Jiang Lindong, Xu Chao, Bai Yuntong, Liu Anqi, Gong Yun, Wang Yu-Ping, Deng Hong-Wen
Tulane Center of Biomedical Informatics and Genomics, School of Medicine, Tulane University, New Orleans, LA, 70112.
Department of Biostatistics and Epidemiology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, 73104.
Res Sq. 2023 Aug 8:rs.3.rs-2486756. doi: 10.21203/rs.3.rs-2486756/v1.
Accurate prognosis for cancer patients can provide critical information for optimizing treatment plans and improving life quality. Combining omics data and demographic/clinical information can offer a more comprehensive view of cancer prognosis than using omics or clinical data alone and can reveal the underlying disease mechanisms at the molecular level. In this study, we developed a novel deep learning framework to extract information from high-dimensional gene expression and miRNA expression data and conduct prognosis prediction for breast cancer and ovarian cancer patients. Our model achieved significantly better prognosis prediction than the conventional Cox Proportional Hazard model and other competitive deep learning approaches in various settings. Moreover, an interpretation approach was applied to tackle the "black-box" nature of deep neural networks and we identified features (i.e., genes, miRNA, demographic/clinical variables) that made important contributions to distinguishing predicted high- and low-risk patients. The identified associations were partially supported by previous studies.
准确预测癌症患者的预后可为优化治疗方案和提高生活质量提供关键信息。与单独使用组学或临床数据相比，整合组学数据和人口统计学/临床信息能更全面地了解癌症预后，并能在分子水平揭示潜在的疾病机制。在本研究中，我们开发了一种新型深度学习框架，用于从高维基因表达和miRNA表达数据中提取信息，并对乳腺癌和卵巢癌患者进行预后预测。在各种情况下，我们的模型在预后预测方面显著优于传统的Cox比例风险模型和其他有竞争力的深度学习方法。此外，我们应用了一种解释方法来解决深度神经网络的“黑箱”性质，并识别出对区分预测的高风险和低风险患者有重要贡献的特征（即基因、miRNA、人口统计学/临床变量）。先前的研究部分支持了所确定的关联。
