跳到主要內容

臺灣博碩士論文加值系統

(44.210.83.132) 您好!臺灣時間:2024/05/22 21:54
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:陳一心
研究生(外文):Yi-Hsin Chen
論文名稱:使用圖卷積網路預測藥物之副作用
論文名稱(外文):Using Graph Convolution Network to Predict Adverse Drug Reaction
指導教授:施因澤蔡垂雄
指導教授(外文):Yintzer ShihChwei-Shyong Tsai
口試委員:陳文淵左瑞麟
口試日期:2021-06-29
學位類別:碩士
校院名稱:國立中興大學
系所名稱:人工智慧與資料科學碩士在職學位學程
學門:電算機學門
學類:電算機應用學類
論文種類:學術論文
論文出版年:2021
畢業學年度:109
語文別:英文
論文頁數:35
中文關鍵詞:藥物副作用圖神經網路圖卷積網路生物信息
外文關鍵詞:drug side effectsadverse effectsgraph neural networkgraph convolution network
相關次數:
  • 被引用被引用:0
  • 點閱點閱:161
  • 評分評分:
  • 下載下載:1
  • 收藏至我的研究室書目清單書目收藏:0
藥物的副作用通常會導致健康或經濟損失。 研究人員通常在進行人體試驗之前試圖在細胞或動物研究中證明藥物的有效性和毒性,並儘可能地確定潛在的副作用,但是通常有所遺漏。 藥物進入市場後的嚴重副作用常常導致巨大的損失。 近年來計算機方法提供了預測副作用的方向。圖神經網絡過去用於解決與生物信息學有關的問題,例如蛋白質網絡。 我們的研究嘗試使用圖神經網絡算法來預測藥物的副作用。結合已知藥物和副作用數據集以及藥物與藥物之間的相似性,使用異構圖的結構來推斷藥物與副作用之間的關係。我們也舉例如何運用模型預測新的副作用,這種概念可以在未來運用於個人化醫療。
The side effects of drugs usually cause health and economic loss. Researchers often try to prove the effectiveness and toxicity of drugs. Cell or animal studies before conducting human trials are performed to identify potential side effects. However, the exhausted efforts often fail. Severe side effects often led to huge losses after the drug enters the market. The in-silico method provides a way to predict the side effect in recent years. Many algorithms are proposed, and graph neural networks had been used to solve bioinformatics-related problems such as protein networks. Our research tries to use a graph neural network to predict the side effects of drugs. Our study combines the known drug and side effects datasets and the similarity between the drug and the drug. We use the structure of the heterogeneous graph to infer the relationship between the drug and the side effect. New predictions are exemplified in our model. This concept can be applied to personalized medicine in the future.
摘要--------------------------------------------------------i
Abstract----------------------------------------------------ii
Table of Contents------------------------------------------iii
List of Tables---------------------------------------------iv
List of Figures---------------------------------------------v
Chapter 1 Introduction--------------------------------------1
Chapter 2 Related works-------------------------------------2
Chapter 3 Methods-------------------------------------------4
3.1 Dataset-------------------------------------------------4
3.2 Graph neural network------------------------------------7
3.3 Subgraph------------------------------------------------8
3.4 Link prediction-----------------------------------------8
3.5 Training-----------------------------------------------12
3.6 Architecture and hyperparameters-----------------------12
3.7 Related algorithms for link prediction-----------------12
3.7.1 Non-negative matrix factorization--------------------12
3.7.2 Non-negative matrix factorization with heat diffusion-12
3.7.3 Common neighbors-------------------------------------13
3.7.4 Jaccard----------------------------------------------13
3.7.5 Adamic Adar------------------------------------------13
3.7.6 Resource allocation 14
3.7.7 Katz 14
3.7.8 Personalized PageRank 14
Chapter 4 Results 15
4.1 GNN 15
4.2 Comparison to matrix factorization methods 15
4.3 Comparison to heuristic methods 15
4.4 Comparison to different link representation methods 23
4.5 Comparison to the different dropout rate 23
4.6 Comparison to different training set percentage 23
4.7 Comparison to hop numbers 23
4.8 New predictions not seen in the present datasets 28
Chapter 5 Conclusion and Future Works 31
References 32
[1]Nir Atias and Roded Sharan. 2011. An algorithmic framework for predicting side effects of drugs. J. Comput. Biol. 18, 3 (March 2011), 207–218.
