Login Register Cart 0
Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Mini-Review Article

Graph Neural Networks in Biomedical Data: A Review

Author(s): You Li, Guiyang Zhang, Pan Wang, Zuo-Guo Yu and Guohua Huang*

Volume 17, Issue 6, 2022

Published on: 08 June, 2022

Page: [483 - 492] Pages: 10

DOI: 10.2174/1574893617666220513114917

Price: $65

Abstract

With the development of sequencing technology, various forms of biomedical data, including genomics, transcriptomics, proteomics, microbiomics, and metabolomics data, are increasingly emerging. These data are an external manifestation of cell activity and mechanism. How to deeply analyze these data is critical to uncovering and understanding the nature of life. Due to the heterogeneousness and complexity of these data, it is a vastly challenging task for traditional machine learning to deal with it. Over the recent ten years, a new machine learning framework called graph neural networks (GNNs) has been proposed. The graph is a very powerful tool to represent a complex system. The GNNs is becoming a key to open the mysterious door of life. In this paper, we focused on summarizing state-ofthe- art GNNs algorithms (GraphSAGE, graph convolutional network, graph attention network, graph isomorphism network and graph auto-encoder), briefly introducing the main principles behind them. We also reviewed some applications of the GNNs to the area of biomedicine, and finally discussed the possible developing direction of GNNs in the future.

Keywords: Graph neural networks, graph convolutional network, graph attention network, graph auto-encoder, biomedical data, disease prediction.

