EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SurvBoard: standardized benchmarking for multi-omics cancer survival models

David Wissel, Nikita Janakarajan, Aayush Grover, Enrico Toniato, Maria Rodríguez Martínez, Valentina Boeva

Briefings in Bioinformatics · 31.08.2025 · 26 (5)

DOI: 10.1093/bib/bbaf521 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 01.10.2025. Verfasst von David Wissel und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, ETH Zurich, Zurich, Switzerland. Hauptthemen laut MEDLINE: Neoplasms, Benchmarking, Software, Genomics. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SDSC, Swiss Government Excellence Scholarship, Swiss National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-omics data, which include genomic, transcriptomic, epigenetic, and proteomic data, are gaining increasing importance for determining the clinical outcomes of cancer patients. Several recent studies have evaluated various multimodal integration strategies for cancer survival prediction, highlighting the need for standardizing model performance results. Addressing this issue, we introduce SurvBoard, a benchmark framework that standardizes key experimental design choices. SurvBoard enables comparisons between single-cancer and pan-cancer data models and assesses the benefits of using patient data with missing modalities. We also address common pitfalls in preprocessing and validating multi-omics cancer survival models. We apply SurvBoard to several exemplary use cases, further confirming that statistical models tend to outperform deep learning methods, especially for metrics measuring survival function calibration. Moreover, most models exhibit better performance when trained in a pan-cancer context and can benefit from leveraging samples for which data of some omics modalities are missing. We provide a web service for model evaluation and to make our benchmark results easily accessible and viewable: https://www.survboard.science/. All code is available on GitHub: https://github.com/BoevaLab/survboard/. All benchmark outputs are available on Zenodo: 10.5281/zenodo.11066226. A video tutorial on how to use the Survboard leaderboard is available on YouTube at https://youtu.be/HJrdpJP8Vvk.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsBenchmarkingSoftwareGenomicsComputational BiologyHumansProteomicsSurvival AnalysisMultiomics

Stichwörter der Autor:innen

cancerdeep learningmulti-omicssurvival analysis

Autor:innen und Institutionen

  • Department of Computer Science, ETH Zurich, Zurich, Switzerland.
  • Department of Molecular Life Sciences, University of Zurich, Zurich, Switzerland.
  • Swiss Institute of Bioinformatics, Lausanne, Switzerland.
  • IBM Research Europe, Zurich, Switzerland.
  • Yale School of Medicine, New Haven, CT 06510, USA.
  • Université de Paris UMR-S1016 Institut Cochin, Inserm U1016 Paris, France.

Förderung

  • SDSC
  • Swiss Government Excellence Scholarship
  • Swiss National Science Foundation
  • European Union's Horizon 2020
  • European Union’s Horizon 2020

Zitieren

APA

Wissel, D., Janakarajan, N., Grover, A., Toniato, E., Martínez, M. R., & Boeva, V. (2025). SurvBoard: standardized benchmarking for multi-omics cancer survival models. Briefings in Bioinformatics, 26(5). https://doi.org/10.1093/bib/bbaf521

Vancouver

Wissel D, Janakarajan N, Grover A, Toniato E, Martínez MR, Boeva V. SurvBoard: standardized benchmarking for multi-omics cancer survival models. Briefings in Bioinformatics. 2025;26(5). doi:10.1093/bib/bbaf521

BibTeX
@article{Wissel2025,
  author = {Wissel, David and Janakarajan, Nikita and Grover, Aayush and Toniato, Enrico and Martínez, Maria Rodríguez and Boeva, Valentina},
  title = {SurvBoard: standardized benchmarking for multi-omics cancer survival models},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {5},
  doi = {10.1093/bib/bbaf521}
}
Kostenlos starten →