Denoising Autoencoder, A Deep Learning Algorithm, Aids the Identification of A Novel Molecular Signa

• 作 者: Jun Wang Xueying Xie Junchao Shi Wenjun He Qi Chen Liang Chen Wanjun Gu Tong Zhou
• 机 构: Department of Thoracic Surgery,Jiangsu Province People’s Hospital and the First Affiliated Hospital
• 出 处: 基因组蛋白质组与生物信息学报（英文版）
• 发表日期: 2020年4期
• 关键词: Denoising autoencoder Unsupervised learning Lung cancer Prognosis Molecular sign

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 data-sets 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 inte-grated 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 suc-cessfully predicts clinical outcome in lung ADC, which is independent of traditional prognostic fac-tors. 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 bio-marker development in the era of precision medicine.