Next »
[1]
Goecks J, Jalili V, Heiser LM, Gray JW. How machine learning will transform biomedicine. Cell 2020; 181(1): 92-101.
[http://dx.doi.org/10.1016/j.cell.2020.03.022]
[2]
Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv 2016; 2016: 1609.02907.
[3]
Zhou J, Cui G, Zhang Z, et al. Graph neural networks: A review of methods and applications. arXiv 2018; 2018: 1812.08434.
[4]
Kampffmeyer M, Chen Y, Liang X, Wang H, Zhang Y, Xing EP. Rethinking knowledge graph propagation for zero-shot learning. arXiv 2019; 2019: 1805.11724.
[http://dx.doi.org/10.1109/CVPR.2019.01175]
[5]
Zhang Y, Xiong Y, Kong X, Li S, Mi J, Zhu Y. Deep collective classification in heterogeneous information networks. WWW '18 Proc World Wide Web Conf 2018; 2018: 399-408.
[http://dx.doi.org/10.1145/3178876.3186106]
[6]
Wang X, Ji H, Shi C, et al. Heterogeneous graph attention network. arXiv 2019; 2019: 1903.07293.
[http://dx.doi.org/10.1145/3308558.3313562]
[7]
Beck D, Haffari G, Cohn T. Graph-to-sequence learning using gated graph neural networks. arXiv 2018; 2018: 1806.09835.
[8]
Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, Welling M. Modeling relational data with graph convolutional networks. In: European semantic web conference. In: Springer 2018; pp. 593-607.
[http://dx.doi.org/10.1007/978-3-319-93417-4_38]
[9]
Li Y, Yu R, Shahabi C, Liu Y. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv 2017; 2017: 1707.01926.
[10]
Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv 2017; 2017: 1709.04875.
[11]
Jain A, Zamir AR, Savarese S, Saxena A. Structural-rnn: Deep learning on spatio-temporal graphs. arXiv 2017; 2017: 1511.05298.
[12]
Yan S, Xiong Y, Lin D. Spatial temporal graph convolutional networks for skeleton-based action recognition. arXiv 2018; 2018: 1801.07455.
[13]
Hamilton WL, Ying R, Leskovec J. Inductive representation learning on large graphs. arXiv 2017; 2017: 1706.02216.
[14]
Chen J, Ma T, Xiao C. Fastgcn: fast learning with graph convolutional networks via importance sampling. arXiv 2018; 2018: 1801.10247.
[15]
Li R, Wang S, Zhu F, Huang J. Adaptive graph convolutional neural networks. arXiv 2018; 2018: 1801.03226.
[16]
Ying R, He R, Chen K, Eksombatchai P, Hamilton WL, Leskovec J. Graph convolutional neural networks for web-scale recommender systems. arXiv 2018; 2018: 1806.01973.
[http://dx.doi.org/10.1145/3219819.3219890]
[17]
Dai H, Kozareva Z, Dai B, Smola A, Song L. Learning steady-states of iterative algorithms over graphs. PMLR 2018; 80: 1106-14.
[18]
Chen J, Zhu J, Song L. Stochastic training of graph convolutional networks with variance reduction. arXiv 2017; 2017: 1710.10568.
[19]
Li Q, Han Z, Wu X-M. Deeper insights into graph convolutional networks for semi-supervised learning. arXiv 2018; 2018: 1801.07606.
[20]
Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS. A comprehensive survey on graph neural networks. arXiv 2019; 2019: 1901.00596.
[PMID: 32217482]
[21]
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G. The graph neural network model. JItonn 2008; 20(1): 61-80.
[22]
Gallicchio C, Micheli A. Graph echo state networks. In: The 2010 International Joint Conference on Neural Networks (IJCNN). Barcelona, Spain 2010; pp. 18-23.
[http://dx.doi.org/10.1109/IJCNN.2010.5596796]
[23]
Bruna J, Zaremba W, Szlam A, LeCun Y. Spectral networks and locally connected networks on graphs. arXiv 2013; 2013: 1312.6203.
[24]
Micheli A. Neural network for graphs: A contextual constructive approach. IEEE Trans Neural Networks 2009; 20(3): 498-511.
[25]
Cao S, Lu W, Xu Q. Deep neural networks for learning graph representations. Proc AAAI Conf Artif Intell 2016 2016; 1145-52.
[26]
Wang D, Cui P, Zhu W. Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 2016 August 13-17; San Francisco, California, USA;. pp. 1225-.
[http://dx.doi.org/10.1145/2939672.2939753]
[27]
Li Y, Vinyals O, Dyer C, Pascanu R, Battaglia P. Learning deep generative models of graphs. arXiv 2018; 2018: 1803.03324.
[28]
Seo Y, Defferrard M, Vandergheynst P, Bresson X. Structured sequence modeling with graph convolutional recurrent networks. arXiv 2016; 2016-1612.07659.
[http://dx.doi.org/10.1007/978-3-030-04167-0_33]
[29]
Zhang Z, Cui P, Zhu W, Engineering D. Deep learning on graphs. Survey (Lond) 2020; 14(8): 1-24.
[30]
Yuting L, Ming Z, Chicheng M, et al. Graph neural network. Sci Sin Math 2020; 50(3): 367.
[http://dx.doi.org/10.1360/N012019-00133]
[31]
Bacciu D, Errica F, Micheli A, Podda MJNN. A gentle introduction to deep learning for graphs. arXiv 2019; 2019: 1912.12693.
[http://dx.doi.org/10.1016/j.neunet.2020.06.006]
[32]
Sato R. A survey on the expressive power of graph neural networks arXiv 2020; 2020: 2003.04078.
[33]
Kinderkhedia M. Learning representations of graph data. arXiv 2019; 2019: 1906.0298.
