000301911 001__ 301911
000301911 005__ 20250730112830.0
000301911 0247_ $$2doi$$a10.1038/s43018-025-00976-5
000301911 0247_ $$2pmid$$apmid:40481322
000301911 0247_ $$2altmetric$$aaltmetric:177852096
000301911 037__ $$aDKFZ-2025-01181
000301911 041__ $$aEnglish
000301911 082__ $$a610
000301911 1001_ $$aYuan, Dongsheng$$b0
000301911 245__ $$acrossNN is an explainable framework for cross-platform DNA methylation-based classification of tumors.
000301911 260__ $$aLondon$$bNature Research$$c2025
000301911 3367_ $$2DRIVER$$aarticle
000301911 3367_ $$2DataCite$$aOutput Types/Journal article
000301911 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1753867675_25932
000301911 3367_ $$2BibTeX$$aARTICLE
000301911 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000301911 3367_ $$00$$2EndNote$$aJournal Article
000301911 500__ $$a2025 Jul;6(7):1283-1294
000301911 520__ $$aDNA 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.
000301911 536__ $$0G:(DE-HGF)POF4-899$$a899 - ohne Topic (POF4-899)$$cPOF4-899$$fPOF IV$$x0
000301911 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000301911 7001_ $$00000-0003-4675-0985$$aJugas, Robin$$b1
000301911 7001_ $$00000-0003-1037-878X$$aPokorna, Petra$$b2
000301911 7001_ $$aSterba, Jaroslav$$b3
000301911 7001_ $$aSlaby, Ondrej$$b4
000301911 7001_ $$aSchmid, Simone$$b5
000301911 7001_ $$aSiewert, Christin$$b6
000301911 7001_ $$aOsberg, Brendan$$b7
000301911 7001_ $$0P:(DE-He78)51bf9ae9cb5771b30c483e5597ef606c$$aCapper, David$$b8$$udkfz
000301911 7001_ $$aHalldorsson, Skarphedinn$$b9
000301911 7001_ $$00000-0001-8303-4123$$aVik-Mo, Einar O$$b10
000301911 7001_ $$aZeiner, Pia S$$b11
000301911 7001_ $$0P:(DE-He78)832f5277c0186f22e7704f1930239636$$aWeber, Katharina$$b12$$udkfz
000301911 7001_ $$aHarter, Patrick N$$b13
000301911 7001_ $$00000-0002-6642-7774$$aThomas, Christian$$b14
000301911 7001_ $$aAlbers, Anne$$b15
000301911 7001_ $$aRechsteiner, Markus$$b16
000301911 7001_ $$aReimann, Regina$$b17
000301911 7001_ $$aAppelt, Anton$$b18
000301911 7001_ $$00000-0002-8731-1121$$aSchüller, Ulrich$$b19
000301911 7001_ $$aJabareen, Nabil$$b20
000301911 7001_ $$aMackowiak, Sebastian$$b21
000301911 7001_ $$aIshaque, Naveed$$b22
000301911 7001_ $$aEils, Roland$$b23
000301911 7001_ $$00000-0001-7045-6327$$aLukassen, Sören$$b24
000301911 7001_ $$0P:(DE-He78)4c0df1e1834aed3b9f4d879f5370029e$$aEuskirchen, Philipp$$b25$$udkfz
000301911 773__ $$0PERI:(DE-600)3005299-3$$a10.1038/s43018-025-00976-5$$n7$$p1283-1294$$tNature cancer$$v6$$x2662-1347$$y2025
000301911 909CO $$ooai:inrepo02.dkfz.de:301911$$pVDB
000301911 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)51bf9ae9cb5771b30c483e5597ef606c$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000301911 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)832f5277c0186f22e7704f1930239636$$aDeutsches Krebsforschungszentrum$$b12$$kDKFZ
000301911 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4c0df1e1834aed3b9f4d879f5370029e$$aDeutsches Krebsforschungszentrum$$b25$$kDKFZ
000301911 9131_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000301911 9141_ $$y2025
000301911 915__ $$0StatID:(DE-HGF)3003$$2StatID$$aDEAL Nature$$d2024-12-05$$wger
000301911 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT CANCER : 2022$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-05
000301911 915__ $$0StatID:(DE-HGF)9920$$2StatID$$aIF >= 20$$bNAT CANCER : 2022$$d2024-12-05
000301911 9201_ $$0I:(DE-He78)BE01-20160331$$kBE01$$lDKTK Koordinierungsstelle Berlin$$x0
000301911 9201_ $$0I:(DE-He78)FM01-20160331$$kFM01$$lDKTK Koordinierungsstelle Frankfurt$$x1
000301911 980__ $$ajournal
000301911 980__ $$aVDB
000301911 980__ $$aI:(DE-He78)BE01-20160331
000301911 980__ $$aI:(DE-He78)FM01-20160331
000301911 980__ $$aUNRESTRICTED