Predicting circRNA-disease Associations by Using Multi-biomolecular Networks Based on Variational Graph Auto-encoder with Attention Mechanism

YANG Jing; LEI Xiujuan; PAN Yi

doi:10.23919/cje.2023.00.344

Article Contents

Article Navigation > Chinese Journal of Electronics > 2024 > Uncorrected proof

Jing YANG, Xiujuan LEI, and Yi PAN, “Predicting circRNA-disease Associations by Using Multi-biomolecular Networks Based on Variational Graph Auto-encoder with Attention Mechanism,” Chinese Journal of Electronics, vol. 33, no. 6, pp. 1–12, 2024 doi: 10.23919/cje.2023.00.344

Citation:

Jing YANG, Xiujuan LEI, and Yi PAN, “Predicting circRNA-disease Associations by Using Multi-biomolecular Networks Based on Variational Graph Auto-encoder with Attention Mechanism,” Chinese Journal of Electronics, vol. 33, no. 6, pp. 1–12, 2024 doi: 10.23919/cje.2023.00.344

Citation:

Jing YANG, Xiujuan LEI, and Yi PAN, “Predicting circRNA-disease Associations by Using Multi-biomolecular Networks Based on Variational Graph Auto-encoder with Attention Mechanism,” Chinese Journal of Electronics, vol. 33, no. 6, pp. 1–12, 2024 doi: 10.23919/cje.2023.00.344

PDF( 6703 KB)

Predicting circRNA-disease Associations by Using Multi-biomolecular Networks Based on Variational Graph Auto-encoder with Attention Mechanism

doi: 10.23919/cje.2023.00.344

YANG Jing^1
,,
LEI Xiujuan^{1
,
,},
PAN Yi^{2, 3
,}

1.
School of Computer Science, Shaanxi Normal University, Xi’an 710119, China
2.
Faculty of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
3.
Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Shenzhen 518055, China

More Information

Author Bio:
Jing YANG pursuing the Ph.D. degree with the School of Computer Science, Shaanxi Normal University, Xi’an, Shaanxi, China. Her research interests include data mining, graph neural network, artificial intelligence and bioinformatics. (Email: yangjing0726@snnu.edu.cn)

Xiujuan LEI is a Professor with the School of Computer Science, Shaanxi Normal University, Xi’an, China. She received her M.S. and Ph.D. degrees from Northwestern Polytechnical University, Xi’an, China, in 2001 and 2005, respectively. Her current research interests mainly include intelligent computing and bioinformatics. (Email: xjlei@snnu.edu.cn)

Yi PAN is currently a Professor of the Faculty of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. He has served as Chair of Computer Science Department, Georgia State University, Atlanta, USA, during 2005–2020. He received his B.Eng. and M.Eng. degrees in Computer Engineering from Tsinghua University, Beijing, China, in 1982 and 1984, respectively, and his Ph.D. degree in Computer Science from University of Pittsburgh, Pittsburgh, USA, in 1991. His current research interests mainly include bioinformatics and health informatics using big data analysis, cloud computing, and machine learning technologies. (Email: yipan@gsu.edu)
Corresponding author: Email: xjlei@snnu.edu.cn
Received Date: 2023-11-01
Accepted Date: 2024-04-15

Available Online: 2024-05-15

Abstract

Abstract

CircRNA-disease association (CDA) can provide a new direction for the treatment of diseases. However, traditional biological experiment is time-consuming and expensive, this urges us to propose the reliable computational model to predict the associations between circRNAs and diseases. And there is existing more and more evidence indicates that the combination of multi-biomolecular information can improve the prediction accuracy. We propose a novel computational model for CDA prediction named MBCDA, we collect the multi-biomolecular information including circRNA, disease, miRNA and lncRNA based on 6 databases, and construct three heterogeneous network among them, then the multi-heads graph attention networks (GAT) are applied to these three networks to extract the features of circRNAs and diseases from different views, the obtained features are put into variational graph auto-encoder (VGAE) network to learn the latent distributions of the nodes, a fully connected neural network (FCNN) is adopted to further process the output of VGAE and uses sigmoid function to obtain the predicted probabilities of circRNA-disease pairs. As a result, MBCDA achieved the values of AUC and AUPR under 5-fold cross-validation of 0.893 and 0.887. MBCDA was applied to the analysis of the top-25 predicted associations between circRNAs and diseases, these experimental results show that our proposed MBCDA is a powerful computational model for CDA prediction.
- CircRNA,
- Multi-source information fusion,
- Variational graph auto-encoder,
- Graph attention mechanism

FullText(HTML)

