State of the art prediction of HIV-1 protease cleavage sites

• DOI: 10.1093/bioinformatics/btu810
• Publication Date: 2014-12-11T05:15:08Z
• Authors: Thorsteinn Rögnva...; Liwen You; Daniel Garwicz
• Keywords: Cleavage (geology); Classification scheme; Protease inhibitor (pharmacology)

Abstract Motivation: Understanding the substrate specificity of human immunodeficiency virus (HIV)-1 protease is important when designing effective HIV-1 inhibitors. Furthermore, characterizing and predicting cleavage profile essential to generate test hypotheses how affects proteins host. Currently available tools for by can be improved. Results: The linear support vector machine with orthogonal encoding shown best predictor cleavage. It considerably better than current publicly services. also found that schemes using physicochemical properties do not improve over standard scheme. Some issues currently data are discussed. Availability implementation: datasets used, which most part, at UCI Machine Learning Repository. used all easily available. Contact: [e-mail]