Imputing DNA Methylation by Transferred Learning Based Neural Network  

作　　者：Xin-Feng Wang Xiang Zhou Jia-Hua Rao Zhu-Jin Zhang Yue-Dong Yang 王新峰;周翔;饶家华;张柱金;杨跃东(School of Computer Science and Engineering,Sun Yat-sen University,Guangzhou 510000,China;Key Laboratory of Machine Intelligence and Advanced Computing of Ministry of Education{Sun Yat-sen University)Guangzhou 510000,China)

机构地区：[1]School of Computer Science and Engineering,Sun Yat-sen University,Guangzhou 510000,China [2]Key Laboratory of Machine Intelligence and Advanced Computing of Ministry of Education(Sun Yat-sen University)Guangzhou 510000,China

出　　处：《Journal of Computer Science & Technology》2022年第2期320-329,共10页计算机科学技术学报（英文版）

基　　金：supported by the National Key Research and Development Program of China under Grant No.2020YFB0204803;the National Natural Science Foundation of China under Grant No.61772566;the Guangdong Key Field Research and Development Plan under Grant Nos.2019B020228001 and 2018B010109006;the Introducing Innovative and Entrepreneurial Teams of Guangdong under Grant No.2016ZT06D211;the Guangzhou Science and Technology Research Plan under Grant No.202007030010.

摘　　要：DNA methylation is one important epigenetic type to play a vital role in many diseases including cancers.With the development of the high-throughput sequencing technology,there is much progress to disclose the relations of DNA methylation with diseases.However,the analyses of DNA methylation data are challenging due to the missing values caused by the limitations of current techniques.While many methods have been developed to impute the missing values,these methods are mostly based on the correlations between individual samples,and thus are limited for the abnormal samples in cancers.In this study,we present a novel transfer learning based neural network to impute missing DNA methylation data,namely the TDimpute-DNAmeth method.The method learns common relations between DNA methylation from pan-cancer samples,and then fine-tunes the learned relations over each specific cancer type for imputing the missing data.Tested on 16 cancer datasets,our method was shown to outperform other commonly-used methods.Further analyses indicated that DNA methylation is related to cancer survival and thus can be used as a biomarker of cancer prognosis.

关 键 词：neural network transfer learning DNA methylation data imputation survival analysis 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]