Quantifying uncertainty of predictions from cancer progression models
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag526 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Yanren Linda Hu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department for Statistical Bioinformatics, University of Regensburg, Regensburg 93053, Germany. Hauptthemen laut MEDLINE: Neoplasms, Computational Biology. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Research Foundation, Swiss National Science Foundation, Swiss Cancer League.
Abstract (Originalsprache)
Motivation Cancer progresses through the accumulation of genomic events. Cancer progression models such as Mutual Hazard Networks (MHNs) describe this dynamic, enabling prediction of temporal event positions and patient-specific risks of acquiring mutations. However, current MHN analyses rely on single most likely models and do not quantify the uncertainty inherent to parameter estimation. Assessing forecast stability is essential before using them to anticipate treatment-relevant mutations, adapt targeted therapies, or prioritize monitoring of patients at elevated progression risk. Results We address a key prerequisite for the responsible clinical use of cancer progression models by making MHN-derived predictions uncertainty-aware. We present a Bayesian framework for MHN that uses Markov Chain Monte Carlo to sample from the posterior distributions of model parameters and derived predictions. For practical use we implemented the Random-Walk Metropolis, Metropolis-Adjusted Langevin Algorithm (MALA), and simplified manifold MALA samplers as part of the existing mhn Python package. Only MALA and smMALA were successful in sampling from MHN posteriors, with MALA performing best. While most MHN parameters and predictions showed low posterior variance, a small subset displayed greater variability across the posterior distribution. This differentiation cannot be obtained from a single most likely model, emphasizing the need for uncertainty quantification, especially in clinical contexts. As an illustrative example, posterior sampling identified a subgroup of STK11$-$, KRAS$+$ lung adenocarcinoma patients with a high predicted short-term risk—with low variance across posterior samples—to develop an STK11 mutation. This subgroup exhibited poorer survival under immunotherapy, resembling patterns observed in STK11+ patients. Availability and implementation Our implementation is part of version 1.2.0 of the mhn package (https://github.com/spang-lab/LearnMHN). All analyses including the code to produce all figures in this article can be found under https://github.com/huy29433/MCMC-sampling-for-MHN (https://doi.org/10.5281/zenodo.21160219).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department for Statistical Bioinformatics, University of Regensburg, Regensburg 93053, Germany.
- Department of Physics, University of Regensburg, Regensburg 93040, Germany.
- Department of Biosystems Science and Engineering, ETH Zürich, Basel 4056, Switzerland.
ORCID-Profile: Yanren Linda Hu, Simon Pfahler, Andreas Lösch, Stefan Vocht, Stefan Hansch, Kevin Rupp, Niko Beerenwinkel, Tilo Wettig, Rudolf Schill, Rainer Spang
Förderung
- German Research Foundation
- Swiss National Science Foundation
- Swiss Cancer League
- Free State of Bavaria [Marianne-Plehn-Program
Zitieren
APA
Hu, Y. L., Pfahler, S., Lösch, A., Vocht, S., Hansch, S., Rupp, K., Beerenwinkel, N., Wettig, T., Schill, R., & Spang, R. (2026). Quantifying uncertainty of predictions from cancer progression models. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag526
Vancouver
Hu YL, Pfahler S, Lösch A, Vocht S, Hansch S, Rupp K, et al. Quantifying uncertainty of predictions from cancer progression models. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag526
BibTeX
@article{Hu2026,
author = {Hu, Yanren Linda and Pfahler, Simon and Lösch, Andreas and Vocht, Stefan and Hansch, Stefan and Rupp, Kevin and Beerenwinkel, Niko and Wettig, Tilo and Schill, Rudolf and Spang, Rainer},
title = {Quantifying uncertainty of predictions from cancer progression models},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag526}
}
EUVIMED