DOI QR코드

DOI QR Code

MicroRNA-Gene Association Prediction Method using Deep Learning Models

  • Seung-Won Yoon (Department of Computer Science, Chungnam National University) ;
  • In-Woo Hwang (Department of Computer Science, Chungnam National University) ;
  • Kyu-Chul Lee (Department of Computer Science, Chungnam National University)
  • Received : 2023.07.21
  • Accepted : 2023.09.16
  • Published : 2023.12.31

Abstract

Micro ribonucleic acids (miRNAs) can regulate the protein expression levels of genes in the human body and have recently been reported to be closely related to the cause of disease. Determining the genes related to miRNAs will aid in understanding the mechanisms underlying complex miRNAs. However, the identification of miRNA-related genes through wet experiments (in vivo, traditional methods are time- and cost-consuming). To overcome these problems, recent studies have investigated the prediction of miRNA relevance using deep learning models. This study presents a method for predicting the relationships between miRNAs and genes. First, we reconstruct a negative dataset using the proposed method. We then extracted the feature using an autoencoder, after which the feature vector was concatenated with the original data. Thereafter, the concatenated data were used to train a long short-term memory model. Our model exhibited an area under the curve of 0.9609, outperforming previously reported models trained using the same dataset.

Keywords

Acknowledgement

This work was supported by research fund of Chungnam National University.

References

  1. L. Fu and Q. Peng, "A deep ensemble model to predict miRNA disease association," Scientific reports, vol. 7, no. 1, pp. 1-13, Nov. 2017. DOI: 10.1038/s41598-017-15235-6.
  2. K. Deepthi and A. S. Jereesh, "An Ensemble Approach Based on Multi-Source Information to Predict Drug-MiRNA Associations via Convolutional Neural Networks," IEEE Access, vol. 9, pp. 38331-38341, 2021. DOI: 10.1109/access.2021.3063885.
  3. M. Lindow and J. Gorodkin, "Principles and limitations of computational microRNA gene and target finding," DNA and cell biology, vol. 26, no. 5, pp. 339-351, May 2007. DOI: 10.1089/dna.2006.0551.
  4. Y. Liu, J. Luo, and P. Ding, "Inferring MicroRNA Targets Based on Restricted Boltzmann Machines," IEEE J Biomed Health Inform, pp 427-436, Jan. 2019. DOI: 10.1109/JBHI.2018.2814609.
  5. M. Wen, P. Cong, Z. Zhang, H. Lu, and T. Li, "DeepMirTar: a deep learning approach for predicting human miRNA targets," Bioinformatics, vol. 34, no. 22, pp 3781-3787, Nov. 2018. DOI: 10.1093/bioinformatics/bty424.
  6. T. Gu, X. Zhao, W. B. Barbazuk, and J.-H. Lee, "miTAR: a hybrid deep learning-based approach for predicting miRNA targets," BMC bioinformatics, vol 22, no. 1, pp 1-16, Feb. 2021. DOI: 10.1186/s12859-021-04026-6
  7. S. Cheng, M. Guo, C. Wang, X. Liu, Y. Liu, and X. Wu, "MiRTDL: a deep learning approach for miRNA target prediction," IEEE/ACM transactions on computational biology and bioinformatics, vol. 13, no. 6, pp. 1161-1169, Nov. 2016. DOI: 10.1109/TCBB.2015.2510002.
  8. W. Xie, J. Luo, C. Pan, and Y. Liu, "SG-LSTM-FRAME: a computational frame using sequence and geometrical information via LSTM to predict miRNA-gene associations," Briefings in bioinformatics, vol. 22, no. 2, pp. 2032-2042, Mar. 2021. DOI: 10.1093/bib/bbaa022.
  9. S. D. Hsu, F-M. Lin, W. Y. Wu, C. Liang, W-C. Huang, W-L. Chan, W-T. Tsai, G-Z. Chen, C. J. Lee, C-M. Chiu, C. H. Chien, M. C. Wu, C. Y. Huang, A. P. Tsou, and H. D. Huang, "miRTarBase: a database curates experimentally validated microRNA-target interactions," Nucleic acids research, vol. 39, no. suppl_1, pp. D163-D169, Jan. 2011. DOI: 10.1093/nar/gkq1107.
  10. Q. Meng, D. Catchpoole, D. Skillicom, and P. J. Kennedy "Relational autoencoder for feature extraction," in 2017 International joint conference on neural networks (IJCNN), Anchorage, USA, pp. 364-371, 2017. DOI: 10.1109/IJCNN.2017.7965877.
  11. Y. Yu, X. Si, C. Hu, and J. Zhang, "A review of recurrent neural networks: LSTM cells and network architectures," Neural computation, vol. 31, no. 7, pp. 1235-1270, Jul. 2019. DOI: 10.1162/neco_a_01199.