GDCL-NcDA: identifying non-coding RNA-disease associations via contrastive learning between deep graph learning and deep matrix factorization

被引:5
作者
Ai, Ning [1 ,2 ]
Liang, Yong [1 ,3 ]
Yuan, Haoliang [4 ]
Ouyang, Dong [1 ,2 ]
Xie, Shengli [5 ]
Liu, Xiaoying [6 ]
机构
[1] Peng Cheng Lab, Shenzhen 518005, Guangdong, Peoples R China
[2] Macau Univ Sci & Technol, Sch Comp Sci & Engn, Ave Wai Long, Taipa, Peoples R China
[3] Pazhou Lab Huangpu, Guangzhou 510555, Guangdong, Peoples R China
[4] Guangdong Univ Technol, Sch Automation, Guangzhou 510006, Guangdong, Peoples R China
[5] Guangdong Univ Technol, Inst Intelligent Informat Proc, Guangzhou 510000, Guangdong, Peoples R China
[6] Guangdong Polytech Sci & Technol, Comp Engn Tech Coll, Zhuhai 519090, Guangdong, Peoples R China
关键词
Non-coding RNA-disease associations; Multi-source heterogenous networks; Contrastive learning; Deep graph learning; Deep matrix factorization; COMPREHENSIVE DATABASE; CIRCRNA; INFORMATION;
D O I
10.1186/s12864-023-09501-3
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Non-coding RNAs (ncRNAs) draw much attention from studies widely in recent years because they play vital roles in life activities. As a good complement to wet experiment methods, computational prediction methods can greatly save experimental costs. However, high false-negative data and insufficient use of multi-source information can affect the performance of computational prediction methods. Furthermore, many computational methods do not have good robustness and generalization on different datasets. In this work, we propose an effective end-to-end computing framework, called GDCL-NcDA, of deep graph learning and deep matrix factorization (DMF) with contrastive learning, which identifies the latent ncRNA-disease association on diverse multi-source heterogeneous networks (MHNs). The diverse MHNs include different similarity networks and proven associations among ncRNAs (miRNAs, circRNAs, and lncRNAs), genes, and diseases. Firstly, GDCL-NcDA employs deep graph convolutional network and multiple attention mechanisms to adaptively integrate multi-source of MHNs and reconstruct the ncRNA-disease association graph. Then, GDCL-NcDA utilizes DMF to predict the latent disease-associated ncRNAs based on the reconstructed graphs to reduce the impact of the false-negatives from the original associations. Finally, GDCL-NcDA uses contrastive learning (CL) to generate a contrastive loss on the reconstructed graphs and the predicted graphs to improve the generalization and robustness of our GDCL-NcDA framework. The experimental results show that GDCL-NcDA outperforms highly related computational methods. Moreover, case studies demonstrate the effectiveness of GDCL-NcDA in identifying the associations among diversiform ncRNAs and diseases.
引用
收藏
页数:17
相关论文
共 69 条
[1]   MHDMF: Prediction of miRNA-disease associations based on Deep Matrix Factorization with Multi-source Graph Convolutional Network [J].
Ai, Ning ;
Liang, Yong ;
Yuan, Hao-Laing ;
Ou-Yang, Dong ;
Liu, Xiao-Ying ;
Xie, Sheng-Li ;
Ji, Yu-Han .
COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 149
[2]   Multi-View Collaborative Network Embedding [J].
Ata, Sezin Kircali ;
Fang, Yuan ;
Wu, Min ;
Shi, Jiaqi ;
Kwoh, Chee Keong ;
Li, Xiaoli .
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2021, 15 (03)
[3]   LncRNADisease 2.0: an updated database of long non-coding RNA-associated diseases [J].
Bao, Zhenyu ;
Yang, Zhen ;
Huang, Zhou ;
Zhou, Yiran ;
Cui, Qinghua ;
Dong, Dong .
NUCLEIC ACIDS RESEARCH, 2019, 47 (D1) :D1034-D1037
[4]  
Charikar M. S., 2002, Proceedings Of The Thiry-Fourth Annual ACM Symposium On Theory Of Computing, STOC '02, P380, DOI DOI 10.1145/509907.509965
[5]   Circular RNA: An emerging non-coding RNA as a regulator and biomarker in cancer [J].
Chen, Bing ;
Huang, Shenglin .
CANCER LETTERS, 2018, 418 :41-50
[6]   LncRNADisease: a database for long-non-coding RNA-associated diseases [J].
Chen, Geng ;
Wang, Ziyun ;
Wang, Dongqing ;
Qiu, Chengxiang ;
Liu, Mingxi ;
Chen, Xing ;
Zhang, Qipeng ;
Yan, Guiying ;
Cui, Qinghua .
NUCLEIC ACIDS RESEARCH, 2013, 41 (D1) :D983-D986
[7]  
Chen Ming, 2020, P MACHINE LEARNING R, V119
[8]   MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction [J].
Chen, Xing ;
Yin, Jun ;
Qu, Jia ;
Huang, Li .
PLOS COMPUTATIONAL BIOLOGY, 2018, 14 (08)
[9]   Biopython']python: freely available Python']Python tools for computational molecular biology and bioinformatics [J].
Cock, Peter J. A. ;
Antao, Tiago ;
Chang, Jeffrey T. ;
Chapman, Brad A. ;
Cox, Cymon J. ;
Dalke, Andrew ;
Friedberg, Iddo ;
Hamelryck, Thomas ;
Kauff, Frank ;
Wilczynski, Bartek ;
de Hoon, Michiel J. L. .
BIOINFORMATICS, 2009, 25 (11) :1422-1423
[10]   MNDR v2.0: an updated resource of ncRNA-disease associations in mammals [J].
Cui, Tianyu ;
Zhang, Lin ;
Huang, Yan ;
Yi, Ying ;
Tan, Puwen ;
Zhao, Yue ;
Hu, Yongfei ;
Xu, Liyan ;
Li, Enmin ;
Wang, Dong .
NUCLEIC ACIDS RESEARCH, 2018, 46 (D1) :D371-D374