A method for miRNA diffusion association prediction using machine learning decoding of multi-level heterogeneous graph Transformer encoded representations.

Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE

Original Publication: London : Nature Publishing Group, copyright 2011-

MicroRNAs*/genetics ; Machine Learning* ; Algorithms* ; Computational Biology*/methods; Humans ; Genetic Predisposition to Disease

MicroRNAs (miRNAs) are a key class of endogenous non-coding RNAs that play a pivotal role in regulating diseases. Accurately predicting the intricate relationships between miRNAs and diseases carries profound implications for disease diagnosis, treatment, and prevention. However, these prediction tasks are highly challenging due to the complexity of the underlying relationships. While numerous effective prediction models exist for validating these associations, they often encounter information distortion due to limitations in efficiently retaining information during the encoding-decoding process. Inspired by Multi-layer Heterogeneous Graph Transformer and Machine Learning XGboost classifier algorithm, this study introduces a novel computational approach based on multi-layer heterogeneous encoder-machine learning decoder structure for miRNA-disease association prediction (MHXGMDA). First, we employ the multi-view similarity matrices as the input coding for MHXGMDA. Subsequently, we utilize the multi-layer heterogeneous encoder to capture the embeddings of miRNAs and diseases, aiming to capture the maximum amount of relevant features. Finally, the information from all layers is concatenated to serve as input to the machine learning classifier, ensuring maximal preservation of encoding details. We conducted a comprehensive comparison of seven different classifier models and ultimately selected the XGBoost algorithm as the decoder. This algorithm leverages miRNA embedding features and disease embedding features to decode and predict the association scores between miRNAs and diseases. We applied MHXGMDA to predict human miRNA-disease associations on two benchmark datasets. Experimental findings demonstrate that our approach surpasses several leading methods in terms of both the area under the receiver operating characteristic curve and the area under the precision-recall curve.
(© 2024. The Author(s).)

Erratum in: Sci Rep. 2024 Oct 15;14(1):24181. doi: 10.1038/s41598-024-76003-x. (PMID: 39406809)

Neurochem Res. 2002 Oct;27(10):957-80. (PMID: 12462398)
Biochem Biophys Res Commun. 2005 Sep 9;334(4):1351-8. (PMID: 16039986)
BMC Bioinformatics. 2022 Jun 21;23(1):244. (PMID: 35729531)
Bioinformatics. 2021 Apr 9;37(1):66-72. (PMID: 32726399)
Pathol Res Pract. 2010 Aug 15;206(8):578-84. (PMID: 20418022)
J Transl Med. 2016 May 20;14(1):143. (PMID: 27197967)
IEEE/ACM Trans Comput Biol Bioinform. 2022 Jul-Aug;19(4):2049-2059. (PMID: 33735084)
Brief Bioinform. 2023 Mar 19;24(2):. (PMID: 36907654)
Interdiscip Sci. 2024 Jun;16(2):289-303. (PMID: 38286905)
Brief Bioinform. 2021 Jul 20;22(4):. (PMID: 33147616)
Biomed Eng Online. 2021 Feb 16;20(1):21. (PMID: 33593374)
IEEE Trans Cybern. 2022 Jun;52(6):5079-5087. (PMID: 33119529)
Brief Bioinform. 2023 Jul 20;24(4):. (PMID: 37332057)
Autoimmun Rev. 2006 May;5(5):299-305. (PMID: 16782553)
IEEE J Biomed Health Inform. 2024 Feb;28(2):1110-1121. (PMID: 38055359)
Noncoding RNA. 2024 Jan 26;10(1):. (PMID: 38392964)
Bioinformatics. 2013 Oct 15;29(20):2617-24. (PMID: 24002109)
Mol Oncol. 2016 Nov;10(9):1387-1403. (PMID: 27507538)
Bioinformatics. 2015 Jun 1;31(11):1805-15. (PMID: 25618864)
Cancer Manag Res. 2018 Oct 08;10:4267-4277. (PMID: 30349361)
Front Genet. 2019 Nov 12;10:1077. (PMID: 31781160)
BMC Endocr Disord. 2011 Mar 22;11:7. (PMID: 21426570)
Bioinformatics. 2019 Nov 1;35(22):4730-4738. (PMID: 31038664)
Mol Ther Nucleic Acids. 2018 Dec 7;13:568-579. (PMID: 30439645)
Adv Drug Deliv Rev. 2015 Jan;81:62-74. (PMID: 25450260)
BMC Med Inform Decis Mak. 2021 Apr 20;21(Suppl 1):133. (PMID: 33882934)
BMC Syst Biol. 2010 May 28;4 Suppl 1:S2. (PMID: 20522252)
IEEE Trans Neural Netw Learn Syst. 2023 Jul 17;PP:. (PMID: 37459265)
IEEE Trans Neural Netw Learn Syst. 2023 Sep;34(9):5570-5579. (PMID: 34860656)
IEEE J Biomed Health Inform. 2022 Jan;26(1):446-457. (PMID: 34111017)
Adv Genet. 2012;80:1-36. (PMID: 23084872)
Nucleic Acids Res. 2010 Jul;38(Web Server issue):W392-7. (PMID: 20478827)
Brief Bioinform. 2022 Sep 20;23(5):. (PMID: 35524503)
Int Rev Cell Mol Biol. 2016;324:125-85. (PMID: 27017008)
Bioinformatics. 2010 Jul 1;26(13):1644-50. (PMID: 20439255)
Comput Biol Med. 2024 Feb;169:107904. (PMID: 38181611)
Cancer Biol Med. 2015 Dec;12(4):328-41. (PMID: 26779370)
BMC Bioinformatics. 2021 Apr 28;22(1):219. (PMID: 33910505)
Cancers (Basel). 2021 Mar 30;13(7):. (PMID: 33808106)
Cell. 2004 Jan 23;116(2):281-97. (PMID: 14744438)
Bioinformatics. 2018 Jul 15;34(14):2425-2432. (PMID: 29490018)
IEEE/ACM Trans Comput Biol Bioinform. 2023 Mar-Apr;20(2):1041-1052. (PMID: 36049014)
Bioinform Adv. 2023 Dec 23;4(1):vbad190. (PMID: 38282976)
BMC Bioinformatics. 2022 May 4;23(1):160. (PMID: 35508967)
Congenit Anom (Kyoto). 2014 Feb;54(1):12-21. (PMID: 24330020)
Int J Mol Sci. 2020 Mar 03;21(5):. (PMID: 32138313)
Front Genet. 2014 Mar 18;5:54. (PMID: 24672539)

BDSY2023002 Anhui Provincial Engineering Laboratory for Beidou Precision Agriculture Information

Keywords: MiRNA-disease association prediction; Multi-layer heterogeneous encoder; Multi-view similarity networks; XGBoost decoder

0 (MicroRNAs)

Date Created: 20240903 Date Completed: 20240903 Latest Revision: 20241018

20250114

PMC11371806

10.1038/s41598-024-68897-4

39227405