MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction.
MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction.
复制标题
用于 miRNA 疾病关联预测的 MDHGI 矩阵分解和异质图推理
DOI：
10.1371/journal.pcbi.1006418
复制
发表时间：
2018-08
影响因子：
4.3
通讯作者：
Huang L
中科院分区：
文献类型：
--
作者：
Chen X;Yin J;Qu J;Huang L
近年来，越来越多的生物学研究和科学实验证明microRNA（miRNA）影响着人类复杂疾病的发生发展。发现miRNA与疾病的关联在设计疾病的诊断和治疗工具方面发挥着越来越重要的作用。然而，由于通过实验方法发现关联是昂贵和耗时的，因此需要新颖且有效的关联预测计算方法。在这项研究中，我们开发了一个用于miRNA-疾病关联预测的矩阵分解和异构图推理的计算模型（MDHGI），通过整合通过稀疏学习方法从矩阵分解获得的预测关联概率，miRNA功能相似性，疾病语义相似性，以及疾病和miRNAs的高斯相互作用谱核相似性到异质网络中。与以往基于异构网络的计算模型相比，该模型充分利用了异构网络构建前的矩阵分解，从而提高了预测精度。MDHGI在全局和局部留一交叉验证中分别获得AUC为0.8945和0.8240。此外，在5倍交叉验证中，AUC为0.8794+/-0.0021证实了其预测性能的稳定性。此外，为了进一步评估模型的准确性，我们将MDHGI应用于三种不同类型的病例研究中的四种重要的人类癌症。在第一种类型中，前50个预测的miRNAs中有98%（食管癌）和98%（淋巴瘤）已被两个数据库（dbDEMC和miR 2Disease）中的至少一个或PubMed中的至少一个实验文献证实。在第二种类型的病例研究中，有所不同的是，我们在对肺肿瘤实施MDHGI之前删除了所有已知的miRNA与肺肿瘤之间的关联。因此，100%（肺肿瘤）的前50个相关miRNA已被三个数据库（dbDEMC，miR 2Disease和HMDD V2.0）中的至少一个或PubMed中的至少一个实验文献索引。此外，我们还在HMDD V1.0数据库上测试了我们的预测方法，以证明MDHGI对不同数据集的适用性。结果显示，在与乳腺肿瘤相关的前50个miRNAs中，有50个被HMDD V2. 0、dbDEMC和miR 2Disease三个数据库中的至少一个或至少一个实验文献验证。明确miRNA与疾病的相关性有助于深入了解疾病的分子机制和发病机制，有助于疾病诊断和治疗工具的开发。与传统的实验方法相比，计算模型可以帮助实验者减少金钱和时间的成本。为了通过计算预测潜在的miRNA-疾病关联，我们通过将稀疏学习方法与异构图推理方法相结合来开发MDHGI。在不同的数据库上进行了MDHGI实验，实验结果表明，MDHGI在留一交叉验证和5折交叉验证方面都优于以往的方法。此外，我们还进行了三种不同类型的四个重要的人类复杂疾病的案例研究，以进一步证明MDHGI的预测精度。因此，在这四种疾病的前50个候选miRNAs中，分别有98%，98%，100%和100%被PubMed的不同数据库或实验文献证实。因此，可以得出结论，MDHGI可以做出可靠的预测，并应作为预测潜在miRNA-疾病关联的有效工具。
Recently, a growing number of biological research and scientific experiments have demonstrated that microRNA (miRNA) affects the development of human complex diseases. Discovering miRNA-disease associations plays an increasingly vital role in devising diagnostic and therapeutic tools for diseases. However, since uncovering associations via experimental methods is expensive and time-consuming, novel and effective computational methods for association prediction are in demand. In this study, we developed a computational model of Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction (MDHGI) to discover new miRNA-disease associations by integrating the predicted association probability obtained from matrix decomposition through sparse learning method, the miRNA functional similarity, the disease semantic similarity, and the Gaussian interaction profile kernel similarity for diseases and miRNAs into a heterogeneous network. Compared with previous computational models based on heterogeneous networks, our model took full advantage of matrix decomposition before the construction of heterogeneous network, thereby improving the prediction accuracy. MDHGI obtained AUCs of 0.8945 and 0.8240 in the global and the local leave-one-out cross validation, respectively. Moreover, the AUC of 0.8794+/-0.0021 in 5-fold cross validation confirmed its stability of predictive performance. In addition, to further evaluate the model's accuracy, we applied MDHGI to four important human cancers in three different kinds of case studies. In the first type, 98% (Esophageal Neoplasms) and 98% (Lymphoma) of top 50 predicted miRNAs have been confirmed by at least one of the two databases (dbDEMC and miR2Disease) or at least one experimental literature in PubMed. In the second type of case study, what made a difference was that we removed all known associations between the miRNAs and Lung Neoplasms before implementing MDHGI on Lung Neoplasms. As a result, 100% (Lung Neoplasms) of top 50 related miRNAs have been indexed by at least one of the three databases (dbDEMC, miR2Disease and HMDD V2.0) or at least one experimental literature in PubMed. Furthermore, we also tested our prediction method on the HMDD V1.0 database to prove the applicability of MDHGI to different datasets. The results showed that 50 out of top 50 miRNAs related with the breast neoplasms were validated by at least one of the three databases (HMDD V2.0, dbDEMC, and miR2Disease) or at least one experimental literature. Identifying potential miRNA-disease associations enhances the understanding towards molecular mechanisms and pathogenesis of diseases, which is beneficial for the development of diagnostic/treatment tools for diseases. Compared with traditional experiment methods, computational models can help experimenters reduce the cost of money and time. In order to computationally predict potential miRNA-disease associations, we developed MDHGI by combining the sparse learning method with the heterogeneous graph inference method. We performed MDHGI on different database and the experiment results indicated that MDHGI had significant advantages over previous methods both in leave-one-out cross validation and 5-fold cross validation. Besides, we also carried out three different kinds of case studies on four important human complex diseases to further demonstrate the prediction accuracy of MDHGI. In consequence, 98%, 98%, 100% and 100% out of the top 50 candidate miRNAs for the four diseases were confirmed by different databases or experimental literatures in PubMed, respectively. Thus, it could be concluded that MDHGI could make reliable predictions and should serve as an effective tool for predicting potential miRNA-disease associations.
登录
查看更多内容
WBSMDA：miRNA 疾病关联预测的评分内和评分之间
影响因子：
4.6
作者：
Chen X;Yan CC;Zhang X;You ZH;Deng L;Liu Y;Zhang Y;Dai Q
通讯作者：
Dai Q
影响因子：
3.1
作者：
Chandrasekaran, Venkat;Sanghavi, Sujay;Willsky, Alan S.
通讯作者：
Willsky, Alan S.
影响因子：
4.5
作者：
Chen, Xing;Niu, Ya-Wei;Yan, Gui-Ying
通讯作者：
Yan, Gui-Ying
影响因子：
64.8
作者：
Alizadeh, AA;Eisen, MB;Staudt, LM
通讯作者：
Staudt, LM
影响因子：
9.5
作者：
Chen, Xing;Xie, Di;You, Zhu-Hong
通讯作者：
You, Zhu-Hong