Biyoinformatik Alanında Graf Uygulamaları
Özet
Bu çalışma, biyoinformatik alanında hızla artan karmaşık verilerin analizinde geleneksel yöntemlerin yetersiz kalması nedeniyle graf teorisi ve graf sinir ağları (GSA) yöntemlerine olan yönelimi ve bu alandaki güncel uygulamaları ayrıntılı şekilde incelemektedir. Disiplinlerarası bir bilim dalı olan biyoinformatik; genomik ve proteomik çalışmaları başta olmak üzere protein fonksiyonu, gen fonksiyonu ve ilaç hedefi belirleme gibi hayati öneme sahip pek çok alanı kapsamaktadır. Gerçek hayattaki karmaşık sistemleri modelleyen graf teorisi, biyolojik problemleri çözmek amacıyla ikili biyolojik graflar, çok ilişkisel biyolojik graflar ve çok modlu biyomedikal bilgi grafları olarak üç ana kategoride ele alınmaktadır. Derin öğrenmeye dayalı graf sinir ağları ve graf evrişimsel sinir ağları ise komşuluk ve topoloji özelliklerini kodlayarak yapısal verileri başarıyla analiz etmektedir. Yazı kapsamında; GLINTER yöntemiyle yürütülen protein-protein arayüzey temas tahmini, Graph Site yöntemiyle yapılan protein-DNA bağlanma bölgelerinin keşfi, BridgeDPI modeliyle ilaç-protein etkileşimlerinin tahmini, miRNA-hastalık ilişkilerinin tespiti, graf enerji sinir ağlarıyla ilaç-ilaç korelasyonlarının çözülmesi ile gen-hastalık ve gen-gen etkileşim ağları üzerinden yürütülen kanser sınıflandırma çalışmaları detaylandırılmıştır. Sonuç olarak graf teorisi, karmaşık biyolojik ağların gizli ve yapısal özelliklerini keşfetmede, yeni ilaç tasarımlarında ve hastalık tanılarında son derece başarılı ve verimli bir hesaplama yöntemi sunmaktadır.
This study examines the trend toward graph theory and graph neural network (GNN) methods due to the insufficiency of traditional methods in analyzing rapidly increasing complex data in the field of bioinformatics, and reviews current applications in detail. Bioinformatics, an interdisciplinary field, covers vital areas such as protein function, gene function, and drug target identification, particularly genomics and proteomics studies. Graph theory, which models complex real-world systems, is categorized into three main areas to solve biological problems: bipartite biological graphs, multirelational biological graphs, and multimodal biomedical knowledge graphs. Deep learning-based graph neural networks and graph convolutional networks successfully analyze structural data by encoding neighborhood and topology features. Within the scope of the text, applications such as inter-protein interfacial contact prediction via GLINTER, protein-DNA binding site discovery via Graph Site, drug-protein interaction prediction via BridgeDPI, miRNA-disease association detection, solving drug-drug correlations with graph energy neural networks, and cancer classification studies conducted through gene-disease and gene-gene interaction networks are detailed. In conclusion, graph theory provides a highly successful, efficient, and computational method for discovering the hidden structural properties of complex biological networks, designing new drugs, and diagnosing diseases.
Referanslar
G. Keklik, B. D. Özcan, Multidisipliner bir bilim dalı olarak biyoinformatiğe genel bir bakış, Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 5(2), 1091-1082, 2022
A. C. Akın, B. Bürçe, B. Çevirici, B. Şahin, E. Şahin, Y. Şahin, Disiplinler arası bir bilim dalı: biyoinformatik, Erişim Tarihi: 20/12/2020 Web adresi: http://tip.baskent.edu.tr/kw/upload/464/dosyalar/cg/sempozyum/ogrsmpzsnm16/16.P12.pdf
J, Gao, T. Lyu, F. Xiong, J. Wang, W. Ke, Z. Li, MGNN: A multimodal graph neural network for predicting the survival of cancer patients, 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Şian (Xi’an), Çin, 2020.
B. L. Hie, K. K. Yang, Adaptive machine learning for protein engineering, Current Opinion In Structural Biology, 72, 152-145, 2022.
P. J. Artymiuk, D. W. Rice, E. M. Mitchell, P. Willett. Structural resemblance between the families of bacterial signal-transduction proteins and of G proteins revealed by graph theoretical techniques, Protein Engineering, Design and Selection, 4(1), 43-39, 1990.
M. Habibi, C. Eslahchi, M. Sadeghi, H. Pezashk, The interpretation of protein structures based on graph theory and contact map, Open Access Bioinformatics, 2, 137-127, 2019.
N. Biggs, E. Lloyd, R. Wilson, Bölüm 1: Paths, Graph Theory, Oxford University Press.A, 1936-1736, 1986.
Simple English Wikipedia, the free encyclopedia, Seven Bridges of Königsberg Erişim tarihi: 10/12/2022, Web adresi: https://simple.wikipedia.org/wiki/Seven_Bridges_ofK%C3%B6nigsberg
H. C. Yi, Z. H. You, D. S. Huang, C. K. Kwoh, Graph representation learning in bioinformatics: trends, methods and applications, Briefings in Bioinformatics, 23(1), bbab340, 2022.