[34]
Grover A, Leskovec J. node2vec: Scalable feature learning for networks. arXiv 2016; 2016: 1607.00653.
[http://dx.doi.org/10.1145/2939672.2939754]
[35]
Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations. arXiv 2014; 2014: 1403.6652.
[http://dx.doi.org/10.1145/2623330.2623732]
[36]
Gori M, Monfardini G, Scarselli F. A new model for learning in graph domains. In: Proceedings 2005 IEEE International Joint Conference on Neural Networks;. Montreal, QC, Canada 2005; 31-4: pp. 729-34.
[http://dx.doi.org/10.1109/IJCNN.2005.1555942]
[37]
Atwood J, Towsley D. Diffusion-convolutional neural networks. In: Advances in neural information processing systems NeurIPS Proc. 2016; 2016: p. 1993-2001.
[38]
Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. arXiv 2016; 2016: 1606.09375.
[39]
Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks? arXiv 2018; 2018: 1810.00826.
[40]
Zhuang C, Ma Q. Dual graph convolutional networks for graph-based semi-supervised classification. WWW '18 Proc World Wide Web Conf 2018; 2018: 499-508.
[http://dx.doi.org/10.1145/3178876.3186116]
[41]
Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. arXiv 2017; 2017: 1710.10903.
[42]
Li Y, Tarlow D, Brockschmidt M, Zemel R. Gated graph sequence neural networks. arXiv 2015; 2015: 1511.05493.
[43]
Kipf TN, Welling M. Variational graph auto-encoders. arXiv 2016; 2016: 1611.07308.
[44]
Pan S, Hu R, Long G, Jiang J, Yao L, Zhang C. Adversarially regularized graph autoencoder for graph embedding. arXiv 2018; 2018: 1802.04407.
[45]
Tu K, Cui P, Wang X, Yu PS, Zhu W. Deep recursive network embedding with regular equivalence. WWW '18 Proc World Wide Web Conf 2018; 2018: 2357-66.
[http://dx.doi.org/10.1145/3219819.3220068]
[46]
Yu W, Zheng C, Cheng W, et al. Learning deep network representations with adversarially regularized autoencoders. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London, UK 2018; 19: pp. (23)2663-71.
[http://dx.doi.org/10.1145/3219819.3220000]
[47]
Wu F, Souza A, Zhang T, Fifty C, Yu T, Weinberger K. Simplifying graph convolutional networks. PMLR 2019; 97: 6861-71.
[48]
Tai KS, Socher R, Manning CD. Improved semantic representations from tree-structured long short-term memory networks. arXiv 2015; 2015: 1503.00075.
[49]
Sabour S, Frosst N, Hinton GE. Dynamic routing between capsules. arXiv 2017; 2017: 1710.09829.
[50]
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. arXiv 2017; 2017: 1706.03762.
[51]
Fey M, Lenssen JE. Fast graph representation learning with PyTorch Geometric. arXiv 2019; 2019: 1903.02428.
[52]
Guan C, Zhang Z, Li H, et al. AutoGL: A Library for Automated Graph Learning. arXiv 2021; 2021: 2104.04987.
[53]
Wang M, Zheng D, Ye Z, et al. Deep graph library: A graphcentric, highly-performant package for graph neural networks. arXiv 2019; 2019: 1909.01315.
[54]
Li J, Xu K, Chen L, Zheng Z, Liu X. GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software. arXiv 2021; 2021: 2102.07933.
[55]
Shin SY, Lee S, Yun ID, Lee KM. Deep vessel segmentation by learning graphical connectivity. JMIA 2019; 58: 101556.
[56]
Zhai Z, Staring M, Zhou X, et al. Linking convolutional neural networks with graph convolutional networks: Application in pulmonary artery-vein separation. Graph Learn Med Imag 2019; 2019: 36-43.
[http://dx.doi.org/10.1007/978-3-030-35817-4_5]
[57]
Yang H, Zhen X, Chi Y, Zhang L, Hua X-S. CPR-GCN: Conditional partial-residual graph convolutional network in automated anatomical labeling of coronary arteries. arXiv 2020; 2020: 2003.08560.
[http://dx.doi.org/10.1109/CVPR42600.2020.00386]
[58]
Zhou C. A hybrid approach for coronary artery anatomical labeling in cardiac CT angiography. J Phys Conf Ser 2020; 2020: 1642.
[http://dx.doi.org/10.1088/1742-6596/1642/1/012020]
[59]
Wang S, Xu Z, Yan C, Huang J. Graph convolutional nets for tool presence detection in surgical videos. In: Chung A, Gee J, Yushkevich P, Bao S, Eds. Information processing in medical imaging lecture notes in computer science. Springer, Cham 2019.
[http://dx.doi.org/10.1007/978-3-030-20351-1_36]
[60]
Yang H, Li X, Wu Y, et al. Interpretable multimodality embedding of cerebral cortex using attention graph network for identifying bipolar disorder. bioRxiv 2019. Available from: https://www.biorxiv.org/content/10.1101/671339v1.full.pdf
[61]
Zhao T, Hu Y, Peng J, Cheng L. GCN-CNN: A novel deep learning method for prioritizing lncRNA target genes. Bioinformatics 2020; 2020: btaa428.
[http://dx.doi.org/10.1093/bioinformatics/btaa428]
[62]
Pan X, Shen H-BJI. Inferring disease-associated microRNAs using semi-supervised multi-label graph convolutional networks. iScience 2019; 20: 265-77.
[http://dx.doi.org/10.1016/j.isci.2019.09.013]
[63]
