|
LPI-MAM:以miRNAs为中介基于深度学习预测lncRNA-蛋白质相互作用
|
Abstract:
长链非编码RNA (Long non-coding RNAs, lncRNAs)是细胞增殖和死亡的重要调控因子,它的失调可能会导致多种疾病发生。LncRNAs主要是通过与蛋白质相互作用(lncRNA-protein interactions, lncRPIs)来发挥生物学功能。因此,研究lncRPIs对了解lncRNAs的功能及相关疾病至关重要。目前,多数计算方法依赖于已知的验证过的lncRPIs构建模型,但经过实验验证的样本是有限的。MiRNAs主要是与mRNAs结合导致基因沉默,而lncRNAs可作为竞争性内源性RNA,竞争性的结合miRNAs来间接地调节基因表达。本文提出LPI-MAM方法,使用miRNAs作为中间体来扩大lncRPIs的预测范围。该方法将序列、结构和组成转换分布特征融合,输入卷积神经网络和独立循环神经网络的集成深度学习框架中。结果表明,LPI-MAM在基准数据集上取得了良好的性能。并且通过构建可视化交互网络发现该模型具有预测未知lncRPIs的能力。
Long non-coding RNAs (lncRNAs) are crucial regulatory factors of cell proliferation and death, its dysregulation may lead to the occurrence of a variety of diseases. LncRNAs play biological functions mainly through lncRNA-protein interactions (lncRPIs). Therefore, it becomes essential to study the interactions between lncRNA and protein (lncRPIs) for exploring the function of lncRNAs. At pre-sent, almost computational methods depend on known lncRPIs to build a model. However, the samples that have been verified are limited. MiRNAs mainly bind to mRNAs to cause gene silencing. As competitive endogenous RNAs (ceRNAs), lncRNAs can indirectly regulate gene expression by competitively binding miRNAs. This study proposes the LPI-MAM method, which uses miRNAs as mediators to expand the prediction range of lncRPIs. The features of sequence, structure and composition transformation distribution (CTD) are fused and then input into the integrated deep learning framework of convolutional neural network (CNN) and independent recurrent neural network (IndRNN). The results indicate that LPI-MAM has achieved good performance on benchmark dataset. And by constructing a visual interaction network, it is found that the model has the ability to predict unknown lncRPIs.
[1] | Muppirala, U.K., Honavar, V.G. and Dobbs, D. (2011) Pre-dicting RNA-Protein Interactions Using Only Sequence Information. BMC Bioinformatics, 12, Article No. 489. https://doi.org/10.1186/1471-2105-12-489 |
[2] | Peng, C., Han, S., Zhang, H. and Li, Y. (2019) RPITER: A Hier-archical Deep Learning Framework for ncRNA-Protein Interaction Prediction. International Journal of Molecular Sci-ences, 20, Article No. 1070.
https://doi.org/10.3390/ijms20051070 |
[3] | Pan, X., Fan, Y.X., Yan, J. and Shen, H.B. (2016) IPMiner: Hidden ncRNA-Protein Interaction Sequential Pattern Mining with Stacked Autoencoder for Accurate Computational Prediction. BMC Genomics, 17, Article No. 582.
https://doi.org/10.1186/s12864-016-2931-8 |
[4] | Xiao, Y., Zhang, J. and Deng, L. (2017) Prediction of lncRNA-Protein Interactions Using HeteSim Scores Based on Heterogeneous Networks. Scientific Reports, 7, Article No. 3664. https://doi.org/10.1038/s41598-017-03986-1 |
[5] | Hu, H., Zhang, L., Ai, H., Zhang, H., Fan, Y., Zhao, Q. and Liu, H. (2018) HLPI-Ensemble: Prediction of Human lncRNA-Protein Interactions Based on Ensemble Strategy. RNA Biology, 15, 797-806.
https://doi.org/10.1080/15476286.2018.1457935 |
[6] | Ge, M., Li, A. and Wang, M. (2016) A Bipartite Net-work-Based Method for Prediction of Long Non-Coding RNA-Protein Interactions. Genomics Proteomics Bioinformat-ics, 14, 62-71. https://doi.org/10.1016/j.gpb.2016.01.004 |
[7] | 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 Combina-tion for ncRNA-Protein Interaction Prediction. BMC Bioinformatics, 22, Article No. 133. https://doi.org/10.1186/s12859-021-04069-9 |
[8] | 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.
https://doi.org/10.1016/j.compbiolchem.2022.107718 |
[9] | Zhou, Y.K., Shen, Z.A., Yu, H., Luo, T., Gao, Y. and Du, P.F. (2020) Predicting lncRNA-Protein Interactions with miRNAs as Mediators in a Heterogeneous Network Model. Frontiers in Genetics, 10, Article No. 1341.
https://doi.org/10.3389/fgene.2019.01341 |
[10] | Chen, D., Wang, H., Zhang, M., Jiang, S., Zhou, C., Fang, B. and Chen, P. (2018) Abnormally Expressed Long Non-Coding RNAs in Prognosis of Osteosarcoma: A Systematic Review and Meta-Analysis. Journal of Bone Oncology, 13, 76-90. https://doi.org/10.1016/j.jbo.2018.09.005 |
[11] | Zhou, H., Wekesa, J.S., Luan, Y. and Meng, J. (2021) PRPI-SC: An Ensemble Deep Learning Model for Predicting Plant lncRNA-Protein Interactions. BMC Bioinformatics, 22, Article No. 415.