References(49)

References

[1]	L. S. Kristensen, M. S. Andersen, L. V. W. Stagsted, et al., “The biogenesis, biology and characterization of circular RNAs,” Nature Reviews Genetics, vol. 20, no. 11, pp. 675–691, 2019. doi: 10.1038/s41576-019-0158-7
[2]	M. T. Hsu and M. Coca-Prados, “Electron microscopic evidence for the circular form of RNA in the cytoplasm of eukaryotic cells,” Nature, vol. 280, no. 5720, pp. 339–340, 1979. doi: 10.1038/280339a0
[3]	T. B. Hansen, T. I. Jensen, B. H. Clausen, et al., “Natural RNA circles function as efficient microRNA sponges,” Nature, vol. 495, no. 7441, pp. 384–388, 2013. doi: 10.1038/nature11993
[4]	J. Ju, Y. N. Song, X. Z. Chen, et al., “CircRNA is a potential target for cardiovascular diseases treatment,” Molecular and Cellular Biochemistry, vol. 477, no. 2, pp. 417–430, 2022. doi: 10.1007/s11010-021-04286-z
[5]	J. Zhou, L. Wang, Q. Sun, et al., “Has_circ_0001666 suppresses the progression of colorectal cancer through the miR-576-5p/PCDH10 axis,” Clinical and Translational Medicine, vol. 11, no. 11, article no. e565, 2021. doi: 10.1002/ctm2.565
[6]	X. Guo, Z. Y. Wang, X. Deng, et al., “Circular RNA CircITCH (has-circ-0001141) suppresses hepatocellular carcinoma (HCC) progression by sponging miR-184,” Cell Cycle, vol. 21, no. 15, pp. 1557–1577, 2022. doi: 10.1080/15384101.2022.2057633
[7]	G. W. Chen, Y. T. Shi, M. M. Liu, et al., “CircHIPK3 regulates cell proliferation and migration by sponging miR-124 and regulating AQP3 expression in hepatocellular carcinoma,” Cell Death & Disease, vol. 9, no. 2, article no. 175, 2018. doi: 10.1038/s41419-017-0204-3
[8]	S. Ghafouri-Fard, T. Khoshbakht, B. M. Hussen, et al., “Emerging role of circular RNAs in the pathogenesis of ovarian cancer,” Cancer Cell International, vol. 22, no. 1, article no. 172, 2022. doi: 10.1186/s12935-022-02602-1
[9]	L. Zhou, F. F. Li, and S. M. Wang, “Circ-ITCH restrains the expression of MMP-2, MMP-9 and TNF-α in diabetic retinopathy by inhibiting miR-22,” Experimental and Molecular Pathology, vol. 118, article no. 104594, 2021. doi: 10.1016/j.yexmp.2020.104594
[10]	Y. Zhang, X. O. Zhang, T. Chen, et al., “Circular intronic long noncoding RNAs,” Molecular Cell, vol. 51, no. 6, pp. 792–806, 2013. doi: 10.1016/j.molcel.2013.08.017
[11]	L. Wan, L. Zhang, K. Fan, et al., “Circular RNA-ITCH suppresses lung cancer proliferation via inhibiting the Wnt/β-catenin pathway,” BioMed Research International, vol. 2016, article no. 1579490, 2016. doi: 10.1155/2016/1579490
[12]	P. Glažar, P. Papavasileiou, and N. Rajewsky, “CircBase: A database for circular RNAs,” RNA, vol. 20, no. 11, pp. 1666–1670, 2014. doi: 10.1261/rna.043687.113
[13]	J. H. Li, S. Liu, H. Zhou, et al., “StarBase v2.0: Decoding miRNA-ceRNA, miRNA-ncRNA and protein–RNA interaction networks from large-scale CLIP-Seq data,” Nucleic Acids Research, vol. 42, no. D1, pp. D92–D97, 2014. doi: 10.1093/nar/gkt1248
[14]	S. L. Li, Y. C. Li, B. Chen, et al., “ExoRBase: A database of circRNA, lncRNA and mRNA in human blood exosomes,” Nucleic Acids Research, vol. 46, no. D1, pp. D106–D112, 2018. doi: 10.1093/nar/gkx891
[15]	Y. C. Liu, J. R. Li, C. H. Sun, et al., “CircNet: A database of circular RNAs derived from transcriptome sequencing data,” Nucleic Acids Research, vol. 44, no. D1, pp. D209–D215, 2016. doi: 10.1093/nar/gkv940
[16]	R. Dong, X. K. Ma, G. W. Li, et al., “CIRCpedia v2: An updated database for comprehensive circular RNA annotation and expression comparison,” Genomics, Proteomics & Bioinformatics, vol. 16, no. 4, pp. 226–233, 2018 doi: 10.1016/j.gpb.2018.08.001
