crossNN is an explainable framework for cross-platform DNA methylation-based classification of tumors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F65269705%3A_____%2F25%3A00082139" target="_blank" >RIV/65269705:_____/25:00082139 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216224:14110/25:00141527

Výsledek na webu

<a href="https://www.nature.com/articles/s43018-025-00976-5" target="_blank" >https://www.nature.com/articles/s43018-025-00976-5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1038/s43018-025-00976-5" target="_blank" >10.1038/s43018-025-00976-5</a>

Jazyk výsledku

angličtina

Název v původním jazyce

crossNN is an explainable framework for cross-platform DNA methylation-based classification of tumors

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

crossNN is an explainable framework for cross-platform DNA methylation-based classification of tumors

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

30204 - Oncology

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Nature Cancer

ISSN

2662-1347

e-ISSN

2662-1347

Svazek periodika

6

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

12

Strana od-do

1283-1294

Kód UT WoS článku

001503296700001

EID výsledku v databázi Scopus

2-s2.0-105007361578