< Previous         Next >  
Accurate prediction of pan-cancer types using machine learning with minimal number of DNA methylation sites
Wei Ning1,2,3 , Tao Wu1 , Chenxu Wu1 , Shixiang Wang1 , Ziyu Tao1 , Guangshuai Wang1 , Xiangyu Zhao1 , Kaixuan Diao1 , Jinyu Wang1 , Jing Chen1 , Fuxiang Chen4 , Xue-Song Liu1,*
1School of Life Science and Technology, ShanghaiTech University, Shanghai 201203, China
2Shanghai Institute of Biochemistry and Cell Biology, Center for Excellence in Molecular Cell Science, Chinese Academy of Sciences, Shanghai 200031, China
3University of Chinese Academy of Sciences, Chinese Academy of Sciences, Beijing 100049, China
4Department of Clinical Immunology, Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200011, China
*Correspondence to:Xue-Song Liu ,
J Mol Cell Biol, Volume 15, Issue 4, April 2023, mjad023,
Keyword: DNA methylation, MethyDeep, cancer type prediction, deep neural network (DNN), machine learning

DNA methylation analysis has been applied to determine the primary site of cancer; however, robust and accurate prediction of cancer types with a minimum number of sites is still a significant scientific challenge. To build an accurate and robust cancer type prediction tool with a minimum number of DNA methylation sites, we internally benchmarked different DNA methylation site selection and ranking procedures, as well as different classification models. We used The Cancer Genome Atlas dataset (26 cancer types with 8296 samples) to train and test models and used an independent dataset (17 cancer types with 2738 samples) for model validation. A deep neural network model using a combined feature selection procedure (named MethyDeep) can predict 26 cancer types using 30 methylation sites with superior performance compared with the known methods for both primary and metastatic cancers in independent validation datasets. In conclusion, MethyDeep is an accurate and robust cancer type predictor with the minimum number of DNA methylation sites; it could help the cost-effective clarification of cancer of unknown primary patients and the liquid biopsy-based early screening of cancers.