TY  - JOUR
AU  - Ritter, Michael
AU  - Blume, Christina
AU  - Tang, Yiheng
AU  - Patel, Areeba Jamilkhan
AU  - Patel, Bhuvic
AU  - Berghaus, Natalie
AU  - Kada Benotmane, Jasim
AU  - Kueckelhaus, Jan
AU  - Yabo, Yahaya
AU  - Zhang, Junyi
AU  - Grabis, Elena
AU  - Villa, Giulia
AU  - Zimmer, David Niklas
AU  - Khriesh, Amir
AU  - Sievers, Philipp
AU  - Seferbekova, Zaira
AU  - Hinz, Felix
AU  - Ravi, Vidhya M
AU  - Seiz-Rosenhagen, Marcel
AU  - Ratliff, Miriam
AU  - Herold-Mende, Christel
AU  - Schnell, Oliver
AU  - Beck, Juergen
AU  - Wick, Wolfgang
AU  - von Deimling, Andreas
AU  - Gerstung, Moritz
AU  - Heiland, Dieter Henrik
AU  - Sahm, Felix
TI  - Spatially resolved transcriptomics and graph-based deep learning improve accuracy of routine CNS tumor diagnostics.
JO  - Nature cancer
VL  - 6
IS  - 2
SN  - 2662-1347
CY  - London
PB  - Nature Research
M1  - DKFZ-2025-00257
SP  - 292-306
PY  - 2025
N1  - #EA:B320#LA:B320# / 2025 Feb;6(2):292-306
AB  - The diagnostic landscape of brain tumors integrates comprehensive molecular markers alongside traditional histopathological evaluation. DNA methylation and next-generation sequencing (NGS) have become a cornerstone in central nervous system (CNS) tumor classification. A limiting requirement for NGS and methylation profiling is sufficient DNA quality and quantity, which restrict its feasibility. Here we demonstrate NePSTA (neuropathology spatial transcriptomic analysis) for comprehensive morphological and molecular neuropathological diagnostics from single 5-µm tissue sections. NePSTA uses spatial transcriptomics with graph neural networks for automated histological and molecular evaluations. Trained and evaluated across 130 participants with CNS malignancies and healthy donors across four medical centers, NePSTA predicts tissue histology and methylation-based subclasses with high accuracy. We demonstrate the ability to reconstruct immunohistochemistry and genotype profiling on tissue with minimal requirements, inadequate for conventional molecular diagnostics, demonstrating the potential to enhance tumor subtype identification with implications for fast and precise diagnostic workup.
LB  - PUB:(DE-HGF)16
C6  - pmid:39880907
DO  - DOI:10.1038/s43018-024-00904-z
UR  - https://inrepo02.dkfz.de/record/298356
ER  -