Combining K Nearest Neighbor With Nonnegative Matrix Factorization for Predicting Circrna-Disease Associations
Combining K Nearest Neighbor With Nonnegative Matrix Factorization for Predicting Circrna-Disease Associations
复制标题
DOI：
10.1109/tcbb.2022.3180903
复制
发表时间：
2023-09-01
影响因子：
4.5
通讯作者：
Chen，Zhan-Heng
中科院分区：
文献类型：
--
作者：
Wang，Mei-Neng;Xie，Xue-Jun;Chen，Zhan-Heng
越来越多的证据表明，环状RNA（circular RNA，circRNA）在基因表达调控中起着重要作用，并参与了人类多种复杂疾病的发生发展。确定circRNA与疾病的关联有助于理解复杂疾病的发病机制，治疗和诊断。由于通过生物学实验推断circRNA与疾病的关联既昂贵又耗时，因此迫切需要开发一种计算模型来确定它们之间的关联。本文提出了一种新的方法KNN-NMF，它结合最近邻和非负矩阵分解来推断circRNA与疾病之间的关联（KNN-NMF）。首先，我们分别计算了circRNA和疾病的高斯相互作用轮廓（GIP）核相似度和疾病的语义相似度。然后，使用权重最近邻建立circRNA-疾病新的相互作用谱，以减少假阴性关联对预测性能的影响。最后，实施非负矩阵分解来预测circRNA与疾病的关联。实验结果表明，KNN-NMF的预测性能优于竞争的方法在五折交叉验证。此外，两种常见疾病的案例研究进一步表明，KNN-NMF可以有效地识别潜在的circRNA-疾病关联。
Accumulating evidences show that circular RNAs (circRNAs) play an important role in regulating gene expression, and involve in many complex human diseases. Identifying associations of circRNA with disease helps to understand the pathogenesis, treatment and diagnosis of complex diseases. Since inferring circRNA-disease associations by biological experiments is costly and time-consuming, there is an urgently need to develop a computational model to identify the association between them. In this paper, we proposed a novel method named KNN-NMF, which combinesnearest neighbors with nonnegative matrix factorization to infer associations between circRNA and disease (KNN-NMF). Frist, we compute the Gaussian Interaction Profile (GIP) kernel similarity of circRNA and disease, the semantic similarity of disease, respectively. Then, the circRNA-disease new interaction profiles are established using weightnearest neighbors to reduce the false negative association impact on prediction performance. Finally, Nonnegative Matrix Factorization is implemented to predict associations of circRNA with disease. The experiment results indicate that the prediction performance of KNN-NMF outperforms the competing methods under five-fold cross-validation. Moreover, case studies of two common diseases further show that KNN-NMF can identify potential circRNA-disease associations effectively.