{"type":"ScholarlyArticle","title":"Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders","authors":[{"name":"Tengfei Ma","slug":"tengfei-ma","given":"Tengfei","family":"Ma","affiliation":"IBM Research; MIT-IBM Watson AI Lab"},{"name":"Cao Xiao","slug":"cao-xiao","given":"Cao","family":"Xiao","affiliation":"IBM Research; MIT-IBM Watson AI Lab"},{"name":"Jiayu Zhou","slug":"jiayu-zhou","given":"Jiayu","family":"Zhou","affiliation":"Computer Science and Engineering , Michigan State University"},{"name":"Fei Wang","slug":"fei-wang","given":"Fei","family":"Wang","affiliation":"Weill Cornell Medical School , Cornell University"}],"abstract":"Drug similarity has been studied to support downstream clinical tasks such as inferring novel properties of drugs (e.g. side effects, indications, interactions) from known properties. The growing availability of new types of drug features brings the opportunity of learning a more comprehensive and accurate drug similarity that represents the full spectrum of underlying drug relations. However, it is challenging to integrate these heterogeneous, noisy, nonlinear-related  information to learn accurate similarity measures especially when labels are scarce. Moreover, there is a trade-off between accuracy and interpretability. In this paper, we propose to learn accurate and interpretable similarity measures from multiple types of drug features. In particular, we model the integration using multi-view graph auto-encoders, and add attentive mechanism to determine the weights for each view with respect to corresponding tasks and features for better interpretability. Our model has flexible design for both semi-supervised and unsupervised settings. Experimental results demonstrated significant predictive accuracy improvement. Case studies also showed better model capacity (e.g. embed node features) and interpretability.","doi":"10.24963/ijcai.2018/483","url":"https://ijcai.org/proceedings/2018/483","pdf":"https://ijcai.org/proceedings/2018/0483.pdf","markdown":"https://ijcai.org/proceedings/2018/483.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/483","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning Applications","track":"Main track","number":483,"pages":{"first":3477,"last":3483},"keywords":["Machine Learning: Deep Learning","Machine Learning Applications: Bio;Medicine","Machine Learning: Data Mining"],"videos":[],"references":[{"position":1,"raw":"[Abadi et al., 2015] Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015.","title":"TensorFlow: Large-scale machine learning on heterogeneous systems","authors":"Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Angione et al., 2016] Claudio Angione, Max Conway, and Pietro Lió. Multiplex methods provide effective integra- tion of multi-omic data in genome-scale models. BMC Bioinformatics, 17(4):83, Mar 2016.","title":"Multiplex methods provide effective integration of multi-omic data in genome-scale models","authors":"Claudio Angione, Max Conway, Pietro Lió","year":"2016","venue":"BMC Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ansari, 2010] J. Ansari. Drug interaction and pharmacist. Journal of Young Pharmacists., 2(3), 2010.","title":"Drug interaction and pharmacist","authors":"J Ansari","year":"2010","venue":"Journal of Young Pharmacists","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2002] X. Chen, ZL. Ji, and YZ. Chen. Ttd: Ther- apeutic target database. Nucleic Acids Res., 30(1), 2002.","title":"Ttd: Therapeutic target database","authors":"Chen","year":"2002","venue":"Nucleic Acids Res","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng and Zhao, 2014] F. Cheng and Z. Zhao. Machine learning-based prediction of drug-drug interactions by in- tegrating drug phenotypic, therapeutic, chemical, and ge- nomic properties. JAMIA, 21, 2014.","title":"Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties","authors":"F Cheng, Z Zhao","year":"2014","venue":"JAMIA","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fokoue et al., 2016] A. Fokoue, O. Hassanzadeh, M. Sadoghi, and P. Zhang. Predicting drug-drug in- teractions through similarity-based link prediction over web data. WWW '16 Companion, pages 175-178, 2016.","title":"Predicting drug-drug interactions through similarity-based link prediction over web data","authors":"A Fokoue, O Hassanzadeh, M Sadoghi, P Zhang","year":"2016","venue":"WWW '16 Companion","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Giacomini