电子学报 ›› 2022, Vol. 50 ›› Issue (6): 1428-1435.DOI: 10.12263/DZXB.20201116

• 学术论文 • 上一篇    下一篇

基于异质图注意力网络的miRNA与疾病关联预测算法

李政伟1,2, 李佳树1,2, 尤著宏3, 聂茹2, 赵欢2, 钟堂波2   

  1. 1.中国矿业大学矿山数字化教育部工程研究中心,江苏 徐州 221116
    2.中国矿业大学计算机科学与技术学院,江苏 徐州 221116
    3.西北工业大学计算机学院,陕西 西安 710129
  • 收稿日期:2020-10-12 修回日期:2021-04-08 出版日期:2022-06-25
    • 通讯作者:
    • 聂茹
    • 作者简介:
    • 李政伟 男,1977年生,河南许昌人.博士.现为中国矿业大学计算机科学与技术学院副教授、硕士生导师.主要研究方向为机器学习与模式识别、生物信息学、计算机视觉等.E-mail: zwli@cumt.edu.cn
      李佳树 男,1998年生,江苏徐州人.现为中国矿业大学计算机科学与技术学院研究生.主要研究方向为图神经网络、miRNA与疾病的关联预测等.E-mail: lijiashu7646@163.com
      尤著宏 男,1980年生,甘肃兰州人.博士.现为西北工业大学计算机学院教授,博士生导师.主要研究方向为大数据分析、数据挖掘及在生物信息学上的应用等.E-mail: zhuhongyou@nwpu.edu.cn
      聂 茹(通讯作者) 女,1976年生,江苏徐州人.博士.现为中国矿业大学计算机科学与技术学院副教授,硕士生导师.主要研究方向为生物信息学、机器学习和图像处理等. E-mail:nr@cumt.edu.cn
    • 基金资助:
    • 国家自然科学基金 (61732012); 科技创新2030—“新一代人工智能”重大项目 (2018AAA0100100)

Associations Prediction Algorithm of MiRNAs and Diseases Based on Heterogeneous Graph Attention Network

LI Zheng-wei1,2, LI Jia-shu1,2, YOU Zhu-hong3, NIE Ru2, ZHAO Huan2, ZHONG Tang-bo2   

  1. 1.Engineering Research Center of Mine Digitalization of Ministry of Education, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China
    2.School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China
    3.School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi 710129, China
  • Received:2020-10-12 Revised:2021-04-08 Online:2022-06-25 Published:2022-06-25
    • Corresponding author:
    • NIE Ru
    • Supported by:
    • National Natural Science Foundation of China (61732012); National Science and Technology Innovation 2030 -- Major program of New generation of artificial intelligence (2018AAA0100100)

摘要:

众多实验表明,microRNA(miRNA)的异常表达与人类复杂疾病的产生和演化有关.识别miRNA与疾病间的关联有助于促进临床医学的发展.然而,传统的实验方法往往耗时耗力、效率低下,因此迫切需要高效的计算方法对miRNA与疾病间的潜在关联进行预测.本文提出了一种基于异质图注意力网络的端到端的计算模型来预测miRNA与疾病的关联.该方法通过多头注意力机制捕获异质邻居的结构和属性信息,并将其与中心顶点的属性信息进行融合,从而构建出更具表达能力的miRNA和疾病的特征嵌入,进而通过全连接层对miRNA与疾病间的潜在关联进行预测.5折交叉验证结果显示,该模型分别在HMDD v2.0和HMDD v3.0数据集上取得了93.52%和94.82%的AUC值.此外,关于食管肿瘤的病例研究结果显示,该模型预测的前50个miRNA中有48个得到了证实.上述实验结果表明,该模型可作为一种可靠的工具预测候选疾病的相关miRNA.

关键词: 图注意力网络, miRNA-疾病关联, 异质图, 深度学习

Abstract:

Lots of experiments have shown that the abnormal expression of microRNA(miRNA) is related to the evolution and progression of human complex diseases. Identifying associations between miRNAs and diseases is beneficial to promote the development of clinical medicine. However, traditional experimental methods are often time-consuming and inefficient, so there is an urgent need for efficient computational methods to predict the potential associations between miRNAs and diseases. In this paper, we propose an end-to-end computational model based on heterogeneous graph attention network to predict the associations between miRNAs and diseases. This model captures the structure and attribute information of heterogeneous neighbors via the multi-head attention mechanism, and fuses them with the attribute information of the central vertex to generate more representative feature embeddings of miRNAs and diseases, and then predicts the potential associations between miRNAs and diseases through a fully connected layer. The 5-fold cross-validation results show that our model achieves 93.52% and 94.82% AUC values based on HMDD v2.0 and HMDD v3.0 datasets, respectively. In addition, the case study on esophageal neoplasms shows that 48 of the top 50 miRNAs predicted by our model are confirmed. The above experimental results indicate that our model can be used as a reliable tool to predict candidate disease-related miRNAs.

Key words: graph attention network, microRNA-disease associations, heterogeneous graph, deep learning

中图分类号: