Department of Thoracic Surgery, Jiangsu Province People's Hospital and the First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China.
State Key Laboratory of Bioelectronics, School of Biological Sciences and Medical Engineering, Southeast University, Nanjing 210096, China.
Genomics Proteomics Bioinformatics. 2020 Aug;18(4):468-480. doi: 10.1016/j.gpb.2019.02.003. Epub 2020 Dec 18.
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.
精准的生物标志物的开发是疾病管理的关键步骤。然而，大多数已发表的生物标志物都是通过有监督的方法从相对较少的样本中得出的。最近无监督机器学习的进展有望利用非常大的数据集来更好地预测疾病生物标志物。去噪自编码器（DA）是一种无监督深度学习算法，是自动编码器技术的随机版本。DA 的原理是通过从损坏的输入中重建干净的输入，迫使自动编码器的隐藏层捕获更稳健的特征。在这里，我们应用 DA 模型来分析来自 13 项已发表的肺癌研究的整合转录组数据，这些研究包含 1916 个人类肺组织样本。使用 DA，我们发现了一个由多个基因组成的肺腺癌（ADC）分子特征。在独立验证队列中，所提出的分子特征被证明是用于肺癌组织亚型的有效分类器。此外，该特征还成功地预测了肺 ADC 的临床结果，这与传统的预后因素无关。更重要的是，与其他已发表的预后基因相比，该特征表现出更高的预后能力。我们的研究表明，在精准医学时代，无监督学习有助于生物标志物的开发。