[2]Jarrod Bailey, Michelle Thew, and Michael Balls. 2014. An analysis of the use of animal models in predicting human toxicology and drug safety. Altern. Lab. Anim. 42, 3 (June 2014), 181–199.
[3]Jose Biller and José M. Ferro. 2014. Neurologic Aspects of Systemic Disease, Part III. Newnes.
[4]Jian-Feng Cai, Emmanuel J. Candès, and Zuowei Shen. 2010. A Singular Value Thresholding Algorithm for Matrix Completion. SIAM J. Optim. 20, 4 (January 2010), 1956–1982.
[5]Monica Campillos, Michael Kuhn, Anne-Claude Gavin, Lars Juhl Jensen, and Peer Bork. 2008. Drug target identification using side-effect similarity. Science 321, 5886 (July 2008), 263–266.
[6]Yu-Chiao Chiu, Hung-I Harry Chen, Tinghe Zhang, Songyao Zhang, Aparna Gorthi, Li-Ju Wang, Yufei Huang, and Yidong Chen. 1/2019. Predicting drug response of tumors from integrated genomic profiles by deep neural networks. BMC Med. Genomics 12, S1 (1/2019), 18.
[7]L. G. Cohen, P. F. Souney, and S. J. Taylor. 1988. Paresthesia and back pain in a patient receiving vancomycin during hemodialysis. Drug Intell. Clin. Pharm. 22, 10 (October 1988), 784–785.
[8]Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. arXiv [cs.LG]. Retrieved from http://arxiv.org/abs/1606.09375
[9]J. Devasahayam, U. Pillai, and C. Uppaluri. 2012. Acute severe intestinal obstruction secondary to amlodipine toxicity. QJM 105, 5 (May 2012), 467–469.
[10]Kartikeya Dwivedi, Nitin Saraswat, and Meena Bisht. 2013. Protons Confirmation of Glimepiride drug using Correlation Spectroscopy a unique tool of Nuclear Magnetic Resonance spectroscopy. Math. Sci. Res. J. 3, 2 (2013), 1–9.
[11]I. R. Edwards and J. K. Aronson. 2000. Adverse drug reactions: definitions, diagnosis, and management. Lancet 356, 9237 (October 2000), 1255–1259.
[12]Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph neural networks for social recommendation. In The World Wide Web Conference on - WWW ’19, ACM Press, New York, New York, USA. DOI:https://doi.org/10.1145/3308558.3313488
[13]Anton F. Fliri, William T. Loging, Peter F. Thadeio, and Robert A. Volkmann. 2005. Analysis of drug-induced effect patterns to link structure and side effects of medicines. Nat. Chem. Biol. 1, 7 (December 2005), 389–397.
[14]M. José Gómez-Lechón, Laia Tolosa, Isabel Conde, and M. Teresa Donato. 2014. Competency of different cell models to predict human hepatotoxic drugs. Expert Opin. Drug Metab. Toxicol. 10, 11 (November 2014), 1553–1568.
[15]Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable Feature Learning for Networks. KDD 2016, (August 2016), 855–864.
[16]William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. arXiv [cs.SI]. Retrieved from http://arxiv.org/abs/1706.02216
[17]Yehuda Handelsman, Brett Lauring, Ira Gantz, Carol Iredale, Edward A. O’Neill, Ziwen Wei, Shailaja Suryawanshi, Keith D. Kaufman, Samuel S. Engel, and Eseng Lai. 2017. A randomized, double-blind, non-inferiority trial evaluating the efficacy and safety of omarigliptin, a once-weekly DPP-4 inhibitor, or glimepiride in patients with type 2 diabetes inadequately controlled on metformin monotherapy. Curr. Med. Res. Opin. 33, 10 (October 2017), 1861–1868.
