Abstract
Resistance to antiretroviral drugs has been a major obstacle for long-lasting treatment of HIV-infected patients. The development of models to predict drug resistance is recognized as useful for helping the decision of the best therapy for each HIV+ individual. The aim of this study was to develop classifiers for predicting resistance to the HIV protease inhibitor lopinavir using a probabilistic neural network (PNN). The data were provided by the Molecular Virology Laboratory of the Health Sciences Center, Federal University of Rio de Janeiro (CCS-UFRJ/Brazil). Using bootstrap and stepwise techniques, ten features were selected by logistic regression (LR) to be used as inputs to the network. Bootstrap and cross-validation were used to define the smoothing parameter of the PNN networks. Four balanced models were designed and evaluated using a separate test set. The accuracies of the classifiers with the test set ranged from 0.89 to 0.94, and the area under the receiver operating characteristic (ROC) curve (AUC) ranged from 0.96 to 0.97. The sensitivity ranged from 0.94 to 1.00, and the specificity was between 0.88 and 0.92. Four classifiers showed performances very close to three existing expert-based interpretation systems, the HIVdb, the Rega and the ANRS algorithms, and to a k-Nearest Neighbor.
Similar content being viewed by others
Notes
For further information on the Brazilian HIV data banks, contact the co-author Rodrigo Brindeiro (robrinde@biologia.ufrj.br).
References
Rambaut, A., Posada, D., Crandall, K., and Holmes, E., The causes and consequences of HIV evolution. Nat. Rev. Genet. 5:52–61, 2004. doi:10.1038/nrg1246.
WHO (2015) Progress report 2011: Global HIV/AIDS response. http://www.who.int/hiv/pub/progress_report2011/en/. Accessed 28 Oct 2014.
Prosperi, M. C. F., Altmann, A., Rosen-Zvi, M., et al., Investigation of expert rule bases, logistic regression, and non-linear machine learning techniques for predicting response to antiretroviral treatment. Antivir. Ther. 14:433–442, 2009.
Van der Borght, K., Verheyen, A., Feyaerts, M., et al., Quantitative prediction of integrase inhibitor resistance from genotype through consensus linear regression modeling. Virol. J. 10:8, 2013. doi:10.1186/1743-422x-10-8.
Raposo, LM, Arruda, MB, Brindeiro, RM et al., Logistic regression models for predicting resistance to HIV protease inhibitor nelfinavir. In: Romero LMR (ed) XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013, IFMBE Proceedings, vol 41. Springer International Publishing 1237–1240, 2014.
Bonet, I., García, M. M., and Saeys, Y., Predicting Human Immunodeficiency Virus (HIV) drug resistance using recurrent neural networks. In: Mira, J. (Ed.), Bio-inspired Modeling of Cognitive Tasks, Lectures Notes in Computer Science, vol 4527. Springer Berlin, Heidelberg, pp. 234–243, 2007.
Larder, B., Wang, D., Revell, A., et al., The development of artificial neural networks to predict virological response to combination HIV therapy. Antivir. Ther. 12:15–24, 2007.
Pasomsub, E., Sukasem, C., Sungkanuparph, S., et al., The application of artificial neural networks for phenotypic drug resistance prediction: Evaluation and comparison with other interpretation systems. Jpn. J. Infect. Dis. 63:87–94, 2010.
Beerenwinkel, N., Geno2pheno: Estimating phenotypic drug resistance from HIV-1 genotypes. Nucleic Acids Res. 31:3850–3855, 2003. doi:10.1093/nar/gkg575.
Beerenwinkel, N., Schmidt, B., Walter, H., et al., Diversity and complexity of HIV-1 drug resistance: A bioinformatics approach to predicting phenotype from genotype. Proc. Natl. Acad. Sci. 99:8271–8276, 2002. doi:10.1073/pnas.112177799.
Wang, D., and Larder, B., Enhanced prediction of lopinavir resistance from genotype by use of artificial neural networks. J. Infect. Dis. 188:653–660, 2003. doi:10.1086/377453.
Chawla, N., Japkowicz, N., and Kotcz, A., Editorial. ACM SIGKDD Explor. Newslett. 6:1, 2004. doi:10.1145/1007730.1007733.
Sun, Y., Kamel, M., Wong, A., and Wang, Y., Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn. 40:3358–3378, 2007. doi:10.1016/j.patcog.2007.04.009.
