Selecting anti-HIV therapies based on a variety of genomic and clinical factors
1Machine learning group, IBM Research Laboratory in Haifa, Israel, 2The Computational Biology and Applied Algorithmics Department, Max Planck Institute for Informatics, Saarbrücken, Germany, 3Computer Science and Automation Department, University of Rome TRE, Italy, 4Division of Infectious Diseases, Department of Medicine, Karolinska Institute, Sweden, 5Institute of Virology, University of Cologne, Cologne, Germany, 6Retrovirology Laboratory, CRP-Santé, Luxembourg, 7Health care and Life sciences group, IBM Research Laboratory in Haifa, Israel, 8Informa srl, Rome, Italy and 9Department of Molecular Biology, University of Siena, Italy
*To whom correspondence should be addressed.
 |
Abstract |
|---|
Motivation: Optimizing HIV therapies is crucial since the virus rapidly develops mutations to evade drug pressure. Recent studies have shown that genotypic information might not be sufficient for the design of therapies and that other clinical and demographical factors may play a role in therapy failure. This study is designed to assess the improvement in prediction achieved when such information is taken into account. We use these factors to generate a prediction engine using a variety of machine learning methods and to determine which clinical conditions are most misleading in terms of predicting the outcome of a therapy.
Results: Three different machine learning techniques were used: generative–discriminative method, regression with derived evolutionary features, and regression with a mixture of effects. All three methods had similar performances with an area under the receiver operating characteristic curve (AUC) of 0.77. A set of three similar engines limited to genotypic information only achieved an AUC of 0.75. A straightforward combination of the three engines consistently improves the prediction, with significantly better prediction when the full set of features is employed. The combined engine improves on predictions obtained from an online state-of-the-art resistance interpretation system. Moreover, engines tend to disagree more on the outcome of failure therapies than regarding successful ones. Careful analysis of the differences between the engines revealed those mutations and drugs most closely associated with uncertainty of the therapy outcome.
Availability: The combined prediction engine will be available from July 2008, see http://engine.euresist.org
Contact: rosen{at}il.ibm.com
CiteULike 
Connotea 
Del.icio.us What's this?