MGSGCN：基于多图结构和注意力机制的图卷积网络预测lncRNA-疾病关联
MGSGCN: Prediction of lncRNA-Disease Associations via Graph Conventional Network Based on Multi-Graph Structure and Attention Mechanism
摘要: 研究表明长非编码RNA (long non-coding RNA, lncRNA)在许多生物的生命活动中发挥着重要作用。识别潜在的lncRNA-疾病关联(lncRNA-disease associations, LDAs)有助于研究疾病的发病机制，及时地诊断、预防和治疗疾病。本文提出了一种基于多图结构和注意力机制的图卷积网络模型预测LDAs，简称MGSGCN。该模型综合了疾病语义相似性、lncRNA功能相似性、疾病与lncRNA高斯相互作用谱核相似性和余弦相似性，构建了疾病和lncRNA的特征向量。基于图卷积网络(graph conventional network, GCN)和图注意力网络(graph attention network, GAT)，使用了提取封闭子图和交互信息传播的多图结构策略来训练和预测LDAs。MGSGCN在Dataset1和Dataset2上的五折交叉验证(five-fold cross validation, 5-CV)的准确率分别为94.55%和87.44%。将MGSGCN与其它四个前人研究的计算模型进行比较，评价指标结果凸显了MGSGCN具有良好的分类性能。此外，对与子宫颈癌相关的lncRNA进行了案例分析。发现MGSGCN预测出了未被实验证实的LDAs，这说明该模型具有预测新的LDAs的能力。
Abstract: Studies have shown that long non-coding RNA (lncRNA) plays an important role in the life activities of many organisms. Identifying potential lncRNA-disease associations (LDAs) helps to study the pathogenesis of diseases and to diagnose, prevent and treat diseases in a timely manner. In this paper, we proposed a graph convolutional network model based on multi-graph structure and attention mechanism to predict LDAs, named MGSGCN. The model integrated disease semantic similarity, lncRNA functional similarity, disease and lncRNA Gaussian interaction profile kernel similarity, and cosine similarity, and constructed disease and lncRNA feature vectors. Based on graph conventional network (GCN) and graph attention network (GAT), a multi-graph structural strategy for extracting enclosing subgraphs and interaction information propagation was used to train and predict LDAs. The accuracy of MGSGCN on Dataset1 and Dataset2 with five-fold cross validation (5-CV) is 94.55% and 87.44%, respectively. Compared MGSGCN with four other computational models from previous studies, and the results of the evaluation metrics highlighted the good classification performance of MGSGCN. In addition, a case study of lncRNAs associated with cervical cancer was performed. MGSGCN was found to predict LDAs that were not experimentally confirmed, suggesting that the model has the ability to predict new LDAs.
文章引用：王若冰, 孟令宇, 谭建军. MGSGCN：基于多图结构和注意力机制的图卷积网络预测lncRNA-疾病关联[J]. 生物医学, 2024, 14(3): 457-470. https://doi.org/10.12677/hjbm.2024.143050

参考文献

[1] Grammatikakis, I. and Lal, A. (2022) Significance of lncRNA Abundance to Function. Mammalian Genome, 33, 271-280. [Google Scholar] [CrossRef] [PubMed]
[2] Kazimierczyk, M., Kasprowicz, M.K., Kasprzyk, M.E. and Wrzesinski, J. (2020) Human Long Noncoding RNA Interactome: Detection, Characterization and Function. International Journal of Molecular Sciences, 21, Article No. 1027. [Google Scholar] [CrossRef] [PubMed]
[3] Tüncel, Ö., Kara, M., Yaylak, B., Erdoğan, İ. and Akgül, B. (2022) Noncoding RNAs in Apoptosis: Identification and Function. Turkish Journal of Biology, 46, 1-40.
[4] Yi, K., Zhang, Y., Wang, Y., Wang, Z., Xie, M., Jin, Z. and Zhao, T. (2019) Long Noncoding RNA and Its Role in Virus Infection and Pathogenesis. Frontiers in Bioscience-Landmark, 24, 777-789. [Google Scholar] [CrossRef] [PubMed]
[5] Chen, L. and Zhang, S. (2016) Long Noncoding RNAs in Cell Differentiation and Pluripotency. Cell and Tissue Research, 366, 509-521. [Google Scholar] [CrossRef] [PubMed]
[6] Wang, J., Zhao, Y., Gong, W., Liu, Y., Wang, M., Huang, X. and Tan, J. (2021) EDLMFC: An Ensemble Deep Learning Framework with Multi-Scale Features Combination for ncRNA-Protein Interaction Prediction. BMC Bioinformatics, 22, Article No. 133. [Google Scholar] [CrossRef] [PubMed]
[7] Huang, X., Shi, Y., Yan, J., Qu, W., Li, X. and Tan, J. (2022) LPI-CSFFR: Combining Serial Fusion with Feature Reuse for Predicting LncRNA-Protein Interactions. Computational Biology and Chemistry, 99, Article ID: 107718. [Google Scholar] [CrossRef] [PubMed]
[8] Yan, J., Qu, W., Li, X., Wang, R. and Tan, J. (2024) GATLGEMF: A Graph Attention Model with Line Graph Embedding Multi-Complex Features for ncRNA-Protein Interactions Prediction. Computational Biology and Chemistry, 108, Article ID: 108000. [Google Scholar] [CrossRef] [PubMed]
[9] Li, X., Qu, W., Yan, J. and Tan, J. (2023) RPI-EDLCN: An Ensemble Deep Learning Framework Based on Capsule Network for ncRNA-Protein Interaction Prediction. Journal of Chemical Information and Modeling, 64, 2221-2235. [Google Scholar] [CrossRef] [PubMed]
[10] Chen, J., Ao, L. and Yang, J. (2019) Long Non-Coding RNAs in Diseases Related to Inflammation and Immunity. Annals of Translational Medicine, 7, 494. [Google Scholar] [CrossRef] [PubMed]
[11] Wang, F., Lin, H., Su, Q. and Li, C. (2022) Cuproptosis-Related lncRNA Predict Prognosis and Immune Response of Lung Adenocarcinoma. World Journal of Surgical Oncology, 20, Article No. 275. [Google Scholar] [CrossRef] [PubMed]
[12] Faghihi, M.A., Modarresi, F., Khalil, A.M., Wood, D.E., Sahagan, B.G., Morgan, T.E., Finch, C.E., St Laurent, G., Kenny, P.J. and Wahlestedt, C. (2008) Expression of a Noncoding RNA Is Elevated in Alzheimer’s Disease and Drives Rapid Feed-Forward Regulation of Beta-Secretase. Nature Medicine, 14, 723-730. [Google Scholar] [CrossRef] [PubMed]
[13] Mei, X., Zhang, B., Zhao, M. and Lu, Q. (2022) An Update on Epigenetic Regulation in Autoimmune Diseases. Journal of Translational Autoimmunity, 5, Article ID: 100176. [Google Scholar] [CrossRef] [PubMed]
[14] Yan, Y., Song, D., Song, X. and Song, C. (2020) The Role of lncRNA MALAT1 in Cardiovascular Disease. IUBMB Life, 72, 334-342. [Google Scholar] [CrossRef] [PubMed]
[15] Xing, C., Sun, S.G., Yue, Z.Q. and Bai, F. (2021) Role of lncRNA LUCAT1 in Cancer. Biomedicine & Pharmacotherapy, 134, Article ID: 111158. [Google Scholar] [CrossRef] [PubMed]
[16] Sun, J., Shi, H., Wang, Z., Zhang, C., Liu, L., Wang, L., He, W., Hao, D., Liu, S. and Zhou, M. (2014) Inferring Novel lncRNA-Disease Associations Based on a Random Walk Model of a lncRNA Functional Similarity Network. Molecular BioSystems, 10, 2074-2081. [Google Scholar] [CrossRef] 
[17] Chen, X., You, Z.H., Yan, G.Y. and Gong, D.W. (2016) IRWRLDA: Improved Random Walk with Restart for lncRNA-Disease Association Prediction. Oncotarget, 7, 57919-57931. [Google Scholar] [CrossRef] [PubMed]