Li J, Li Z, Nie R, You Z, Bao W. FCGCNMDA: predicting miRNA-disease associations by applying fully connected graph convolutional networks. Mol Genet Genom 2020; 295(5): 1197-209.
[http://dx.doi.org/10.1007/s00438-020-01693-7]
[64]
O'Neil NJ, Bailey ML, Hieter P. Synthetic lethality and cancer. JNRG 2017; 18(10): 613-23.
[http://dx.doi.org/10.1038/nrg.2017.47]
[65]
Cai R, Chen X, Fang Y, Wu M, Hao Y. Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers. Bioinformatics 2020; 36(16): 4458-65.
[http://dx.doi.org/10.1093/bioinformatics/btaa211] [PMID: 32221609]
[66]
Wang L, You Z-H, Li Y-M, Zheng K, Huang Y-A. GCNCDA: A new method for predicting circRNA-disease associations based on Graph Convolutional Network Algorithm. PLOS Comput Biol 2020; 16(5): e1007568.
[http://dx.doi.org/10.1371/journal.pcbi.1007568] [PMID: 32433655]
[67]
Parisot S, Ktena SI, Ferrante E, et al. Spectral graph convolutions for population-based disease prediction. In: International conference on medical image computing and computer-assisted intervention. Springer 2017; pp. 177-85.
[http://dx.doi.org/10.1007/978-3-319-66179-7_21]
[68]
Parisot S, Ktena SI, Ferrante E, et al. Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer’s disease. Med Image Anal 2018; 48: 117-30.
[http://dx.doi.org/10.1016/j.media.2018.06.001] [PMID: 29890408]
[69]
Kazi A, Shekarforoush S, Kortuem K, Albarqouni S, Navab N. Self-attention equipped graph convolutions for disease prediction. arXiv 2018; 2018: 1812.09954.
[http://dx.doi.org/10.1109/ISBI.2019.8759274]
[70]
Zhang J, Hu X, Jiang Z, Song B, Quan W, Chen Z. Predicting disease-related RNA associations based on graph convolutional attention network. 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 177-82.
[http://dx.doi.org/10.1109/BIBM47256.2019.8983191]
[71]
Singh V, Lio P. Towards probabilistic generative models harnessing graph neural networks for disease-gene prediction. arXiv 2019; 2019: 1907.05628.
[72]
Li C, Liu H, Hu Q, Que J, Yao J. A novel computational model for predicting microRNA–disease associations based on heterogeneous graph convolutional networks. Cells 2019; 8(9): 977.
[http://dx.doi.org/10.3390/cells8090977] [PMID: 31455028]
[73]
Sun Z, Yin H, Chen H, Chen T, Cui L, Yang F. Disease prediction via graph neural networks. IEEE J Biomed Health Inform 2020; 25(3): 818-26.
[PMID: 32749976]
[74]
Zhang J, Jiang Z, Hu X, Song B. A novel graph attention adversarial network for predicting disease-related associations. Methods 2020; 179: 81-8.
[http://dx.doi.org/10.1016/j.ymeth.2020.05.010] [PMID: 32446956]
[75]
Sun M, Zhao S, Gilvary C, Elemento O, Zhou J, Wang F. Graph convolutional networks for computational drug development and discovery. JBib 2020; 21(3): 919-35.
[76]
Chen X, Liu X, Wu J. GCN-BMP: Investigating graph representation learning for DDI prediction task. Methods 2020; 179: 47-54.
[http://dx.doi.org/10.1016/j.ymeth.2020.05.014] [PMID: 32622985]
[77]
Zhao D, Wang J, Lin H, Yang Z, Zhang Y. Extracting drug–drug interactions with hybrid bidirectional gated recurrent unit and graph convolutional network. IEEE J Biomed Health Inform 2019; 99: 103295.
[78]
Park C, Park J. AGCN: Attention-based graph convolutional networks for drug-drug interaction extraction. JESwA 2020; 113538.
[79]
Feng Y-H, Zhang S-W, Shi J-Y. DPDDI: A deep predictor for drug-drug interactions. BMC Bioinform 2020; 21(1): 419.
[80]
Zhao T, Hu Y, Valsdottir LR, Zang T, Peng J. Identifying drug–target interactions based on graph convolutional network and deep neural network. Brief Bioinform 2021; 22(2): 2141-50.
[81]
Nguyen T, Le H, Venkatesh SJB. GraphDTA: Prediction of drug–target binding affinity using graph convolutional networks. Bioinformatics 2021; 37(8): 1140-7.
[82]
Jiang M, Li Z, Zhang S, et al. Drug–target affinity prediction using graph neural network and contact maps JRA 2020; 10(35): 20701-12.
[http://dx.doi.org/10.1039/D0RA02297G]
[83]
Wang Z, Zhou M, Arnold CJB. Toward heterogeneous information fusion: bipartite graph convolutional networks for in silico drug repurposing. JB 2020; 36(Suppl. 1): i525-33.
[http://dx.doi.org/10.1093/bioinformatics/btaa437]
[84]
Liu Q, Hu Z, Jiang R, Zhou MJB. DeepCDR: A hybrid graph convolutional network for predicting cancer drug response. JB 2020; 36(Suppl. 2): i911-8.
[http://dx.doi.org/10.1093/bioinformatics/btaa822]
[85]
Nguyen TT, Nguyen T, Le D-H. Graph convolutional networks for drug response prediction. IEEE/ACM Trans Comput Biol Bioinform 2022; 19(1): 146-54.
[http://dx.doi.org/10.1101/2020.04.07.030908]
[86]
Long Y, Wu M, Kwoh CK, Luo J, Li X. Predicting human microbe–drug associations via graph convolutional network with conditional random field. Bioinformatics 2020; 36(19): 4918-27.

Rights & Permissions Print Cite
Article Metrics
53
3
© 2024 Bentham Science Publishers | Privacy Policy