A Method for Predicting Disease-Related MicroRNAs Based on Topological Information

GAO Peng; CHEN Zhi-hua

doi:10.3969/j.issn.0372-2112.2020.02.016

您当前的位置：

首页 >

文章列表页 >

A Method for Predicting Disease-Related MicroRNAs Based on Topological Information

更新时间：2025-07-16

- A Method for Predicting Disease-Related MicroRNAs Based on Topological Information
- Acta Electronica Sinica Vol. 48, Issue 2, Pages: 333-340(2020)
- 作者机构：
  
  1. 华中科技大学人工智能与自动化学院,湖北,武汉,430074
  2. 广州大学计算科技研究院,广东,广州,510006
  3. 华中科技大学人工智能与自动化学院,湖北,武汉,430074
  4. 广州大学计算科技研究院,广东,广州,510006
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61876047, No.61702200)
- DOI：10.3969/j.issn.0372-2112.2020.02.016
  CLC： TP18
- Published Online：25 February 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
GAO Peng, CHEN Zhi-hua. A Method for Predicting Disease-Related MicroRNAs Based on Topological Information[J]. Acta Electronica Sinica, 2020, 48(2): 333-340.
DOI：

GAO Peng, CHEN Zhi-hua. A Method for Predicting Disease-Related MicroRNAs Based on Topological Information[J]. Acta Electronica Sinica, 2020, 48(2): 333-340. DOI： 10.3969/j.issn.0372-2112.2020.02.016.

摘要

研究表明，micRNAs（miRNA）突变或者异常会导致多种疾病，鉴定出与疾病相关的microRNA可以帮助诊断和治疗相关疾病.然而，通过生物实验方式获取准确关联关系，花费大，而且周期长.因此，本文中提出了一种基于网络内部拓扑信息的机器学习方法（HNDLM）预测疾病-miRNA关联关系.HNDLM避免搭建相似网络，而是将近年提出的network embedding方法应用在生物网络上.实验结果显示，HNDLM相较于MIDPE，MIDP，WBSMDA，RLSMDA，CPTL，HDMP经典算法在准确率和AUC值上效果更好.此外，在案例学习中，HNDLM推荐的前30个候选miRNAs，基本都能通过先前实验得到证实，HNDLM能发现潜在疾病-miRNA关系，有助于进一步研究疾病发病机制，推动生物信息学发展.

Abstract

Studies show that mutations or abnormalities in micRNAs can lead to many diseases

and the identification of disease-associated microRNAs (miRNAs) can help diagnose and treat related diseases. However

it is costly and long-term to obtain accurate correlations through biological experiments. Therefore

this paper proposes a machine learning method (HNDLM) that uses network topology information to predict disease-miRNA associations. HNDLM avoids the construction of similarity networks

but applies the network embedding method proposed in recent years to biological networks. Experimental results show that HNDLM performs better than MIDPE

MIDP

WBSMDA

RLSMDA

CPTL

HDMP classical algorithms in accuracy and AUC value. In case study

the top 30 candidate miRNAs recommended by HNDLM can be confirmed by previous experiments. HNDLM can discover the potential disease-miRNA relationship and help to further study the pathogenesis of the disease

promote the development of bioinformatics.

关键词

Keywords

references

Views

111

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Detection Method for Android Repackaged Malware Based on Sensitive Component Function Call Graph

Individual Random Walks for Gene-Phenotype Association Analysis

Research on High-Efficiency Integrated Circuit DFT Technology Based on Machine Learning

DRHA-UIE: An Underwater Image Enhancement Method Based on Dual Residual Hybrid Attention Block

Cognitive Learning: A New Paradigm for Machine Learning in Electromagnetic Spectrum Environment

Related Author

DU Rui-ying

CHEN Jing

WU Cong

YAN Xi-yu

TAN Hao-jiang

WANG Jun

YU Guo-xian

CHEN Jian

Related Institution

School of Computer and Information Engineering, Henan Normal University

School of Cyber Science and Engineering, Wuhan University

Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, Wuhan University

Rizhao Institute of Information Technology, Wuhan University

Department of Electrical and Electronic Engineering, Faculty of Engineering, The University of Hong Kong

⁰