He, H., and Garcia, E., Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21:1263–1284, 2009. doi:10.1109/tkde.2008.239.
Algoritmo Brasileiro, Interpretação—Genotipagem do HIV-1. http://forrest.ime.usp.br:3001/resistencia 2012. Accessed 15 Sep 2014.
Wensing, A. M., Calvez, V., Günthard, H. F., et al., 2014 Update of the drug resistance mutations in HIV-1. Top Antivir. Med. 22:642–650, 2014.
Efron, B., Bootstrap methods: Another look at the jackknife. Ann. Stat. 7:1–26, 1979. doi:10.1214/aos/1176344552.
Akaike, H., A new look at the statistical model identification. IEEE Trans. Autom. Control 19:716–723, 1974. doi:10.1109/tac.1974.1100705.
Krzanowski, WJ., An Introduction to Statistical Modelling. Reprint edition, John Wiley & Sons, 2010.
Budak, F., and Übeyli, E., Detection of resistivity for antibiotics by probabilistic neural networks. J. Med. Syst. 35:87–91, 2009. doi:10.1007/s10916-009-9344-z.
Bascil, M. S., and Oztekin, H., A study on hepatitis disease diagnosis using probabilistic neural network. J. Med. Syst. 36(3):1603–6, 2013. doi:10.1007/s10916-010-9621-x.
Singh, K., Gupta, S., and Rai, P., Predicting carcinogenicity of diverse chemicals using probabilistic neural network modeling approaches. Toxicol. Appl. Pharmacol. 272:465–475, 2013. doi:10.1016/j.taap.2013.06.029.
Kumar, H. P., and Srinivasan, S., Classification of ovary abnormality using the probabilistic neural network (PNN). Technol. Health Care: Off. J. Europ. Soc. Eng. Med. 22:857–865, 2014.
Hirschauer, T. J., Adeli, H., and Buford, J. A., Computer-aided diagnosis of Parkinson’s disease using enhanced probabilistic neural network. J. Med. Syst. 39(11):179, 2015. doi:10.1007/s10916-015-0353-9.
Specht, D., Probabilistic neural networks. Neural Netw. 3:109–118, 1990.
Berrar, DP, Downes, CS, and Dubitzky, W., Multiclass cancer classification using gene expression profiling and probabilistic neural networks. Pac. Symp. Biocomput. 5–16, 2003.
Parzen, E., On estimation of a probability density function and mode. Ann. Math. Statist. 33:1065–1076, 1962. doi:10.1214/aoms/1177704472.
Liu, T., and Shafer, R., Web resources for HIV type 1 genotypic-resistance test interpretation. Clin. Infect. Dis. 42:1608–1618, 2006. doi:10.1086/503914.
Rega Instituut KU Leuven., Rega Algorithm. https://rega.kuleuven.be/cev/avd/software/rega-algorithm. Accessed 20 Oct 2014.
HIV French Resistance., HIV-1 genotypic drug resistance interpretation’s algorithms http://www.hivfrenchresistance.org/index.html. Accessed 20 Oct 2014.
The MathWorks, Inc., MATLAB and Statistics Toolbox Release 2009b, Massachusetts.
R Development Core Team., R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing, 2013.
Wei, Q., and Dunbrack, R., The role of balanced training and testing data sets for binary classifiers in bioinformatics. PLoS ONE 8:e67863, 2013. doi:10.1371/journal.pone.0067863.
Rhee, S.-Y., Taylor, J., Wadhera, G., et al., Genotypic predictors of human immunodeficiency virus type 1 drug resistance. Proc. Natl. Acad. Sci. U. S. A. 103:17355–17360, 2006.
Acknowledgments
The authors would like to acknowledge FAPERJ (Carlos Chagas Filho Foundation for Research Support of the State of Rio de Janeiro), CNPq Brazil (National Counsel of Technological and Scientific Development) and CAPES (Coordination for the Improvement of Higher-Education Personnel) for the financial support provided for this research.
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is part of the Topical Collection on Systems-Level Quality Improvement
Rights and permissions
About this article
Cite this article
Raposo, L.M., Arruda, M.B., de Brindeiro, R.M. et al. Lopinavir Resistance Classification with Imbalanced Data Using Probabilistic Neural Networks. J Med Syst 40, 69 (2016). https://doi.org/10.1007/s10916-015-0428-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-015-0428-7