全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

SSAL:一种基于序列与结构特征及注意力模型的circRNA-RBP相互作用位点预测方法
SSAL: A Prediction Method for circRNA-RBP Interaction Sites Using an Attention Model Based on Sequence and Structural Features

DOI: 10.12677/hjcb.2026.162006, PP. 64-78

Keywords: 相互作用位点预测,注意力机制,深度学习,多尺度特征
Interaction Site Prediction
, Attention Mechanism, Deep Learning, Multi-Scale Features

Full-Text   Cite this paper   Add to My Lib

Abstract:

预测环状RNA (circRNA)与RNA结合蛋白(RBP)之间的相互作用位点,对于揭示疾病调控机制及开发新型治疗靶点具有重要意义。随着基因组范围内circRNA结合事件数据的日益丰富,计算模型已成为高效预测circRNA-RBP相互作用位点的主流工具。然而,如何通过有效提取circRNA的多尺度特征来提升预测准确率,仍是该领域面临的核心挑战。为解决这一问题,本研究提出了一种名为SSAL的深度学习模型,旨在实现大规模数据集上circRNA-RBP相互作用位点的精准预测。该模型的核心模块包括:首先,系统性地提取circRNA的序列特征与二级结构特征;随后,利用注意力机制对多尺度序列特征进行融合。为增强模型的稳定性和泛化能力,本文构建了一个集成学习框架,通过整合多个子模型的预测结果,有效缓解了单一模型固有的误差与随机性。为验证SSAL的性能,本文在14个大规模circRNA数据集上进行了全面评估,并将其与当前主流方法进行了对比。实验结果表明,SSAL的平均曲线下面积(AUC)达到97.66%,不仅充分证实了其在效率与鲁棒性方面的优势,且在预测准确率上均优于所有对比方法。
Predicting the interaction sites between circular RNA (circRNA) and RNA-binding proteins (RBPs) is of significant importance for deciphering disease regulatory mechanisms and developing novel therapeutic targets. With the increasing accumulation and availability of genome-wide circRNA binding event data for computational analysis, computational models have become mainstream tools for efficiently predicting circRNA-RBP interaction sites. However, enhancing prediction accuracy by effectively extracting multi-scale features of circRNA remains a key challenge in this field. To address this issue, this study proposes a deep learning model named SSAL, which can accurately predict circRNA-RBP interaction sites on large-scale datasets. The core modules of this model include: first, systematic extraction of circRNA sequence features and secondary structure features; Subsequently, an attention mechanism was employed to fuse multi-scale sequence features. To enhance model stability and generalization capability, we constructed an ensemble learning framework that integrates predictions from multiple sub-models, effectively mitigating the errors and randomness inherent in individual models. To validate the performance of SSAL, we conducted comprehensive evaluations on 14 large-scale circRNA datasets and compared it with current mainstream methods. The results demonstrate that SSAL achieved an average AUC of 97.66%, not only fully confirming its advantages in efficiency and robustness but also surpassing all comparison methods in prediction accuracy.

References

[1]  Yao, Z., et al. (2020) Advances in the Effects of Related Specific Molecules in Circular RNA on Bladder Cancer Cells. Journal of Clinical Urology, 35, 417-420.
[2]  Liu, C. and Chen, L. (2022) Circular RNAs: Characterization, Cellular Roles, and Applications. Cell, 185, 2016-2034.
https://doi.org/10.1016/j.cell.2022.04.021
[3]  Zhou, H., Zhang, H., Yan, R., et al. (2024) Mechanism and Role of CircRNA in Occurrence and Development of Hepatocellular Carcinoma. Cancer Research on Prevention and Treatment, 49, 496-502.
[4]  Sinha, T., Panigrahi, C., Das, D. and Chandra Panda, A. (2021) Circular RNA Translation, a Path to Hidden Proteome. WIREs RNA, 13, e1685.
https://doi.org/10.1002/wrna.1685
[5]  Kelaini, S., Chan, C., Cornelius, V.A. and Margariti, A. (2021) RNA-binding Proteins Hold Key Roles in Function, Dysfunction, and Disease. Biology, 10, Article 366.
https://doi.org/10.3390/biology10050366
[6]  Zang, J., Lu, D. and Xu, A. (2018) The Interaction of CircRNAs and RNA Binding Proteins: An Important Part of CircRNA Maintenance and Function. Journal of Neuroscience Research, 98, 87-97.
https://doi.org/10.1002/jnr.24356
[7]  Su, J., Chen, S., Yang, S. and Deng, Z. (2024) RNA-Binding Proteins Regulate Osteoarthritis via RNA Metabolism Regulation. Journal of Central South University (Medical Sciences), 49, 1973-1982.
[8]  Peng, T. and Xu L. (2023) Crosstalk between Epigenetic Modification and CircRNA in Colorectal Cancer: Recent Advances. Journal of Shanghai Jiao Tong University (Medical Science), 43, 237-243.
[9]  Li. H., Wang, Wei. and Hao, M. (2021) Progress of CircRNAs as A Promising Biomarker and Therapeutic Target for Cervical Cancer. Journal of International Obstetrics and Gynecology, 48, 322-327.
[10]  Zhu, H., Jia, J., and Yu, L. (2021) Research Progress on CircRNA in Liquid Biopsy of Gastric Cancer. Cancer Research on Prevention and Treatment, 48, 1023-1029.
[11]  Lee, J. (2023) The Principles and Applications of High-Throughput Sequencing Technologies. Development & Reproduction, 27, 9-24.
https://doi.org/10.12717/dr.2023.27.1.9
[12]  Kuwamoto-Imanishi, S. and Fujii, H. (2025) Online Databases in Circular RNAs. In: Xiao, J., Ed., Advances in Experimental Medicine and Biology, Springer, 43-57.
https://doi.org/10.1007/978-981-96-9428-0_4
[13]  Fan, C., Lei, X., Fang, Z., Jiang, Q. and Wu, F. (2018) CircR2Disease: A Manually Curated Database for Experimentally Supported Circular RNAs Associated with Various Diseases. Database, 2018, bay044.
https://doi.org/10.1093/database/bay044
[14]  Meng, X., Hu, D., Zhang, P., Chen, Q. and Chen, M. (2019) CircFunBase: A Database for Functional Circular RNAs. Database, 2019, baz003.
https://doi.org/10.1093/database/baz003
[15]  Zhang, K., Pan, X., Yang, Y. and Shen, H. (2019) CRIP: Predicting CircRNA-RBP-Binding Sites Using a Codon-Based Encoding and Hybrid Deep Neural Networks. RNA, 25, 1604-1615.
https://doi.org/10.1261/rna.070565.119
[16]  Jia, C., Bi, Y., Chen, J., Leier, A., Li, F. and Song, J. (2020) PASSION: An Ensemble Neural Network Approach for Identifying the Binding Sites of RBPs on CircRNAs. Bioinformatics, 36, 4276-4282.
https://doi.org/10.1093/bioinformatics/btaa522
[17]  Yang, Y., Hou, Z., Ma, Z., Li, X. and Wong, K. (2020) iCircRBP-DHN: Identification of CircRNA-RBP Interaction Sites Using Deep Hierarchical Network. Briefings in Bioinformatics, 22, bbaa274.
https://doi.org/10.1093/bib/bbaa274
[18]  Niu, M., Zou, Q. and Lin, C. (2022) CRBPDL: Identification of CircRNA-RBP Interaction Sites Using an Ensemble Neural Network Approach. PLOS Computational Biology, 18, e1009798.
https://doi.org/10.1371/journal.pcbi.1009798