[18]Ramin Hasibi and Tom Michoel. 2020. A Graph Feature Auto-Encoder for the Prediction of Unobserved Node Features on Biological Networks. arXiv [q-bio.QM]. Retrieved from http://arxiv.org/abs/2005.03961
[19]E. W. Hook 3rd and W. D. Johnson Jr. 1978. Vancomycin therapy of bacterial endocarditis. Am. J. Med. 65, 3 (September 1978), 411–415.
[20]J. Hosie, A. D. Bremner, P. J. Fell, I. G. James, P. A. Saul, and S. H. Taylor. 1992. Comparison of early side effects with amlodipine and nifedipine retard in hypertension. Cardiology 80 Suppl 1, (1992), 54–59.
[21]Masashi Ishihara, Noriyuki Matsutani, Shuji Ota, and Nobuhiko Seki. 2017. A Case of Posterior Reversible Encephalopathy Syndrome Induced by Cisplatin/Pemetrexed Chemotherapy for Lung Cancer. Case Rep. Oncol. 10, 1 (January 2017), 235–238.
[22]Md Jamiul Jahid and Jianhua Ruan. 2013. An Ensemble Approach for Drug Side Effect Prediction. Proceedings (2013), 440–445.
[23]Alexandros Karatzoglou, Xavier Amatriain, Linas Baltrunas, and Nuria Oliver. 2010. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems (RecSys ’10), Association for Computing Machinery, New York, NY, USA, 79–86.
[24]Zeki Kemeç, Yusuf Kahya, Arif Atay, Mustafa Demir, and Ali Gürel. 2019. Vancomycin Dependent Pancytopenia- a rare side effect: A Case Report. International Journal of Medical Reviews and Case Reports 3, 6 (June 2019), 1.
[25]Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv [cs.LG]. Retrieved from http://arxiv.org/abs/1412.6980
[26]László Lovász and Others. 1993. Random walks on graphs: A survey. Combinatorics, Paul erdos is eighty 2, 1 (1993), 1–46.
[27]Hao Ma, Haixuan Yang, Michael R. Lyu, and Irwin King. 2008. Mining social networks using heat diffusion processes for marketing candidates selection. In Proceedings of the 17th ACM conference on Information and knowledge management (CIKM ’08), Association for Computing Machinery, New York, NY, USA, 233–242.
[28]Aditya Krishna Menon and Charles Elkan. 2011. Link Prediction via Matrix Factorization. In Machine Learning and Knowledge Discovery in Databases, Springer Berlin Heidelberg, 437–452.
[29]S. Mizutani, E. Pauwels, V. Stoven, S. Goto, and Y. Yamanishi. 2012. Relating drug-protein interaction network with drug side effects. Bioinformatics 28, i522–i528. DOI:https://doi.org/10.1093/bioinformatics/bts383
[30]Emir Muñoz, Vít Nováček, and Pierre-Yves Vandenbussche. 2016. Using Drug Similarities for Discovery of Possible Adverse Reactions. AMIA Annu. Symp. Proc. 2016, (2016), 924–933.
[31]Thin Nguyen, Hang Le, Thomas P. Quinn, Tri Nguyen, Thuc Duy Le, and Svetha Venkatesh. 2021. GraphDTA: predicting drug-target binding affinity with graph neural networks. Bioinformatics 37, 8 (May 2021), 1140–1147.
[32]Daniela Nitsch, Joana P. Gonçalves, Fabian Ojeda, Bart de Moor, and Yves Moreau. 2010. Candidate gene prioritization by network analysis of differential expression using machine learning approaches. BMC Bioinformatics 11, (September 2010), 460.
[33]Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. The PageRank Citation Ranking: Bringing Order to the Web. (November 1999). Retrieved May 1, 2021 from http://ilpubs.stanford.edu:8090/422
[34]Vlatka Periša, Dorian Laslo, Lana Maričić, and Lada Zibar. 2021. Perindopril/amlodipine-induced thrombotic microangiopathy. Turk J Emerg Med 21, 1 (January 2021), 38–41.
[35]R. P. Russell. 1988. Side effects of calcium channel blockers. Hypertension 11, 3 Pt 2 (March 1988), II42-4.