https://doi.org/10.1186/s12859-021-04328-9 |
[12] | Yi, Y., Zhao, Y., Li, C., Zhang, L., Huang, H., Li, Y., Liu, L., Hou, P., Cui, T., Tan, P., Hu, Y., Zhang, T., Huang, Y., Li, X., Yu, J. and Wang, D. (2017) RAID v2.0: An Updated Resource of RNA-Associated Interactions across Organisms. Nucleic Acids Research, 45, D115-D118. https://doi.org/10.1093/nar/gkw1052 |
[13] | Lorenz, R., Bernhart, S.H., H?ner Zu Siederdissen, C., Tafer, H., Flamm, C., Stadler, P.F. and Hofacker, I.L. (2011) ViennaRNA Package 2.0. Algorithms for Molecular Biology: AMB, 6, Article No. 26.
https://doi.org/10.1186/1748-7188-6-26 |
[14] | Brown, G.R., Hem, V., Katz, K.S., et al. (2015) Gene: A Gene-Centered Information Resource at NCBI. Nucleic Acids Research, 43, D36-D42. https://doi.org/10.1093/nar/gku1055 |
[15] | Kozomara, A. and Griffiths-Jones, S. (2011) miRBase: Integrating mi-croRNA Annotation and Deep-Sequencing Data. Nucleic Acids Research, 39, D152-D157. https://doi.org/10.1093/nar/gkq1027 |
[16] | UniProt Consortium (2021) UniProt: The Universal Protein Knowledge-base in 2021. Nucleic Acids Research, 49, D480-D489. |
[17] | Hunt, S.E., McLaren, W., Gil, L., et al. (2018) Ensembl Variation Resources. Database (Oxford), 2018, bay119.
https://doi.org/10.1093/database/bay119 |
[18] | Yang, S., Wang, Y., Lin, Y., Shao, D., He, K. and Huang, L. (2020) LncMirNet: Predicting LncRNA-miRNA Interaction Based on Deep Learning of Ribonucleic Acid Sequences. Molecules (Basel, Switzerland), 25, Article No. 4372.
https://doi.org/10.3390/molecules25194372 |
[19] | Geourjon, C. and Deléage, G. (1995) SOPMA: Significant Im-provements in Protein Secondary Structure Prediction by Consensus Prediction from Multiple Alignments. Computer Applications in the Biosciences: CABIOS, 11, 681-684.
https://doi.org/10.1093/bioinformatics/11.6.681 |
[20] | Yang, S., Wang, Y., Zhang, S., Hu, X., Ma, Q. and Tian, Y. (2020) NCResNet: Noncoding Ribonucleic Acid Prediction Based on a Deep Resident Network of Ribonucleic Acid Sequences. Frontiers in Genetics, 11, Article No. 90.
https://doi.org/10.3389/fgene.2020.00090 |
[21] | Tong, X. and Liu, S. (2019) CPPred: Coding Potential Prediction Based on the Global Description of RNA Sequence. Nucleic Acids Research, 47, e43. https://doi.org/10.1093/nar/gkz087 |
[22] | Kazimierczyk, M., Kasprowicz, M.K., Kasprzyk, M.E. and Wrzesinski, J. (2020) Human Long Noncoding RNA In-teractome: Detection, Characterization and Function. International Journal of Molecular Sciences, 21, Article No. 1027.
https://doi.org/10.3390/ijms21031027 |
[23] | Zhao, D., Wang, C., Yan, S. and Chen, R. (2022) Advances in the Identification of Long Non-Coding RNA Binding Proteins. Analytical Biochemistry, 639, Article ID: 114520. https://doi.org/10.1016/j.ab.2021.114520 |
[24] | Otasek, D., Morris, J.H., Bou?as, J., Pico, A.R. and Demchak, B. (2019) Cytoscape Automation: Empowering Workflow-Based Network Analysis. Genome Biology, 20, Article No. 185. https://doi.org/10.1186/s13059-019-1758-4 |
[25] | Mila, M., Alvarez-Mora, M.I., Madrigal, I. and Rodri-guez-Revenga, L. (2018) Fragile X Syndrome: An Overview and Update of the FMR1 Gene. Clinical Genetics, 93, 197-205. https://doi.org/10.1111/cge.13075 |
[26] | Pabit, S.A., Chen, Y.L., Usher, E.T., Cook, E.C., Pollack, L. and Showalter, S.A. (2020) Elucidating the Role of Microprocessor Protein DGCR8 in Bending RNA Structures. Biophysi-cal Journal, 119, 2524-2536.
https://doi.org/10.1016/j.bpj.2020.10.038 |
[27] | Hang, Q., Zeng, L., Wang, L., et al. (2021) Non-Canonical Function of DGCR8 in DNA Double-Strand Break Repair Signaling and Tumor Radioresistance. Nature Communications, 12, Article No. 4033.
https://doi.org/10.1038/s41467-021-24298-z |
[28] | Marchese, D., de Groot, N.S., Lorenzo Gotor, N., Livi, C.M. and Tartaglia, G.G. (2016) Advances in the Characterization of RNA-Binding Proteins. Wiley Interdisciplinary Reviews. RNA, 7, 793-810. https://doi.org/10.1002/wrna.1378 |
[29] | Zhu, W., Zhou, B.L., Rong, L.J., et al. (2020) Roles of PTBP1 in Alternative Splicing, Glycolysis, and Oncogensis. Journal of Zhejiang University Science B, 21, 122-136. https://doi.org/10.1631/jzus.B1900422 |