% 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{Benfatto:298994,
      author       = {S. Benfatto and M. Sill$^*$ and D. Jones$^*$ and S.
                      Pfister$^*$ and F. Sahm$^*$ and A. von Deimling$^*$ and D.
                      Capper$^*$ and V. Hovestadt},
      title        = {{E}xplainable artificial intelligence of {DNA}
                      methylation-based brain tumor diagnostics.},
      journal      = {Nature Communications},
      volume       = {16},
      number       = {1},
      issn         = {2041-1723},
      address      = {[London]},
      publisher    = {Springer Nature},
      reportid     = {DKFZ-2025-00404},
      pages        = {1787},
      year         = {2025},
      abstract     = {We have recently developed a machine learning classifier
                      that enables fast, accurate, and affordable classification
                      of brain tumors based on genome-wide DNA methylation
                      profiles that is widely employed in the clinic.
                      Neuro-oncology research would benefit greatly from
                      understanding the underlying artificial intelligence
                      decision process, which currently remains unclear. Here, we
                      describe an interpretable framework to explain the
                      classifier's decisions. We show that functional genomic
                      regions of various sizes are predominantly employed to
                      distinguish between different tumor classes, ranging from
                      enhancers and CpG islands to large-scale heterochromatic
                      domains. We detect a high degree of genomic redundancy, with
                      many genes distinguishing individual tumor classes,
                      explaining the robustness of the classifier and revealing
                      potential targets for further therapeutic investigation. We
                      anticipate that our resource will build up trust in machine
                      learning in clinical settings, foster biomarker discovery
                      and development of compact point-of-care assays, and enable
                      further epigenome research of brain tumors. Our
                      interpretable framework is accessible to the research
                      community via an interactive web application (
                      https://hovestadtlab.shinyapps.io/shinyMNP/ ).},
      keywords     = {DNA Methylation / Humans / Brain Neoplasms: genetics /
                      Brain Neoplasms: diagnosis / Artificial Intelligence / CpG
                      Islands: genetics / Machine Learning / Biomarkers, Tumor:
                      genetics / Biomarkers, Tumor (NLM Chemicals)},
      cin          = {B062 / HD01 / B360 / B300 / BE01},
      ddc          = {500},
      cid          = {I:(DE-He78)B062-20160331 / I:(DE-He78)HD01-20160331 /
                      I:(DE-He78)B360-20160331 / I:(DE-He78)B300-20160331 /
                      I:(DE-He78)BE01-20160331},
      pnm          = {312 - Funktionelle und strukturelle Genomforschung
                      (POF4-312)},
      pid          = {G:(DE-HGF)POF4-312},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:39979307},
      pmc          = {pmc:PMC11842776},
      doi          = {10.1038/s41467-025-57078-0},
      url          = {https://inrepo02.dkfz.de/record/298994},
}