% 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{Yuan:301911,
author = {D. Yuan and R. Jugas and P. Pokorna and J. Sterba and O.
Slaby and S. Schmid and C. Siewert and B. Osberg and D.
Capper$^*$ and S. Halldorsson and E. O. Vik-Mo and P. S.
Zeiner and K. Weber$^*$ and P. N. Harter and C. Thomas and
A. Albers and M. Rechsteiner and R. Reimann and A. Appelt
and U. Schüller and N. Jabareen and S. Mackowiak and N.
Ishaque and R. Eils and S. Lukassen and P. Euskirchen$^*$},
title = {cross{NN} is an explainable framework for cross-platform
{DNA} methylation-based classification of tumors.},
journal = {Nature cancer},
volume = {6},
number = {7},
issn = {2662-1347},
address = {London},
publisher = {Nature Research},
reportid = {DKFZ-2025-01181},
pages = {1283-1294},
year = {2025},
note = {2025 Jul;6(7):1283-1294},
abstract = {DNA methylation-based classification of (brain) tumors has
emerged as a powerful and indispensable diagnostic
technique. Initial implementations used methylation
microarrays for data generation, while most current
classifiers rely on a fixed methylation feature space. This
makes them incompatible with other platforms, especially
different flavors of DNA sequencing. Here, we describe
crossNN, a neural network-based machine learning framework
that can accurately classify tumors using sparse methylomes
obtained on different platforms and with different epigenome
coverage and sequencing depth. It outperforms other deep and
conventional machine learning models regarding accuracy and
computational requirements while still being explainable. We
use crossNN to train a pan-cancer classifier that can
discriminate more than 170 tumor types across all organ
sites. Validation in more than 5,000 tumors profiled on
different platforms, including nanopore and targeted
bisulfite sequencing, demonstrates its robustness and
scalability with $99.1\%$ and $97.8\%$ precision for the
brain tumor and pan-cancer models, respectively.},
cin = {BE01 / FM01},
ddc = {610},
cid = {I:(DE-He78)BE01-20160331 / I:(DE-He78)FM01-20160331},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40481322},
doi = {10.1038/s43018-025-00976-5},
url = {https://inrepo02.dkfz.de/record/301911},
}