[36]Abdelrahman Saad, Fahima A. Maghraby, and Yasser M. Omar. 2020. Predicting drug target interaction by integrating drug fingerprint and drug side effect using machine learning. In Advances in Intelligent Systems and Computing. Springer International Publishing, Cham, 281–290.
[37]Hiroshi Saito. 2020. Autonomic dysreflexia in a case of radiation myelopathy and cisplatin-induced polyneuropathy. Spinal Cord Ser Cases 6, 1 (August 2020), 71.
[38]Josef Scheiber, Bin Chen, Mariusz Milik, Sai Chetan K. Sukuru, Andreas Bender, Dmitri Mikhailov, Steven Whitebread, Jacques Hamon, Kamal Azzaoui, Laszlo Urban, Meir Glick, John W. Davies, and Jeremy L. Jenkins. 2009. Gaining insight into off-target mediated effects of drug candidates with a comprehensive systems chemical biology analysis. J. Chem. Inf. Model. 49, 2 (February 2009), 308–317.
[39]Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling Relational Data with Graph Convolutional Networks. In The Semantic Web, Springer International Publishing, 593–607.
[40]Mohan Timilsina, Declan Patrick Mc Kernan, Haixuan Yang, and Mathieu D’Aquin. 2020. Synergy Between Embedding and Protein Functional Association Networks for Drug Label Prediction using Harmonic Function. IEEE/ACM Trans. Comput. Biol. Bioinform. (2020), 1–1.
[41]Mohan Timilsina, Meera Tandan, Mathieu d’Aquin, and Haixuan Yang. 12/2019. Discovering Links Between Side Effects and Drugs Using a Diffusion Based Method. Sci. Rep. 9, 1 (12/2019), 10436.
[42]Beste Turanli, Kubra Karagoz, Gizem Gulfidan, Raghu Sinha, Adil Mardinoglu, and Kazim Yalcin Arga. 2018. A Network-Based Cancer Drug Discovery: From Integrated Multi-Omics Approaches to Precision Medicine. Curr. Pharm. Des. 24, 32 (2018), 3778–3790.
[43]Jennifer C. Veeren and Marjorie Weiss. 2016. Trends in emergency hospital admissions in England due to adverse drug reactions: 2008–2015. J. Pharm. Health Serv. Res. 8, 1 (November 2016), 5–11.
[44]Santiago Vilar, Carol Friedman, and George Hripcsak. 2017. Detection of drug–drug interactions through data mining studies using clinical sources, scientific literature and social media. Brief. Bioinform. 19, 5 (February 2017), 863–877.
[45]Lance De Vine, Lance De Vine, Guido Zuccon, Bevan Koopman, Laurianne Sitbon, and Peter Bruza. 2014. Medical Semantic Similarity with a Neural Language Model. Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. DOI:https://doi.org/10.1145/2661829.2661974
[46]H. Wang, Q. Gu, J. Wei, Z. Cao, and Q. Liu. 2015. Mining drug-disease relationships as a complement to medical genetics-based drug repositioning: Where a recommendation system meets genome-wide association studies. Clin. Pharmacol. Ther. 97, 5 (May 2015), 451–454.
[47]Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, and Tat-Seng Chua. 2019. KGAT. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD ’19, ACM Press, New York, New York, USA. DOI:https://doi.org/10.1145/3292500.3330989
[48]Ryen W. White, Sheng Wang, Apurv Pant, Rave Harpaz, Pushpraj Shukla, Walter Sun, William DuMouchel, and Eric Horvitz. 2016. Early identification of adverse drug reactions from search log data. J. Biomed. Inform. 59, (February 2016), 42–48.
[49]Yangyang Xu, Wotao Yin, Zaiwen Wen, and Yin Zhang. 2012. An alternating direction algorithm for matrix completion with nonnegative factors. Front. Math. China 7, 2 (April 2012), 365–384.
[50]Wen Zhang, Hua Zou, Longqiang Luo, Qianchao Liu, Weijian Wu, and Wenyi Xiao. 2016. Predicting potential side effects of drugs by recommender methods and ensemble learning. Neurocomputing 173, (January 2016), 979–987.
[51]Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2020. Graph neural networks: A review of methods and applications. AI Open 1, (2020), 57–81.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top