Denoising Autoencoder, A Deep Learning Algorithm, Aids the Identification of A Novel Molecular Signature of Lung Adenocarcinoma

作     者：Jun Wang Xueying Xie Junchao Shi Wenjun He Qi Chen Liang Chen Wanjun Gu Tong Zhou Jun Wang;Xueying Xie;Junchao Shi;Wenjun He;Qi Chen;Liang Chen;Wanjun Gu;Tong Zhou

作者机构：Department of Thoracic SurgeryJiangsu Province People’s Hospital and the First Affiliated Hospital of Nanjing Medical UniversityNanjing 210029China State Key Laboratory of BioelectronicsSchool of Biological Sciences and Medical EngineeringSoutheast UniversityNanjing 210096China Department of Physiology and Cell BiologyUniversity of NevadaReno School of MedicineRenoNV 89557USA State Key Lab of Respiratory DiseaseGuangzhou Medical UniversityGuangzhou 510000China 

出 版 物：《Genomics, Proteomics & Bioinformatics》 (基因组蛋白质组与生物信息学报（英文版）)

年 卷 期：2020年第18卷第4期

页      面：468-480页

核心收录：

学科分类：0710[理学-生物学] 1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 08[工学] 081104[工学-模式识别与智能系统] 100214[医学-肿瘤学] 0714[理学-统计学（可授理学、经济学学位）] 0703[理学-化学] 0811[工学-控制科学与工程] 0701[理学-数学] 10[医学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by the National Natural Science Foundation of China(Grant Nos.61372164 to XX,61471112 to WG,and 61571109 to WG) the Key R&D Program of Jiangsu Province,China(Grant No.BE2016002-3 to WG) the Fundamental Research Funds for the Central Universities,China(Grant No.2242017K3DN04 to WG) the Clinical Research Cultivation Program,China(Grant No.2017CX010 to LC) the Social Development Foundation of Jiangsu Province–Clinical Frontier Technology,China(Grant No.BE2018746 to LC) 

主　　题：Denoising autoencoder Unsupervised learning Lung cancer Prognosis Molecular signature 

摘      要：Precise biomarker development is a key step in disease management. However, most of the published biomarkers were derived from a relatively small number of samples with supervised approaches. Recent advances in unsupervised machine learning promise to leverage very large datasets for making better predictions of disease biomarkers. Denoising autoencoder(DA) is one of the unsupervised deep learning algorithms, which is a stochastic version of autoencoder techniques. The principle of DA is to force the hidden layer of autoencoder to capture more robust features by reconstructing a clean input from a corrupted one. Here, a DA model was applied to analyze integrated transcriptomic data from 13 published lung cancer studies, which consisted of 1916 human lung tissue samples. Using DA, we discovered a molecular signature composed of multiple genes for lung adenocarcinoma(ADC). In independent validation cohorts, the proposed molecular signature is proved to be an effective classifier for lung cancer histological subtypes. Also, this signature successfully predicts clinical outcome in lung ADC, which is independent of traditional prognostic factors. More importantly, this signature exhibits a superior prognostic power compared with the other published prognostic genes. Our study suggests that unsupervised learning is helpful for biomarker development in the era of precision medicine.