[19]  Yang, Y., Hou, Z., Wang, Y., Ma, H., Sun, P., Ma, Z., et al. (2022) HCRNet: High-Throughput CircRNA-Binding Event Identification from CLIP-Seq Data Using Deep Temporal Convolutional Network. Briefings in Bioinformatics, 23, bbac027.
https://doi.org/10.1093/bib/bbac027
[20]  Cao, C., Yang, S., Li, M. and Li, C. (2023) CircSSNN: CircRNA-Binding Site Prediction via Sequence Self-Attention Neural Networks with Pre-Normalization. BMC Bioinformatics, 24, Article No. 220.
https://doi.org/10.1186/s12859-023-05352-7
[21]  Wang, X., Yu, S., Lou, E., Tan, Y. and Tan, Z. (2023) RNA 3D Structure Prediction: Progress and Perspective. Molecules, 28, 5532.
https://doi.org/10.3390/molecules28145532
[22]  Shen, T., Hu, Z., Sun, S., Liu, D., Wong, F., Wang, J., et al. (2024) Accurate RNA 3D Structure Prediction Using a Language Model-Based Deep Learning Approach. Nature Methods, 21, 2287-2298.
https://doi.org/10.1038/s41592-024-02487-0
[23]  Mukherjee, S., Moafinejad, S.N., Badepally, N.G., Merdas, K. and Bujnicki, J.M. (2024) Advances in the Field of RNA 3D Structure Prediction and Modeling, with Purely Theoretical Approaches, and with the Use of Experimental Data. Structure, 32, 1860-1876.
https://doi.org/10.1016/j.str.2024.08.015
[24]  Zheng, J., Liu, H., Feng, Y., Xu, J. and Zhao, L. (2023) CASF-Net: Cross-Attention and Cross-Scale Fusion Network for Medical Image Segmentation. Computer Methods and Programs in Biomedicine, 229, Article 107307.
https://doi.org/10.1016/j.cmpb.2022.107307
[25]  Xia, S., Zhang, X., Meng, H. and Jiao, L. (2024) Ternary Modality Contrastive Learning for Hyperspectral and Lidar Data Classification. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-17.
https://doi.org/10.1109/tgrs.2024.3417011
[26]  Hamed, S.K., Ab Aziz, M.J. and Yaakub, M.R. (2023) A Review of Fake News Detection Approaches: A Critical Analysis of Relevant Studies and Highlighting Key Challenges Associated with the Dataset, Feature Representation, and Data Fusion. Heliyon, 9, e20382.
https://doi.org/10.1016/j.heliyon.2023.e20382
[27]  Dudekula, D.B., Panda, A.C., Grammatikakis, I., et al. (2016) CircInteractome: A Web Tool for Exploring Circular RNAs and Their Interacting Proteins and microRNAs. RNA Biology, 13, 34-42.
https://doi.org/10.1080/15476286.2015.1128065
[28]  Wei, Y., Zhang, Q. and Liu, L. (2025) The Improved De Bruijn Graph for Multitask Learning: Predicting Functions, Subcellular Localization, and Interactions of Noncoding RNAs. Briefings in Bioinformatics, 26, bbae627.
https://doi.org/10.1093/bib/bbae627
[29]  Uhl, M., Houwaart, T., Corrado, G., et al. (2017) Computational Analysis of CLIP-seq Data. Methods, 118, 60-72.
https://doi.org/10.1016/j.ymeth.2017.02.006
[30]  Zhang, M., Wang, T., Xiao, G. and Xie, Y. (2020) Large-Scale Profiling of Rbp-CircRNA Interactions from Public Clip-Seq Datasets. Genes, 11, Article 54.
https://doi.org/10.3390/genes11010054
[31]  Li, M., Fan, Y., Zhang, Y. and Lv, Z. (2022) Using Sequence Similarity Based on CKSNP Features and a Graph Neural Network Model to Identify MiRNA-Disease Associations. Genes, 13, Article 1759.
https://doi.org/10.3390/genes13101759
[32]  Amerifar, S., Norouzi, M. and Ghandi, M. (2022) A Tool for Feature Extraction from Biological Sequences. Briefings in Bioinformatics, 23, bbac108.
https://doi.org/10.1093/bib/bbac108
[33]  Mishra, R. (2024) Deep Learning Based Convolute Neural Approach in the Prediction of RNA Structure. 2024 IEEE International Conference on Big Data & Machine Learning (ICBDML), Bhopal, 24-25 February 2024, 86-90.
https://doi.org/10.1109/icbdml60909.2024.10577366
[34]  Wei, Y., Tan, Z. and Liu, L. (2025) Cr-Deal: Explainable Neural Network for CircRNA-RBP Binding Site Recognition and Interpretation. Interdisciplinary Sciences: Computational Life Sciences, 17, 463-476.
