Privacy-Preserving Outsourced Support Vector Machine Design for Secure Drug Discovery
- 5 February 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 8 (2) , 610-622
Abstract
In this paper, we propose a framework for privacy-preserving outsourced drug discovery in the cloud, which we refer to as POD. Specifically, POD is designed to allow the cloud to securely use multiple drug formula providers' drug formulas to train Support Vector Machine (SVM) provided by the analytical model provider. In our approach, we design secure computation protocols to allow the cloud server to perform commonly used integer and fraction computations. To securely train the SVM, we design a secure SVM parameter selection protocol to select two SVM parameters and construct a secure sequential minimal optimization protocol to privately refresh both selected SVM parameters. The trained SVM classifier can be used to determine whether a drug chemical compound is active or not in a privacy-preserving way. Lastly, we prove that the proposed POD achieves the goal of SVM training and chemical compound classification without privacy leakage to unauthorized parties, as well as demonstrating its utility and efficiency using three real-world drug datasets.Keywords
Funding Information
- AXA Research Fund
- National Natural Science Foundation of China (61702105, 61402112)
This publication has 23 references indexed in Scilit:
- Privacy-Preserving Clinical Decision Support System Using Gaussian Kernel-Based ClassificationIEEE Journal of Biomedical and Health Informatics, 2014
- Privacy-Preserving Multi-Class Support Vector Machine for Outsourcing the Data Classification in CloudIEEE Transactions on Dependable and Secure Computing, 2013
- Drug Design for Neuropathic Pain Regulation from Traditional Chinese MedicineScientific Reports, 2013
- Drug discovery in pharmaceutical industry: productivity challenges and trendsDrug Discovery Today, 2012
- Principles of early drug discoveryBritish Journal of Pharmacology, 2011
- Computer-aided drug design platform using PyMOLJournal of Computer-Aided Molecular Design, 2010
- Privacy-preserving SVM classificationKnowledge and Information Systems, 2007
- Effect of Molecular Descriptor Feature Selection in Support Vector Machine Classification of Pharmacokinetic and Toxicological Properties of Chemical AgentsJournal of Chemical Information and Computer Sciences, 2004
- Molecular Similarity Searching Using Atom Environments, Information-Based Feature Selection, and a Naïve Bayesian ClassifierJournal of Chemical Information and Computer Sciences, 2003
- Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug ClassificationJournal of Chemical Information and Computer Sciences, 2003