Ji Yanrong, Dutta Pratik, Davuluri Ramana
Division of Health and Biomedical Informatics, Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL 60611, USA.
Department of Biomedical Informatics, Stony Brook Cancer Center, Stony Brook Medicine, Stony Brook University, Stony Brook, NY 11794, USA.
Bioinform Adv. 2023 Jun 21;3(1):vbad075. doi: 10.1093/bioadv/vbad075. eCollection 2023.
Molecular subtyping by integrative modeling of multi-omics and clinical data can help the identification of robust and clinically actionable disease subgroups; an essential step in developing precision medicine approaches.
We developed a novel outcome-guided molecular subgrouping framework, called Deep Multi-Omics Integrative Subtyping by Maximizing Correlation (DeepMOIS-MC), for integrative learning from multi-omics data by maximizing correlation between all input -omics views. DeepMOIS-MC consists of two parts: clustering and classification. In the clustering part, the preprocessed high-dimensional multi-omics views are input into two-layer fully connected neural networks. The outputs of individual networks are subjected to Generalized Canonical Correlation Analysis loss to learn the shared representation. Next, the learned representation is filtered by a regression model to select features that are related to a covariate clinical variable, for example, a survival/outcome. The filtered features are used for clustering to determine the optimal cluster assignments. In the classification stage, the original feature matrix of one of the -omics view is scaled and discretized based on equal frequency binning, and then subjected to feature selection using RandomForest. Using these selected features, classification models (for example, XGBoost model) are built to predict the molecular subgroups that were identified at clustering stage. We applied DeepMOIS-MC on lung and liver cancers, using TCGA datasets. In comparative analysis, we found that DeepMOIS-MC outperformed traditional approaches in patient stratification. Finally, we validated the robustness and generalizability of the classification models on independent datasets. We anticipate that the DeepMOIS-MC can be adopted to many multi-omics integrative analyses tasks.
Source codes for PyTorch implementation of DGCCA and other DeepMOIS-MC modules are available at GitHub (https://github.com/duttaprat/DeepMOIS-MC).
Supplementary data are available at online.
通过多组学和临床数据的整合建模进行分子亚型分类有助于识别稳健且具有临床可操作性的疾病亚组，这是开发精准医学方法的关键步骤。
我们开发了一种新的结果导向型分子亚组分类框架，称为最大化相关性的深度多组学整合亚型分类法（DeepMOIS-MC），用于通过最大化所有输入组学视图之间的相关性从多组学数据中进行整合学习。DeepMOIS-MC由两部分组成：聚类和分类。在聚类部分，将预处理后的高维多组学视图输入到两层全连接神经网络中。各个网络的输出经过广义典型相关分析损失以学习共享表示。接下来，通过回归模型对学习到的表示进行过滤，以选择与协变量临床变量（例如生存/结果）相关的特征。过滤后的特征用于聚类以确定最佳聚类分配。在分类阶段，对其中一个组学视图的原始特征矩阵基于等频分箱进行缩放和离散化，然后使用随机森林进行特征选择。使用这些选定的特征构建分类模型（例如XGBoost模型）来预测在聚类阶段识别出的分子亚组。我们使用TCGA数据集将DeepMOIS-MC应用于肺癌和肝癌。在比较分析中，我们发现DeepMOIS-MC在患者分层方面优于传统方法。最后，我们在独立数据集上验证了分类模型的稳健性和通用性。我们预计DeepMOIS-MC可应用于许多多组学整合分析任务。
DGCCA和其他DeepMOIS-MC模块的PyTorch实现的源代码可在GitHub（https://github.com/duttaprat/DeepMOIS-MC）上获取。
补充数据可在网上获取。