Z. Liu, J. Zhou, Introduction to graph neural networks, Synthesis Lectures on Artificial Intelligence and Machine Learning, 14(2), 127-1, 2020.
Z. Ye, Y. J. Kumar, G. O. Sing, F. Song, J. Wang, A comprehensive survey of graph neural networks for knowledge graphs, IEEE Access, 10, 75741-75729, 2022.
M. Zhang, H. Luo, W. Song, H. Mei, C. Su, Spectral-Spatial offset graph convolutional networks for hyperspectral image classification, Remote Sensing, 13(21), 4342, 2021.
X. Zheng, Y. Liu, S. Pan, M. Zhang, D. Jin, P. S. Yu, Graph neural networks for graphs with heterophily: A survey, arXiv:2202.07082, Erişim Tarihi:15/12/2022, https://arxiv.org/pdf/2202.07082.pdf.
E. Burgos, H. Ceva, L, Hernandez, RP, Perazzo, M, Devoto, D, Medan, Two classes of bipartite networks: nested biological and social systems, Physical Review E, Statistical, Nonlinear, and Soft Matter Physics, 78(4), 046113, 2008.
E. Khaledian, A. H. Gebremedhin, K. A. Brayton, S. L. Broschat, A network science approach for determining the ancestral phylum of bacteria, 2018 ACM International Conference On Bioinformatics, Computational Biology, and Health Informatics, 403-398, 2018.
V. N. Ioannidis, A. G. Marques, G. B. Giannakis, Tensor graph convolutional networks for multi-relational and robust learning, IEEE Transactions on Signal Processing, 68, 6546-6535, 2020.
D. Davis, N. Chawla, Exploring and exploiting disease interactions from multi-relational gene and phenotype networks, PLoS One, 6, 2011.
C. Zhu, Z. Yang, X. Xia, N. Li, F. Zhong, L. Liu, Multimodal reasoning based on knowledge graph embedding for specific diseases, Bioinformatics, 38(8), 2245-2235, 2022.
M. Nickel, K. Murphy, V. Tresp, E. Gabrilovich, A review of relational machine learning for knowledge graphs, Proceedings of the IEEE, 104(1), 33-11, 2015.
M. Alshahrani, M. A. Thafar, M. Essack, Application and evaluation of knowledge graph embeddings in biomedical data, PeerJ Computer Science, 7, e341, 2021.
X. Zhu, Z. Li, X. Wang, X., Jiang, P. Sun, X. Wang, N. J. Yuan, Multi-Modal Knowledge Graph Construction and Application: A Survey, arXiv:2202.05786, Erişim Tarihi:15/12/2022, https://arxiv.org/pdf/2202.05786.pdf, 2022.
Q. Yuan, S. Chen, J. Rao, S. Zheng, H. Zhao, H, Y. Yang, AlphaFold2-aware protein–DNA binding site prediction using graph transformer, Briefings in Bioinformatics, 23(2), bbab564, 2022.
G. A. Pavlopoulos, P. I. Kontou, A. Pavlopoulou, C. Bouyioukos, E. Markou, P. G. Bagos. Bipartite graphs in systems biology and medicine: a survey of methods and applications, GigaScience, 7(4), giy014, 2018.
G. A. Pavlopoulos, M. Secrier, CN. Moschopoulos, TG. Soldatos, S. Kossida, J. Aerts, R. Schneider, P. G. Bagos, Using graph theory to analyze biological networks, BioData Mining, 4(10), 2011.
Z. Xie, J. Xu, Deep graph learning of inter-protein contacts, Bioinformatics, 38(4), 953-947, 2022.
Y. Wu, M. Gao, M. Zeng, J. Zhang, M. Li, BridgeDPI: a novel graph geural network for predicting drug–protein interactions, Bioinformatics, 38(9), 2578-2571, 2022.
X. Tang, J. Luo, C. Shen, Z. Lai, Multi-view multichannel attention graph convolutional network for miRNA–disease association prediction, Brief in Bioinformatics, 22(6), bbab174, 2021.
K. Han, E. E. Jeng, G. T. Hess, D. W. Morgens, A. Li, M. C. Bassik, Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions, Nature Biotechnology, 35(5), 474-463, 2017.
Y. Ma, S. Wang, C. C. Aggarwal, D. Yin, J. Tang, Multi-dimensional graph convolutional networks, 2019 SIAM International Conference on Data Mining, 665-657, Alberta, Kanada, 2019.
A. Altabaa, D. Huang, C. Byles-Ho, H. Khatib, F. Sosa, T. Hu, geneDRAGNN: Gene Disease Prioritization using Graph Neural Networks, 19th IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, Ottawa, Kanada 2022.
A. D. Perkins, M. A. Langston, M. A, Threshold selection in gene co-expression networks using spectral graph theory techniques, BMC Bioinformatics, 10(11), 11-1, 2009.
C. J. Wolfe, I. S. Kohane, A. J. Butte, Systematic survey revals general applicability of “guilt-by-association” within gene coexpression networks, BMC Bioinformatics, 6(1), 2005.
