摘要
Cancer is a leading cause of death worldwide,and the identification of biomarkers and subtypes that can predict the long-term survival of cancer patients is essential for their risk stratification,treatment,and prognosis.However,there are currently no standardized tools for exploring cancer biomarkers or subtypes.In this study,we introduced Cancer Biomarker and subtype Profiler(CBioProfiler),a web server and standalone application that includes two pipelines for analyzing cancer biomarkers and subtypes.The cancer biomarker pipeline consists of five modules for identifying and annotating cancer survival-related biomarkers using multiple survival-related machine learning algorithms.The cancer subtype pipeline includes three modules for data preprocessing,subtype identification using multiple unsupervised machine learning methods,and subtype evaluation and validation.CBioProfiler also includes CuratedCancerPrognosisData,a novel R package that integrates reviewed and curated gene expression and clinical data from 268 studies.These studies cover 43 common blood and solid tumors and draw upon 47,686 clinical samples.The web server is available at https://www.cbioprofiler.com/and https://cbioprofiler.znhospital.cn/CBioProfiler/,and the standalone app and source code can be found at https://github.com/liuxiaoping2020/CBioProfiler.
