Enhancing gene regulatory networks inference through hub-based data integration

One of the main research topics in computational biology is Gene Regulatory Network (GRN) reconstruction that refers to inferring the relationships between genes involved in regulating cell conditions in response to internal or external stimuli. To this end, most computational methods use only transcriptional gene expression data to reconstruct gene regulatory network, but recent studies suggest that gene expression data must be integrated with other types of data to obtain more accurate models predicting real relationships between genes. In this study, a diffusion-based method is enhanced to integrate biological data of network types besides structural prior knowledge. The Random Walk with Restart algorithm (RWR) with an emphasis on hub nodes is executed separately on each network, and then jointly optimizes low-dimensional feature vectors for network nodes by diffusion component analysis. Next, these feature vectors are used to infer gene regulatory networks. Fourteen centrality measures are studied for the detection of hub nodes to be used in the RWR algorithm, and the best centrality measure having the greatest effect on the improvement of gene network inference is selected. A case study for the Saccharomyces cerevisiae and E. coli networks shows that using the proposed features in comparison with gene expression data alone results in 0.02 to 0.08 units improvement in Area Under Receiver Characteristic Operator (AUROC) criteria across different gene regulatory network inference methods. Furthermore, the proposed method was applied to the esophageal cancer data to infer its gene regulatory network. The proposed framework substantially improves accuracy and scalability of GRN inference. The fused features and the best centrality measure detected can be used to provide functional insights about genes or proteins in various biological applications. Moreover, it can be served as a general framework for network data and structural data integration and analysis problems in various scientific disciplines including biology.计算生物学的核心研究方向之一为基因调控网络（Gene Regulatory Network, GRN）重构，即推断参与调控细胞响应内外部刺激状态的基因间相互作用关系。现有多数计算方法仅依赖转录组基因表达数据开展基因调控网络重构，但近期研究表明，需将基因表达数据与其他类型生物数据相融合，方可构建更精准的模型以还原基因间的真实关联。本研究对一款基于扩散的方法进行改进，使其能够在结构化先验知识之外，整合多类网络型生物数据。研究针对每个网络单独执行聚焦枢纽节点（hub nodes）的重启随机游走算法（Random Walk with Restart, RWR），并通过扩散分量分析联合优化网络节点的低维特征向量，后续利用所得特征向量完成基因调控网络的推断任务。本研究针对RWR算法所需的枢纽节点检测任务，共评估了14种中心性测度，并筛选出对基因网络推断效果提升最显著的最优中心性测度。针对酿酒酵母（Saccharomyces cerevisiae）与大肠杆菌（E. coli）网络的案例研究表明，相较于仅使用基因表达数据的方案，本研究提出的特征在各类基因调控网络推断方法中，可使受试者工作特征曲线下面积（Area Under Receiver Characteristic Operator, AUROC）指标提升0.02至0.08个单位。此外，本研究将所提方法应用于食管癌数据集，完成了该疾病相关基因调控网络的推断。所提出的框架可显著提升基因调控网络推断的精度与可扩展性。所融合的特征与筛选出的最优中心性测度，可用于为各类生物应用场景中的基因或蛋白质功能解析提供参考依据。此外，该框架还可作为通用框架，应用于包括生物学在内的多学科领域中的网络数据与结构化数据集成及分析相关问题。