Auto-Encoder and Representation Learning Based MiRNA-Disease Association Prediction

  • Yutao Zhang Fuzhou University
  • Xiya Lu Beijing Information Science and Technology University
DOI: https://doi.org/10.18686/aem.v11i2.238
Keywords: MiRNAs Auto-Encoder Gaussian Interaction Profile Kernel Function

Abstract

As expressions of miRNAs are often associated with diseases, understanding the pathophysiology of illness at the miRNA level is beneficial for the treatment and prevention of associated diseases, as well as the creation of related medicines. Recent computational methods for predicting miRNA-disease associations integrate their pertinent heterogeneous data. The difficulty in this study is how to extract the implied associations from sparse data. In the present study, by drawing on natural language processing, a learning-based method is used to extract dense and high-dimensional representations of illnesses and miRNAs from integrated disease semantic similarity, miRNA functional similarity, and heterogeneous related interaction data. To predict disease-miRNA associations, we use a deep autoencoder and its reconstruction error as a measurement. Our experimental results suggest that our strategy is comparable to cutting-edge methods for predicting disease-related miRNAs.

References

[1] Wang, X Z., 2020. A Research on Prediction Method of Disease Related-miRNA Based on Biased Heat Conduction Recommended Algorithm.

[2] Chen, X., Chenggang ClarenceYan, et al, 2016. WBSMDA: Within and Between Score for MiRNA-Disease Association prediction.

[3] P. Xuan, K. Han, M. Guo, Y. Guo, J. Li, J. Ding, Y. Liu, Q. Dai, J. Li, Z. Teng, 2013 Prediction of microRNAs associated with human diseases based on weighted k most similar neighbors, PLoS One 8.

[4] P. Xuan, K. Han, Y. Guo, J. Li, X. Li, Y. Zhong, Z. Zhang, J. Ding. 2015 Prediction disease-associated microRNAs based on random walk.

[5] EdgarManzanarez-Ozuna, Dora-Luz Flores, EverardoGutiérrez-López, David Cervantes and Patricia Juárez,2018. Model based on GA and DNN for prediction of mRNA-Smad7 expression regulated by miRNAs in breast cancer.

[6] Liao, F., Chen, X., Peng, PL., Dong, WG., 2020, RWR-algorithm-based dissection of microRNA-506-3p and microRNA-140-5p as radiosensitive biomarkers in colorectal cancer.

[7] Li, J.-Q. et al. 2017 MCMDA: matrix completion for MiRNA–disease association prediction. Oncotarget, 8, 21187–21199.

[8] Vladimir Gligorijević, Meet Barot, Richard Bonneau, deepNF: deep network fusion for protein function prediction, Bioinformatics, Volume 34, Issue 22, 15 November 2018, Pages 3873–3881.
Published
2022-07-07
Issue
Vol 11 No 2 (2022)
Section
Original Research Article

Copyright (c) 2022 Yutao Zhang, Xiya Lu

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Authors submitting to USP journals agree to publish their manuscript under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0) where authors agree to allow third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit, and that in the event of reuse or distribution, the terms of this license are made clear

Authors retain copyright of their work, with first publication rights (online and print) granted to Universe Scientific Publishing or the owner of the journal in question.