[17]	C. Y. Fan, X. J. Lei, Z. Q. Fang, et al., “CircR2Disease: A manually curated database for experimentally supported circular RNAs associated with various diseases,” Database, vol. 2018, article no. bay044, 2018. doi: 10.1093/database/bay044
[18]	C. Y. Fan, X. J. Lei, J. J. Tie, et al., “CircR2Disease v2.0: An updated web server for experimentally validated circRNA–disease associations and its application,” Genomics, Proteomics & Bioinformatics, vol. 20, no. 3, pp. 435–445, 2022. doi: 10.1016/j.gpb.2021.10.002
[19]	X. W. Meng, D. H. Hu, P. J. Zhang, et al., “CircFunBase: A database for functional circular RNAs,” Database, vol. 2019, article no. baz003, 2019. doi: 10.1093/database/baz003
[20]	Z. Zhao, K. Y. Wang, F. Wu, et al., “CircRNA disease: A manually curated database of experimentally supported circRNA-disease associations,” Cell Death & Disease, vol. 9, no. 5, article no. 475, 2018. doi: 10.1038/s41419-018-0503-3
[21]	D. X. Yao, L. Zhang, M. Y. Zheng, et al., “Circ2Disease: A manually curated database of experimentally validated circRNAs in human disease,” Scientific Reports, vol. 8, no. 1, article no. 11018, 2018. doi: 10.1038/s41598-018-29360-3
[22]	C. Y. Fan, X. J. Lei, and F. X. Wu, “Prediction of circRNA-disease associations using KATZ model based on heterogeneous networks,” International Journal of Biological Sciences, vol. 14, no. 14, pp. 1950–1959, 2018. doi: 10.7150/ijbs.28260
[23]	C. Yan, J. X. Wang, and F. X. Wu, “DWNN-RLS: Regularized least squares method for predicting circRNA-disease associations,” BMC Bioinformatics, vol. 19, no. S19, article no. 520, 2018. doi: 10.1186/s12859-018-2522-6
[24]	Y. C. Zhang, X. J. Lei, Y. Pan, et al., “Prediction of disease-associated circRNAs via circRNA–disease pair graph and weighted nuclear norm minimization,” Knowledge-Based Systems, vol. 214, article no. 106694, 2021. doi: 10.1016/J.KNOSYS.2020.106694
[25]	Y. C. Zhang, X. J. Lei, Z. Q. Fang, et al., “CircRNA-disease associations prediction based on metapath2vec++ and matrix factorization,” Big Data Mining and Analytics, vol. 3, no. 4, pp. 280–291, 2020. doi: 10.26599/BDMA.2020.9020025
[26]	M. L. Li, M. Y. Liu, Y. Bin, et al., “Prediction of circRNA-disease associations based on inductive matrix completion,” BMC Medical Genomics, vol. 13, no. S5, article no. 42, 2020. doi: 10.1186/s12920-020-0679-0
[27]	L. Wang, Z. H. You, Y. M. Li, et al., “GCNCDA: A new method for predicting circRNA-disease associations based on graph convolutional network algorithm,” PLoS Computational Biology, vol. 16, no. 5, article no. e1007568, 2020. doi: 10.1371/journal.pcbi.1007568
[28]	J. Yang and X. J. Lei, “Predicting circRNA-disease associations based on autoencoder and graph embedding,” Information Sciences, vol. 571, pp. 323–336, 2021. doi: 10.1016/j.ins.2021.04.073
[29]	M. T. Niu, Q. Zou, and C. Y. Wang, “GMNN2CD: Identification of circRNA– disease associations based on variational inference and graph Markov neural networks,” Bioinformatics, vol. 38, no. 8, pp. 2246–2253, 2022. doi: 10.1093/bioinformatics/btac079
[30]	H. Y. Zhang, L. Wang, Z. H. You, et al., “iGRLCDA: Identifying circRNA–disease association based on graph representation learning,” Briefings in Bioinformatics, vol. 23, no. 3, article no. bbac083, 2022. doi: 10.1093/bib/bbac083
[31]	X. J. Lei, T. B. Mudiyanselage, Y. C. Zhang, et al., “A comprehensive survey on computational methods of non-coding RNA and disease association prediction,” Briefings in Bioinformatics, vol. 22, no. 4, article no. bbaa350, 2021. doi: 10.1093/bib/bbaa350
[32]	P. Veličković, G. Cucurull, A. Casanova, et al., “Graph attention networks,” in Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada, pp. 1–12, 2018.
