Efficient Discovery of Robust Prognostic Biomarkers and Signatures in Solid Tumors

Zaoqu Liu; Jinhai Deng; Hui Xu; Long Liu; Yuyuan Zhang; Yuhao Ba; Zhengyu Zhang; Fuchu He; Linhai Xie

doi:10.1016/j.canlet.2025.217502

Efficient Discovery of Robust Prognostic Biomarkers and Signatures in Solid Tumors

Cancer Lett. 2025 Jan 24:217502. doi: 10.1016/j.canlet.2025.217502. Online ahead of print.

Authors

Zaoqu Liu¹, Jinhai Deng², Hui Xu³, Long Liu⁴, Yuyuan Zhang³, Yuhao Ba³, Zhengyu Zhang⁵, Fuchu He⁶, Linhai Xie⁷

Affiliations

¹ Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences and Peking Union Medical College, 100730, Beijing, China; State Key Laboratory of Medical Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Lifeomics, 102206, Beijing, China; International Academy of Phronesis Medicine (Guangdong), 510320, Guangdong, China.
² Richard Dimbleby Department of Cancer Research, Comprehensive Cancer Centre, Kings College London, London, United Kingdom.
³ Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, 450052, Zhengzhou, Henan, China.
⁴ Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital of Xi'an Jiaotong University, 710061, Xi'an, Shanxi, China.
⁵ Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China. Electronic address: fcczhangzy1@zzu.edu.cn.
⁶ State Key Laboratory of Medical Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Lifeomics, 102206, Beijing, China; International Academy of Phronesis Medicine (Guangdong), 510320, Guangdong, China; Research Unit of Proteomics Dirven Cancer Precision Medicine, Chinese Academy of Medical Sciences, 102206, Beijing, China. Electronic address: hefc@bmi.ac.cn.
⁷ State Key Laboratory of Medical Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Lifeomics, 102206, Beijing, China; International Academy of Phronesis Medicine (Guangdong), 510320, Guangdong, China. Electronic address: xielinhai@ncpsb.org.cn.

PMID: 39864538
DOI: 10.1016/j.canlet.2025.217502

Abstract

Recent advancements in multi-omics and big-data technologies have facilitated the discovery of numerous cancer prognostic biomarkers and gene signatures. However, their clinical application remains limited due to poor reproducibility and insufficient independent validation. Despite the availability of high-quality datasets, achieving reliable biomarker identification across multiple cohorts continues to be a significant challenge. To address these issues, we developed a comprehensive platform, SurvivalML, designed to support the discovery and validation of prognostic biomarkers and gene signatures using large-scale and harmonized data from 21 cancer types. Through SurvivalML, we identified DCLRE1B as a novel prognostic biomarker for hepatocellular carcinoma, with experimental confirmation of its role in promoting tumor progression. Additionally, we developed the Chinese glioblastoma prognostic signature (CGPS) and its simplified version, SCGPS, a three-gene model. Both demonstrated superior predictive performance compared to other glioblastoma signatures in our in-house cohort and five independent Chinese datasets. The SCGPS model was further validated in 109 clinical samples using multiplex immunofluorescence, showing strong consistency with the original CGPS model. Overall, SurvivalML provides a robust platform for the identification and validation of prognostic biomarkers and gene signatures, offering a valuable resource for advancing cancer research and clinical application.

Keywords: Biomarker; Cancer; Machine-learning; Prognosis; Signature.