et al., 2007] K. Giacomini, R. Krauss, D. Roden, M. Eichelbaum, and M. Hayden. When good drugs go bad. Nature, 446:975-977, 2007.","title":"When good drugs go bad","authors":"K Giacomini, R Krauss, D Roden, M Eichelbaum, M Hayden","year":"2007","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hesse et al., 2003] LM. Hesse, LL. von Moltke, and DJ. Greenblatt. Clinically important drug interactions with zopiclone, zolpidem and zaleplon. CNS Drugs., 17(7), 2003.","title":"Clinically important drug interactions with zopiclone, zolpidem and zaleplon","authors":"Hesse","year":"2003","venue":"CNS Drugs","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jin et al., 2017] B. Jin, H. Yang, C. Xiao, P. Zhang, X. Wei, and F. Wang. Multitask dyadic prediction and its appli- cation in prediction of adverse drug-drug interaction. In AAAI, 2017.","title":"Multitask dyadic prediction and its application in prediction of adverse drug-drug interaction","authors":"B Jin, H Yang, C Xiao, P Zhang, X Wei, F Wang","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kipf and Welling, 2016a] TN. Kipf and M. Welling. Semi- supervised classification with graph convolutional networks. 2016.","title":"Semisupervised classification with graph convolutional networks","authors":"Welling Kipf, Tn, M Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kipf and Welling, 2016b] TN. Kipf and M. Welling. Varia- tional graph auto-encoders. 2016.","title":"Variational graph auto-encoders","authors":"Welling Kipf, T N Kipf, M Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kuhn et al., 2015] M. Kuhn, I. Letunic, LJ. Jensen, and P. Bork. The sider database of drugs and side effects. Nu- cleic Acids Res., 2015.","title":"The sider database of drugs and side effects","authors":"M Kuhn, I Letunic, L J Jensen, P Bork","year":"2015","venue":"Nucleic Acids Res","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2015] R. Li, Y. Dong, Q. Kuang, Y. Wu, Y. Li, M. Zhu, and M. Li. Inductive matrix completion for pre- dicting adverse drug reactions (adrs) integrating drug-target interactions. Chemometrics and Intelligent Laboratory Sys- tems, 144:71-79, 2015.","title":"Inductive matrix completion for predicting adverse drug reactions (adrs) integrating drug-target interactions","authors":"R Li, Y Dong, Q Kuang, Y Wu, Y Li, M Zhu, M Li","year":"2015","venue":"Chemometrics and Intelligent Laboratory Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2012] M. Liu, Y. Wu, Y. Chen, J. Sun, Z. Zhao, X. Chen, M. Matheny, and H. Xu. Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs. JAMIA, 19(e1):e28-e35, 2012.","title":"Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs","authors":"M Liu, Y Wu, Y Chen, J Sun, Z Zhao, X Chen, M Matheny, H Xu","year":"2012","venue":"JAMIA","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[McFee and Lanckriet, 2011] B. McFee and G. Lanckriet. Learning multi-modal similarity. J. Mach. Learn. Res., 12, 2011.","title":"Learning multi-modal similarity","authors":"B Mcfee, G Lanckriet","year":"2011","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nachimuthu et al., 2012] S. Nachimuthu, MD. Assar, and JM. Schussler. Drug-induced qt interval prolongation: mechanisms and clinical management. Therapeutic Ad- vances in Drug Safety., 3(5), 2012.","title":"Drug-induced qt interval prolongation: mechanisms and clinical management","authors":"S Nachimuthu, M D Assar, J M Schussler","year":"2012","venue":"Therapeutic Advances in Drug Safety","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Peter et al., 2006] I. Peter, S. Christian, and M. Achim. Drugs, their targets and the nature and number of drug targets. Nature Reviews Drug Discovery, 5:821-834, 2006.","title":"Drugs, their targets and the nature and number of drug targets","authors":"Peter","year":"2006","venue":"Nature Reviews Drug Discovery","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Schlichtkrull et al., 2017] M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling. Mod- eling Relational Data with Graph Convolutional Networks. ArXiv e-prints, 2017.","title":"Modeling Relational Data with Graph Convolutional Networks","authors":"M Schlichtkrull, T N Kipf, P Bloem, R Van Den Berg, I Titov, M Welling","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Strazar and Curk, 2016] M. Strazar and T. Curk. Learning the kernel matrix via predictive low-rank approximations. CoRR, abs/1601.04366, 2016.","title":"Learning the kernel