[33]	T. N. Kipf and M. Welling, “Variational graph auto-encoders,” arXiv preprint, arXiv: 1611.07308, 2016.
[34]	M. Liu, Q. Wang, J. Shen, et al., “Circbank: A comprehensive database for circRNA with standard nomenclature,” RNA Biology, vol. 16, no. 7, pp. 899–905, 2019. doi: 10.1080/15476286.2019.1600395
[35]	Z. Huang, J. C. Shi, Y. X. Gao, et al., “HMDD v3.0: A database for experimentally supported human microRNA–disease associations,” Nucleic Acids Research, vol. 47, no. D1, pp. D1013–D1017, 2019. doi: 10.1093/nar/gky1010
[36]	X. Lin, Y. Y. Lu, C. H. Zhang, et al., “LncRNADisease v3.0: An updated database of long non-coding RNA-associated diseases,” Nucleic Acids Research, vol. 52, no. D1, pp. D1365–D1369, 2024. doi: 10.1093/nar/gkad828
[37]	D. Wang, J. Wang, M. Lu, et al., “Inferring the human microRNA functional similarity and functional network based on microRNA-associated diseases,” Bioinformatics, vol. 26, no. 13, pp. 1644–1650, 2010. doi: 10.1093/bioinformatics/btq241
[38]	C. E. Lipscomb, “Medical subject headings (MeSH),” Bulletin of the Medical Library Association, vol. 88, no. 3, pp. 265–266, 2000.
[39]	Y. Q. Mao and Z. Y. Lu, “MeSH now: Automatic meSH indexing at PubMed scale via learning to rank,” Journal of Biomedical Semantics, vol. 8, no. 1, article no. 15, 2017. doi: 10.1186/s13326-017-0123-3
[40]	T. Van Laarhoven, S. B. Nabuurs, and E. Marchiori, “Gaussian interaction profile kernels for predicting drug–target interaction,” Bioinformatics, vol. 27, no. 21, pp. 3036–3043, 2011. doi: 10.1093/bioinformatics/btr500
[41]	T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proceedings of the 5th International Conference on Learning Representations, Toulon, France, pp. 1–14, 2017.
[42]	D. J. Hand, “Measuring classifier performance: A coherent alternative to the area under the ROC curve,” Machine Learning, vol. 77, no. 1, pp. 103–123, 2009. doi: 10.1007/s10994-009-5119-5
[43]	B. Ozenne, F. Subtil, and D. Maucort-Boulch, “The precision–recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases,” Journal of Clinical Epidemiology, vol. 68, no. 8, pp. 855–859, 2015. doi: 10.1016/j.jclinepi.2015.02.010
[44]	M. G. Huang, Z. Y. Zhong, M. X. Lv, et al., “Comprehensive analysis of differentially expressed profiles of lncRNAs and circRNAs with associated co-expression and ceRNA networks in bladder carcinoma,” Oncotarget, vol. 7, no. 30, pp. 47186–47200, 2016. doi: 10.18632/oncotarget.9706
[45]	W. Zhang, C. L. Yu, X. C. Wang, et al., “Predicting circRNA-disease associations through linear neighborhood label propagation method,” IEEE Access, vol. 7, pp. 83474–83483, 2019. doi: 10.1109/ACCESS.2019.2920942
[46]	L. Deng, W. Zhang, Y. C. Shi, et al., “Fusion of multiple heterogeneous networks for predicting circRNA-disease associations,” Scientific Reports, vol. 9, no. 1, article no. 9605, 2019. doi: 10.1038/s41598-019-45954-x
[47]	H. Wei and B. Liu, “iCircDA-MF: Identification of circRNA-disease associations based on matrix factorization,” Briefings in Bioinformatics, vol. 21, no. 4, pp. 1356–1367, 2020. doi: 10.1093/bib/bbz057
[48]	H. Z. Zhang, J. T. Fang, Y. P. Sun, et al., “Predicting miRNA-disease associations via node-level attention graph auto-encoder,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 20, no. 2, pp. 1308–1318, 2023. doi: 10.1109/TCBB.2022.3170843
[49]	Q. Z. Wu, Z. H. Deng, W. Zhang, et al., “MLNGCF: CircRNA–disease associations prediction with multilayer attention neural graph-based collaborative filtering,” Bioinformatics, vol. 39, no. 8, article no. btad499, 2023. doi: 10.1093/bioinformatics/btad499