Networks,
                      Computer / Transcriptome / Gene Expression Profiling /
                      Machine Learning / Computational Biology: methods / deep
                      neural networks (Other) / differential gene expression
                      (Other) / explainable artificial intelligence (Other) /
                      heart failure subtypes (Other)},
      cin          = {FM01},
      ddc          = {004},
      cid          = {I:(DE-He78)FM01-20160331},
      pnm          = {899 - ohne Topic (POF4-899)},
      pid          = {G:(DE-HGF)POF4-899},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:41222558},
      pmc          = {pmc:PMC12610404},
      doi          = {10.1093/bib/bbaf581},
      url          = {https://inrepo02.dkfz.de/record/306179},
}