matrix via predictive low-rank approximations","authors":"M Strazar, T Curk","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tatonetti et al., 2012] NP.","title":"NP","authors":"Tatonetti","year":"2012","venue":"NP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"Tatonetti, P. Patrick, R. Daneshjou, and RB. Altman. Data-driven prediction of drug effects and interactions. Science translational medicine, 4(125):125ra31-125ra31, 2012.","title":"Data-driven prediction of drug effects and interactions","authors":"P Tatonetti, R Patrick, R B Daneshjou, Altman","year":"2012","venue":"Science translational medicine","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Vilar et al., ] S. Vilar, R. Harpaz, E. Uriarte, L. Santana, R. Rabadan, and C. Friedman. Drug drug interaction through molecular structure similarity analysis. JAMIA, (6):1066-1074.","title":"Drug drug interaction through molecular structure similarity analysis","authors":"Vilar","year":null,"venue":"JAMIA","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vilar et al., 2012] S. Vilar, R. Harpaz, E. Uriarte, L. Santana, R. Rabadan, and C. Friedman. Drug-drug interaction through molecular structure similarity analysis. JAMIA, 19(6):1066-1074, 2012.","title":"Drug-drug interaction through molecular structure similarity analysis","authors":"S Vilar, R Harpaz, E Uriarte, L Santana, R Rabadan, C Friedman","year":"2012","venue":"JAMIA","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2010] F. Wang, P. Li, and AC. Konig. Learning a bi-stochastic data similarity matrix. In ICDM, pages 551-560, 2010.","title":"Learning a bi-stochastic data similarity matrix","authors":"F Wang, P Li, A C Konig","year":"2010","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2014] B. Wang, A. Mezlini, F. Demir, M. Fi- ume, Z. Tu, M. Brudno, and A. Goldenberg. Similarity network fusion for aggregating data types on a genomic scale. Nature Methods, 11:333-337, 2014.","title":"Similarity network fusion for aggregating data types on a genomic scale","authors":"B Wang, A Mezlini, F Demir, M Fiume, Z Tu, M Brudno, A Goldenberg","year":"2014","venue":"Nature Methods","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wishart et al., 2008] DS. Wishart, C. Knox, and AC. Guo. Drugbank: a knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Research, 36, 2008.","title":"Drugbank: a knowledgebase for drugs, drug actions and drug targets","authors":"Ds, C Wishart, A C Knox, Guo","year":"2008","venue":"Nucleic Acids Research","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xu et al., 2016] Taosheng Xu, Thuc Duy Le, Lin Liu, Ru- jing Wang, Bingyu Sun, and Jiuyong Li. Identifying cancer subtypes from mirna-tf-mrna regulatory networks and ex- pression data. PLOS ONE, 11(4):1-20, 04 2016.","title":"Identifying cancer subtypes from mirna-tf-mrna regulatory networks and expression data","authors":"Xu","year":"2016","venue":"PLOS ONE","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2015] P. Zhang, F. Wang, J. Hu, and R. Sor- rentino. Label propagation prediction of drug-drug inter- actions based on clinical side effects. Scientific reports, 5, 2015.","title":"Label propagation prediction of drug-drug interactions based on clinical side effects","authors":"P Zhang, F Wang, J Hu, R Sorrentino","year":"2015","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2016] W. Zhang, H. Zou, L. Luo, Q. Liu, W. Wu, and W. Xiao. Predicting potential side effects of drugs by recommender methods and ensemble learning. Neurocomputing., 173, 2016.","title":"Predicting potential side effects of drugs by recommender methods and ensemble learning","authors":"W Zhang, H Zou, L Luo, Q Liu, W Wu, W Xiao","year":"2016","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2017] W. Zhang, Y. Chen, F. Liu, F. Luo, G. Tian, and X. Li. Predicting potential drug-drug interac- tions by integrating chemical, biological, phenotypic and network data. BMC Bioinformatics., 2017.","title":"Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data","authors":"W Zhang, Y Chen, F Liu, F Luo, G Tian, X Li","year":"2017","venue":"BMC Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhuang et al., 2011] J. Zhuang, IW. Tsang, and S. Hoi. Two- layer multiple kernel learning. In AISTATS, volume 15, pages 909-917, 2011.","title":"Twolayer multiple kernel learning","authors":"J Zhuang, I W Tsang, S Hoi","year":"2011","venue":"AISTATS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}