CBioExplorer: a web and standalone application for screening, validation, and annotation of cancer survival related biomarkers from molecular level to clinical settings

Abstract

AbstractCancer is one of the main killers threatening human life and health. The exploration of biomarkers that can predict the long-term survival of cancer patients is of great significance for the risk stratification, treatment and prognosis of cancer patients. However, the screening and validation process involving biomarkers is a complicated process. Currently, there are no unified tools for physicians and researchers to explore tumor biomarkers. Herein, we present CBioExplorer (Cancer Biomarker Explorer), a user-friendly web server and standalone application that includes 5 major modules (dimensionality reduction, benchmark experiment, prediction model, clinical annotation; and, biological annotation) and integrated a novel R package CuratedCancerPrognosisData that reviewed, curated and integrated the gene expression data and corresponding clinical data of 47,210 clinical samples from 268 gene expression studies of 43 common blood and solid tumors, for screening, validation, and annotation of cancer survival related biomarkers based on 6 machine learning survival learners from molecular level to clinical settings. The web server is available at http://cbioexplorer.znhospital.cn:8383/CBioExplorer/, and the standalone app and source code of CBioExplorer and CuratedCancerPrognosisData can be found at https://github.com/liuxiaoping2020/CBioExplorer or https://gitee.com/liuxiaoping2020/CBioExplorer.