[18] Zhang, J., Zhang, Z., Chen, Z. and Deng, L. (2019) Integrating Multiple Heterogeneous Networks for Novel LncRNA-Disease Association Inference. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 16, 396-406. [Google Scholar] [CrossRef] 
[19] Fu, G., Wang, J., Domeniconi, C. and Yu, G. (2018) Matrix Factorization-Based Data Fusion for the Prediction of lncRNA-Disease Associations. Bioinformatics, 34, 1529-1537. [Google Scholar] [CrossRef] [PubMed]
[20] Lu, C., Yang, M., Luo, F., Wu, F.X., Li, M., Pan, Y., Li, Y. and Wang, J. (2018) Prediction of lncRNA-Disease Associations Based on Inductive Matrix Completion. Bioinformatics, 34, 3357-3364. [Google Scholar] [CrossRef] [PubMed]
[21] Xi, W.Y., Zhou, F., Gao, Y.L., Liu, J.X. and Zheng, C.H. (2023) LDCMFC: Predicting Long Non-Coding RNA and Disease Association Using Collaborative Matrix Factorization Based on Correntropy. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20, 1774-1782. [Google Scholar] [CrossRef] 
[22] Chen, X. and Yan, G.Y. (2013) Novel Human lncRNA-Disease Association Inference Based on lncRNA Expression Profiles. Bioinformatics, 29, 2617-2624. [Google Scholar] [CrossRef] [PubMed]
[23] Zhu, R., Wang, Y., Liu, J.X. and Dai, L.Y. (2021) IPCARF: Improving lncRNA-Disease Association Prediction Using Incremental Principal Component Analysis Feature Selection and a Random Forest Classifier. BMC Bioinformatics, 22, Article No. 175. [Google Scholar] [CrossRef] [PubMed]
[24] Khalid, R., Naveed, H. and Khalid, Z. (2023) Computational Prediction of Disease Related lncRNAs Using Machine Learning. Scientific Reports, 13, Article No. 806. [Google Scholar] [CrossRef] [PubMed]
[25] Xuan, P., Cao, Y., Zhang, T., Kong, R. and Zhang, Z. (2019) Dual Convolutional Neural Networks with Attention Mechanisms Based Method for Predicting Disease-Related lncRNA Genes. Frontiers in Genetics, 10, Article No. 416. [Google Scholar] [CrossRef] [PubMed]
[26] Xuan, P., Pan, S., Zhang, T., Liu, Y. and Sun, H. (2019) Graph Convolutional Network and Convolutional Neural Network Based Method for Predicting lncRNA-Disease Associations. Cells, 8, Article No. 1012. [Google Scholar] [CrossRef] [PubMed]
[27] Xuan, P., Sheng, N., Zhang, T., Liu, Y. and Guo, Y. (2019) CNNDLP: A Method Based on Convolutional Autoencoder and Convolutional Neural Network with Adjacent Edge Attention for Predicting lncRNA-Disease Associations. International Journal of Molecular Sciences, 20, Article No. 4260. [Google Scholar] [CrossRef] [PubMed]
[28] Xuan, P., Jia, L., Zhang, T., Sheng, N., Li, X. and Li, J. (2019) LDAPred: A Method Based on Information Flow Propagation and a Convolutional Neural Network for the Prediction of Disease-Associated lncRNAs. International Journal of Molecular Sciences, 20, Article No. 4458. [Google Scholar] [CrossRef] [PubMed]
[29] Xuan, P., Zhan, L., Cui, H., Zhang, T., Nakaguchi, T. and Zhang, W. (2022) Graph Triple-Attention Network for Disease-Related LncRNA Prediction. IEEE Journal of Biomedical and Health Informatics, 26, 2839-2849. [Google Scholar] [CrossRef] 
