EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning to estimate sample-specific transcriptional networks for 7,000 tumors

Caleb N Ellington iD, Benjamin J Lengerich, Thomas B K Watkins, Jiekun Yang, Abhinav K Adduri, Sazan Mahbub iD, Hanxi Xiao iD, Manolis Kellis iD, Eric P Xing

Proceedings of the National Academy of Sciences · 27.05.2025 · 122 (21)

DOI: 10.1073/pnas.2411930122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 23.05.2025. Verfasst von Caleb N Ellington und 8 weiteren Autor:innen. Beteiligte Einrichtung: Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213. Hauptthemen laut MEDLINE: Gene Regulatory Networks, Neoplasms, Gene Expression Regulation, Neoplastic. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, HHS | National Institutes of Health (NIH).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cancers are shaped by somatic mutations, microenvironment, and patient background, each altering gene expression and regulation in complex ways, resulting in heterogeneous cellular states and dynamics. Inferring gene regulatory networks (GRNs) from expression data can help characterize this regulation-driven heterogeneity, but network inference requires many statistical samples, limiting GRNs to cluster-level analyses that ignore intracluster heterogeneity. We propose to move beyond coarse analyses of predefined subgroups by using contextualized learning, a multitask learning paradigm that uses multiview contexts including phenotypic, molecular, and environmental information to infer personalized models. With sample-specific contexts, contextualization enables sample-specific models and even generalizes at test time to predict network models for entirely unseen contexts. We unify three network model classes (Correlation, Markov, and Neighborhood Selection) and estimate context-specific GRNs for 7,997 tumors across 25 tumor types, using copy number and driver mutation profiles, tumor microenvironment, and patient demographics as model context. Our generative modeling approach allows us to predict GRNs for unseen tumor types based on a pan-cancer model of how somatic mutations affect gene regulation. Finally, contextualized networks enable GRN-based precision oncology by providing a structured view of expression dynamics at sample-specific resolution, explaining known biomarkers in terms of network-mediated effects and leading to subtypings that improve survival prognosis. We provide a SKLearn-style Python package https://contextualized.ml for learning and analyzing contextualized models, as well as interactive plotting tools for pan-cancer data exploration at https://github.com/cnellington/CancerContextualized .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene Regulatory NetworksNeoplasmsGene Expression Regulation, NeoplasticHumansTumor MicroenvironmentMutationMachine Learning

Stichwörter der Autor:innen

cancerheterogeneitymultitask learningnetworkspersonalized models

Autor:innen und Institutionen

  • Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213.
  • Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139.
  • Broad Institute, Massachusetts Institute of Technology and Harvard University, Cambridge, MA 02142.
  • Cancer Institute, University College London, London WC1E 6DD, United Kingdom.
  • Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260.
  • Machine Learning Department, Mohamed bin Zayed University of Artificial Intelligence, Masdar City SE45 05, Abu Dhabi, United Arab Emirates.

ORCID-Profile: Caleb N Ellington, Sazan Mahbub, Hanxi Xiao, Manolis Kellis

Förderung

  • NIGMS NIH HHS
  • HHS | National Institutes of Health (NIH)

Zitieren

APA

Ellington, C. N., Lengerich, B. J., Watkins, T. B. K., Yang, J., Adduri, A. K., Mahbub, S., Xiao, H., Kellis, M., & Xing, E. P. (2025). Learning to estimate sample-specific transcriptional networks for 7,000 tumors. Proceedings of the National Academy of Sciences, 122(21). https://doi.org/10.1073/pnas.2411930122

Vancouver

Ellington CN, Lengerich BJ, Watkins TBK, Yang J, Adduri AK, Mahbub S, et al. Learning to estimate sample-specific transcriptional networks for 7,000 tumors. Proceedings of the National Academy of Sciences. 2025;122(21). doi:10.1073/pnas.2411930122

BibTeX
@article{Ellington2025,
  author = {Ellington, Caleb N and Lengerich, Benjamin J and Watkins, Thomas B K and Yang, Jiekun and Adduri, Abhinav K and Mahbub, Sazan and Xiao, Hanxi and Kellis, Manolis and Xing, Eric P},
  title = {Learning to estimate sample-specific transcriptional networks for 7,000 tumors},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2025},
  volume = {122},
  number = {21},
  doi = {10.1073/pnas.2411930122}
}
Kostenlos starten →