EUVIMEDEUVIMED entdecken
Crossref

DLB class : a probabilistic molecular classifier to guide clinical investigation and practice in diffuse large B-cell lymphoma

Björn Chapuy iD, Timothy Wood iD, Chip Stewart iD, Andrew Dunford iD, Kirsty Wienand iD, Sumbul Jawed Khan iD, Nazli Serin iD, Meng Wang iD, Eleonora Calabretta iD, Joji Shimono iD, Samantha Van Seters iD, Sam Wisemann iD und 5 weitere

Blood · 01.05.2025 · 145 (18) · 2041-2055

DOI: 10.1182/blood.2024025652 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Blood, erschienen am 01.05.2025. Verfasst von Björn Chapuy und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA. Hauptthemen laut MEDLINE: Lymphoma, Large B-Cell, Diffuse. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffuse large B-cell lymphoma (DLBCL) is a clinically and molecularly heterogeneous disease. The increasing recognition and targeting of genetically defined DLBCLs highlight the need for robust classification algorithms. We previously characterized recurrent genetic alterations in DLBCL and identified 5 discrete subtypes, clusters 1 to 5 (C1-C5), with unique mechanisms of transformation, immune evasion, candidate treatment targets, and different outcomes after standard first-line therapy. Herein, we validate the C1 to C5 DLBCL taxonomy in an independent data set and use the expanded series of 699 primary DLBCLs to develop a probabilistic molecular classifier and confirm its performance in an independent test set. Using our previously assigned cluster labels as a reference, we systematically compared multiple machine learning models and strategies for input feature dimensionality reduction with a newly developed performance metric that captured the relationship between accuracy and confidence of class assignments. The winning neural network model, DLBclass, assigned all cases in the training/validation and independent test sets with 91% and 89% accuracies, respectively. In the 75% of cases with confidence >0.7, DLBclass assignments were accurate in 97% of the training/validation set and 98% of the test set. DLBclass enables robust prospective classification of single cases for inclusion in genetically guided clinical trials or practice and represents a framework for the development of genomics-based classification methods in other cancers.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lymphoma, Large B-Cell, DiffuseHumansNeural Networks, ComputerMachine LearningMaleFemaleAlgorithms

Autor:innen und Institutionen

  • Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA.
  • Harvard Medical School, Boston, MA.
  • Department of Hematology, Oncology, and Cancer Immunology, Campus Benjamin Franklin, Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
  • German Cancer Consortium, partner site Berlin, a partnership between German Cancer Consortium and Charité-Universitätsmedizin Berlin, Berlin, Germany.
  • Cancer Program, Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA.
  • Department of Biostatistics and Computational Biology, Dana-Farber Cancer Institute, Boston, MA.

ORCID-Profile: Björn Chapuy, Timothy Wood, Chip Stewart, Andrew Dunford, Kirsty Wienand, Sumbul Jawed Khan, Nazli Serin, Meng Wang, Eleonora Calabretta, Joji Shimono, Samantha Van Seters, Sam Wisemann, Saveliy Belkin, David Heimann, Robert Redd, Margaret A Shipp, Gad Getz

Zitieren

APA

Chapuy, B., Wood, T., Stewart, C., Dunford, A., Wienand, K., Khan, S. J., Serin, N., Wang, M., Calabretta, E., Shimono, J., Van Seters, S., Wisemann, S., Belkin, S., Heimann, D., Redd, R., Shipp, M. A., & Getz, G. (2025). DLB class : a probabilistic molecular classifier to guide clinical investigation and practice in diffuse large B-cell lymphoma. Blood, 145(18), 2041-2055. https://doi.org/10.1182/blood.2024025652

Vancouver

Chapuy B, Wood T, Stewart C, Dunford A, Wienand K, Khan SJ, et al. DLB class : a probabilistic molecular classifier to guide clinical investigation and practice in diffuse large B-cell lymphoma. Blood. 2025;145(18):2041-2055. doi:10.1182/blood.2024025652

BibTeX
@article{Chapuy2025,
  author = {Chapuy, Björn and Wood, Timothy and Stewart, Chip and Dunford, Andrew and Wienand, Kirsty and Khan, Sumbul Jawed and Serin, Nazli and Wang, Meng and Calabretta, Eleonora and Shimono, Joji and Van Seters, Samantha and Wisemann, Sam and Belkin, Saveliy and Heimann, David and Redd, Robert and Shipp, Margaret A and Getz, Gad},
  title = {DLB class : a probabilistic molecular classifier to guide clinical investigation and practice in diffuse large B-cell lymphoma},
  journal = {Blood},
  year = {2025},
  volume = {145},
  number = {18},
  pages = {2041--2055},
  doi = {10.1182/blood.2024025652}
}
Kostenlos starten →