scSurv: a deep generative model for single-cell survival analysis
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btaf671 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Chikara Mizukoshi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational and Systems Biology, Division of Biological Data Science, Medical Research Laboratory, Institute for Integrated Research,…. Hauptthemen laut MEDLINE: Single-Cell Analysis, Neoplasms, Software. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Transformative Research Areas, Grant-in-Aid for Transformative Research Areas (A), Japan Society for the Promotion of Science (JSPS).
Abstract (Originalsprache)
Motivation Single-cell omics analysis has unveiled the heterogeneity of various cell types within tumors. However, no methodology currently reveals how this heterogeneity influences cancer patient survival at single-cell resolution. Here, we introduce scSurv, combining a Cox proportional hazards model with a deep generative model of single-cell transcriptome, to estimate individual cellular contributions to clinical outcomes. Results The accuracy of scSurv was validated using both simulated and real datasets. This method identifies cells associated with favorable or adverse prognoses and extracts genes correlated with their contribution levels. In melanoma, scSurv reproduces known prognostic macrophage classifications and facilitates hazard mapping through spatial transcriptomics in renal cell carcinoma. We also identified genes consistently associated with prognosis across multiple cancers and demonstrated the applicability of this method to infectious diseases. scSurv is a novel framework for quantifying the heterogeneity of individual cellular effects on clinical outcomes. Availability The implementation of scSurv is available on GitHub (https://github.com/3254c/scSurv) and Zenodo (https://doi.org/10.5281/zenodo.17793054).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computational and Systems Biology, Division of Biological Data Science, Medical Research Laboratory, Institute for Integrated Research, Institute of Science Tokyo, Tokyo 113-8510, Japan.
- Division of Systems Biology, Graduate School of Medicine, Nagoya University, Nagoya, Aichi 466-8550, Japan.
- Nagoya University Hospital, Nagoya, Aichi 466-8560, Japan.
- Laboratory of Computational Life Science, National Cancer Center Research Institute, Tokyo, 104-0045, Japan.
- Department of Emergency and Critical Care Medicine, Graduate School of Medicine, Nagoya University, Nagoya, Aichi 466-8550, Japan.
- Institute of Nano-Life-Systems, Institutes of Innovation for Future Society, Nagoya University, Nagoya, Aichi 464-8601, Japan.
ORCID-Profile: Chikara Mizukoshi, Shuto Hayashi, Teppei Shimamura
Förderung
- Transformative Research Areas
- Grant-in-Aid for Transformative Research Areas (A)
- Japan Society for the Promotion of Science (JSPS)
- Japan Agency for Medical Research and Development (AMED)
- Core Research for Evolutional Science and Technology
- Project Promoting Support for Drug Discovery
- Brain/MINDS Health and Diseases
- Interdisciplinary Cutting-edge Research
Zitieren
APA
Mizukoshi, C., Kojima, Y., Hayashi, S., Abe, K., Kasugai, D., & Shimamura, T. (2026). scSurv: a deep generative model for single-cell survival analysis. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf671
Vancouver
Mizukoshi C, Kojima Y, Hayashi S, Abe K, Kasugai D, Shimamura T. scSurv: a deep generative model for single-cell survival analysis. Bioinformatics. 2026. doi:10.1093/bioinformatics/btaf671
BibTeX
@article{Mizukoshi2026,
author = {Mizukoshi, Chikara and Kojima, Yasuhiro and Hayashi, Shuto and Abe, Ko and Kasugai, Daisuke and Shimamura, Teppei},
title = {scSurv: a deep generative model for single-cell survival analysis},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btaf671}
}
EUVIMED