[30] Lu, C. and Xie, M. (2023) LDAEXC: LncRNA-Disease Associations Prediction with Deep Autoencoder and XGBoost Classifier. Interdisciplinary Sciences: Computational Life Sciences, 15, 439-451. [Google Scholar] [CrossRef] [PubMed]
[31] Cui, T., Zhang, L., Huang, Y., Yi, Y., Tan, P., Zhao, Y., Hu, Y., Xu, L., Li, E. and Wang, D. (2018) MNDR v2.0: An Updated Resource of ncRNA-Disease Associations in Mammals. Nucleic Acids Research, 46, D371-D374. [Google Scholar] [CrossRef] [PubMed]
[32] Bao, Z., Yang, Z., Huang, Z., Zhou, Y., Cui, Q. and Dong, D. (2019) LncRNADisease 2.0: An Updated Database of Long Non-Coding RNA-Associated Diseases. Nucleic Acids Research, 47, D1034-D1037. [Google Scholar] [CrossRef] [PubMed]
[33] Gao, Y., Shang, S., Guo, S., Li, X., Zhou, H., Liu, H., Sun, Y., Wang, J., Wang, P., Zhi, H., Li, X., Ning, S. and Zhang, Y. (2021) Lnc2Cancer 3.0: An Updated Resource for Experimentally Supported lncRNA/circRNA Cancer Associations and Web Tools Based on RNA-seq and scRNA-seq Data. Nucleic Acids Research, 49, D1251-D1258. [Google Scholar] [CrossRef] [PubMed]
[34] Li, J., Wang, D., Yang, Z. and Liu, M. (2023) HEGANLDA: A Computational Model for Predicting Potential LncRNA-Disease Associations Based on Multiple Heterogeneous Networks. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20, 388-398.
[35] Xie, G., Jiang, J. and Sun, Y. (2022) LDA-LNSUBRW: lncRNA-Disease Association Prediction Based on Linear Neighborhood Similarity and Unbalanced Bi-Random Walk. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19, 989-997.
[36] Wang, D., Wang, J., Lu, M., Song, F. and Cui, Q. (2010) Inferring the Human microRNA Functional Similarity and Functional Network Based on microRNA-Associated Diseases. Bioinformatics, 26, 1644-1650. [Google Scholar] [CrossRef] [PubMed]
[37] Chen, X. (2015) Predicting lncRNA-Disease Associations and Constructing lncRNA Functional Similarity Network Based on the Information of miRNA. Scientific Reports, 5, Article No. 13186. [Google Scholar] [CrossRef] [PubMed]
[38] van Laarhoven, T., Nabuurs, S.B. and Marchiori, E. (2011) Gaussian Interaction Profile Kernels for Predicting Drug-Target Interaction. Bioinformatics, 27, 3036-3043. [Google Scholar] [CrossRef] [PubMed]
[39] Wang, B., Liu, R., Zheng, X., Du, X. and Wang, Z. (2022) lncRNA-Disease Association Prediction Based on Matrix Decomposition of Elastic Network and Collaborative Filtering. Scientific Reports, 12, Article No. 12700. [Google Scholar] [CrossRef] [PubMed]
[40] Shi, Z., Zhang, H., Jin, C., Quan, X. and Yin, Y. (2021) A Representation Learning Model Based on Variational Inference and Graph Autoencoder for Predicting lncRNA-Disease Associations. BMC Bioinformatics, 22, Article No. 136. [Google Scholar] [CrossRef] [PubMed]
[41] Wu, X., Lan, W., Chen, Q., Dong, Y., Liu, J. and Peng, W. (2020) Inferring LncRNA-Disease Associations Based on Graph Autoencoder Matrix Completion. Computational Biology and Chemistry, 87, Article ID: 107282. [Google Scholar] [CrossRef] [PubMed]
[42] Hu, Y., Sun, X., Mao, C., Guo, G., Ye, S., Xu, J., Zou, R., Chen, J., Wang, L., Duan, P. and Xue, X. (2017) Upregulation of Long Noncoding RNA TUG1 Promotes Cervical Cancer Cell Proliferation and Migration. Cancer Medicine, 6, 471-482. [Google Scholar] [CrossRef] [PubMed]

为你推荐