https://doi.org/10.1007/s12539-025-00694-7
[35]  Liu, L., Wei, Y., Tan, Z., Zhang, Q., Sun, J. and Zhao, Q. (2024) Predicting CircRNA-RBP Binding Sites Using a Hybrid Deep Neural Network. Interdisciplinary Sciences: Computational Life Sciences, 16, 635-648.
https://doi.org/10.1007/s12539-024-00616-z
[36]  Vu, H.L., Ng, K.T.W., Richter, A. and An, C. (2022) Analysis of Input Set Characteristics and Variances on K-Fold Cross Validation for a Recurrent Neural Network Model on Waste Disposal Rate Estimation. Journal of Environmental Management, 311, Article 114869.
https://doi.org/10.1016/j.jenvman.2022.114869
[37]  Sun, Y., Ding, S., Zhang, Z. and Jia, W. (2021) An Improved Grid Search Algorithm to Optimize SVR for Prediction. Soft Computing, 25, 5633-5644.
https://doi.org/10.1007/s00500-020-05560-w
[38]  Li, Q., Jia, X., Zhou, J., Shen, L. and Duan, J. (2024) Rediscovering BCE Loss for Uniform Classification. arXiv:2403.07289.
[39]  Obi, J.C. (2023) A Comparative Study of Several Classification Metrics and Their Performances on Data. World Journal of Advanced Engineering Technology and Sciences, 8, 308-314.
https://doi.org/10.30574/wjaets.2023.8.1.0054
[40]  Naidu, G., Zuva, T. and Sibanda, E.M. (2023) A Review of Evaluation Metrics in Machine Learning Algorithms. In: Silhavy, R. and Silhavy, P., Eds., Lecture Notes in Networks and Systems, Springer International Publishing, 15-25.
https://doi.org/10.1007/978-3-031-35314-7_2
[41]  Chicco, D. and Jurman, G. (2023) The Matthews Correlation Coefficient (MCC) Should Replace the ROC AUC as the Standard Metric for Assessing Binary Classification. BioData Mining, 16, Article No. 4.
https://doi.org/10.1186/s13040-023-00322-4
[42]  Du, X. and Xue, Z. (2022) JLCRB: A Unified Multi-View-Based Joint Representation Learning for CircRNA Binding Sites Prediction. Journal of Biomedical Informatics, 136, Article 104231.
https://doi.org/10.1016/j.jbi.2022.104231
[43]  Gibertini, E. and Magagnin, L. (2022) PEDOTS:PSS@KNF Wire‐shaped Electrodes for Textile Symmetrical Capacitor. Advanced Materials Interfaces, 9, Article 2200513.
https://doi.org/10.1002/admi.202200513
[44]  Orenstein, Y., Wang, Y. and Berger, B. (2016) RCK: Accurate and Efficient Inference of Sequence-and Structure-Based Protein-RNA Binding Models from Rnacompete Data. Bioinformatics, 32, i351-i359.
https://doi.org/10.1093/bioinformatics/btw259
[45]  Wang, Z., Lei, X., Zhang, Y., Wu, F. and Pan, Y. (2025) Recent Progress of Deep Learning Methods for RBP Binding Sites Prediction on CircRNA. Current Bioinformatics, 20, 487-505.
https://doi.org/10.2174/0115748936308564240712053215
[46]  Wang, Z. and Lei, X. (2021) Prediction of RBP Binding Sites on CircRNAs Using an LSTM-Based Deep Sequence Learning Architecture. Briefings in Bioinformatics, 22, bbab342.
https://doi.org/10.1093/bib/bbab342
[47]  Liu, X., Wang, S., Sun, Y., Liao, Y., Jiang, G., Sun, B., et al. (2025) Unlocking the Potential of Circular RNA Vaccines: A Bioinformatics and Computational Biology Perspective. eBioMedicine, 114, Article 105638.
https://doi.org/10.1016/j.ebiom.2025.105638
[48]  Chen, X. and Huang, L. (2022) Computational Model for NcRNA Research. Briefings in Bioinformatics, 23, bbac472.
https://doi.org/10.1093/bib/bbac472
[49]  Wang, X., Yu, C., You, Z., Qiao, Y., Li, Z. and Huang, W. (2023) An Efficient CircRNA-MiRNA Interaction Prediction Model by Combining Biological Text Mining and Wavelet Diffusion-Based Sparse Network Structure Embedding. Computers in Biology and Medicine, 165, Article 107421.
https://doi.org/10.1016/j.compbiomed.2023.107421

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133