Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders

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.

[1]  Zhongming Zhao,et al.  Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. , 2014, Journal of the American Medical Informatics Association : JAMIA.

[2]  R. Altman,et al.  Data-Driven Prediction of Drug Effects and Interactions , 2012, Science Translational Medicine.

[3]  R. Krauss,et al.  When good drugs go bad , 2007, Nature.

[4]  Hua Zou,et al.  Predicting potential side effects of drugs by recommender methods and ensemble learning , 2016, Neurocomputing.

[5]  Zhuowen Tu,et al.  Similarity network fusion for aggregating data types on a genomic scale , 2014, Nature Methods.

[6]  X. Chen,et al.  TTD: Therapeutic Target Database , 2002, Nucleic Acids Res..

[7]  Ivor W. Tsang,et al.  Two-Layer Multiple Kernel Learning , 2011, AISTATS.

[8]  Jan de Leeuw,et al.  Journal of Statistical Software , 2009 .

[9]  David J. Greenblatt,et al.  Clinically Important Drug Interactions with Zopiclone, Zolpidem and Zaleplon , 2003, CNS drugs.

[10]  Pietro Liò,et al.  Multiplex methods provide effective integration of multi-omic data in genome-scale models , 2016, BMC Bioinformatics.

[11]  Ping Zhang,et al.  Multitask Dyadic Prediction and Its Application in Prediction of Adverse Drug-Drug Interaction , 2017, AAAI.

[12]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[13]  Rong Li,et al.  Inductive matrix completion for predicting adverse drug reactions (ADRs) integrating drug–target interactions , 2015 .

[14]  Ping Zhang,et al.  Predicting Drug-Drug Interactions Through Similarity-Based Link Prediction Over Web Data , 2016, WWW.

[15]  Hua Xu,et al.  Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs , 2012, J. Am. Medical Informatics Assoc..

[16]  W. Bretz,et al.  Red Marine Algae Lithothamnion calcareum Supports Dental Enamel Mineralization , 2023, Marine drugs.

[17]  Feng Liu,et al.  Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data , 2017, BMC Bioinformatics.

[18]  Carol Friedman,et al.  Drug-drug interaction through molecular structure similarity analysis , 2012, J. Am. Medical Informatics Assoc..

[19]  JA Ansari,et al.  Drug Interaction and Pharmacist , 2010, Journal of young pharmacists : JYP.

[20]  David S. Wishart,et al.  DrugBank: a knowledgebase for drugs, drug actions and drug targets , 2007, Nucleic Acids Res..

[21]  Fei Wang,et al.  Learning a Bi-Stochastic Data Similarity Matrix , 2010, 2010 IEEE International Conference on Data Mining.

[22]  Jianying Hu,et al.  Label Propagation Prediction of Drug-Drug Interactions Based on Clinical Side Effects , 2015, Scientific Reports.

[23]  Jeffrey M Schussler,et al.  Drug-induced QT interval prolongation: mechanisms and clinical management , 2012, Therapeutic advances in drug safety.

[24]  Tomaz Curk,et al.  Learning the kernel matrix via predictive low-rank approximations , 2016, 1601.04366.

[25]  Peer Bork,et al.  The SIDER database of drugs and side effects , 2015, Nucleic Acids Res..

[26]  P. Imming,et al.  Drugs, their targets and the nature and number of drug targets , 2006, Nature Reviews Drug Discovery.

[27]  Gert R. G. Lanckriet,et al.  Learning Multi-modal Similarity , 2010, J. Mach. Learn. Res..