Probabilistic Neural Network for Predicting Resistance to HIV-Protease Inhibitor Nelfinavir

Letícia Martins Raposo, Mônica Barcellos Arruda, Rodrigo de Moraes Brindeiro, Flavio Fonseca Nobre

Abstract

Resistance to antiretroviral drugs has been a major obstacle for a long-lasting treatment of HIV infected patients. The development of models to predict drug resistance is already recognized as useful for helping the decision making process regarding the best therapy for each individual HIV+. The aim of this study was to develop classifiers for predicting resistance to HIV protease inhibitor Nelfinavir using 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 a combination of bootstrap and cross-validation to develop the classifiers, four features were selected to be used as input for the network. Additionally, this approach was also used to define the spread parameter of the PNN networks. Final modelling strategy involved the development of four PNN networks with balanced data and evaluation of the models was done using a separate test set. The accuracies on the test set of the classifiers ranged from 71.2 to 76.0% and the area under the receiver operating characteristic (ROC) curve (AUC) ranged from 0.70 to 0.73. For the two best classifiers the sensitivity and specificity were 66.7% and 78.9% respectively, and the accuracy and AUC were 76.0% and 0.73 for both classifiers. The classifiers showed performances very close to two existing expert-based interpretation systems (IS), the Stanford HIV db and the Rega algorithms. The analysis also illustrates the use of a computational approach for feature selection and model parameters estimation that can be used in other settings.

References

  1. Barouch, D.H. 2008. Challenges in the development of an HIV-1 vaccine. Nature 455, 7213, 613 - 619.
  2. Beerenwinkel, N., Schmidt, B., Walter, H., Kaiser, R., Lengauer, T., Hoffmann, D., Korn, K. and Selbig, J. 2002. Diversity and complexity of HIV-1 drug resistance: a bioinformatics approach to predicting phenotype from genotype. Proc. Natl. Acad. Sci. U. S. A. 99, 8271 - 8276.
  3. Beerenwinkel, N. Däumer, M., Oette, M., Korn, K., Hoffmann, D., Kaiser, R., Lengauer, T., Selbig, J. and Walter, H. 2003. Geno2pheno: Estimating phenotypic drug resistance from HIV-1 genotypes. Nucleic Acids Res. 31, 3850-3855.
  4. Berrar, D. P., Downes, C. S. and Dubitzky, W. 2003. Multiclass Cancer Classification Using Gene Expression Profiling and Probabilistic Neural Networks. In: Pacific Symposium on Biocomputing'03, 5 - 16.
  5. Bonet, I., Garcia, M.M., Saeys, Y., Sanchez, R., Saeys, Y., Van de Peer, Y. and Grau, R. 2007. Predicting Human Immunodeficiency Virus (HIV) Drug Resistance Using Recurrent Neural Networks. In: Mira, J., Álvarez, J. R. (Eds.), IWINAC (1), vol. 4527, Lecture Notes in Computer Science, 234 - 243. Springer.
  6. Bushman, F., Landau, N.R. and Emini, E.A. 1998. New developments in the biology and treatment of HIV. Proc Natl Acad Sci USA 95, 19, 11041 - 11042.
  7. Efron, B. 1979. Bootstrap methods: another look at the jackknife. The annals of Statistics, 1-26.
  8. Eisenberg, D., Schwarz, E., Komaromy, M., and Wall, R. 1984. Analysis of membrane and surface protein sequences with the hydrophobic moment plot. Journal of Molecular Biology 179, 1, 125-142.
  9. He H. and Garcia, E.A. 2009. Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering 21, 9, 1263-1284.
  10. Johnson, V.A., Calvez, V., Günthard, H.F., Paredes R., Pillay, D., Shafer, R., Wensing, A.M. and Richman D.D. 2011. 2011 update of the drug resistance mutations in HIV-1. Top Antivir Med 19, 4, 156 - 164.
  11. Liu, T.F. and Shafer, R.W. 2006. Web Resources for HIV type 1 Genotypic-Resistance Test Interpretation. Clin Infect Dis 42, 11, 1608-1618.
  12. Parzen, E. 1962. On estimation of a probability densityfunction and mode. Ann Math Statist 33, 3, 1065 - 1076.
  13. Pasomsub, E., Sukasem, C., Sungkanuparph, S., Kijsirikul and B., Chantratita, W. 2010. The application of artificial neural networks for phenotypic drug resistance prediction: evaluation and comparison with other interpretation systems. Jpn J Infect Dis. 63, 2, 87 - 94.
  14. Peeters, M. 2011. The genetic variability of HIV-1 and its implications. Transfus Clin Biol. 8, 3, 222 - 225.
  15. Prosperi, M.C.F., Altmann, A., Rosen-Zvi, M. Aharoni, E., Borgulya, G., Bazso, F,Sönnerborg, A., Schülter, E., Struck, D., Ulivi, G., Vandamme, A., Vercauteren, J. and Zazziet, M. 2009. Investigation of expert rule bases, logistic regression, and non-linear machine learning techniques for predicting response to antiretroviral treatment. Antivir Ther. 14, 433-442.
  16. Raposo, L., Arruda, M., Brindeiro, R. and Nobre, F. 2013. Logistic Regression Models for Predicting Resistance to HIV Protease Inhibitor Nelfinavir XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013, Springer International Publishing, 41, 1237 - 1240.
  17. Richman, D.D. 2006. Antiviral drug resistance. Antiviral Res. 71, 117-121.
  18. Specht, D. F. 1990. Probabilistic neural networks, Neural Netw. 3, 1, 109 - 118.
  19. UNAIDS 2011. How to get to zero: Faster. Smarter. Better.
  20. Van der Borght, K., Verheyen, A., Feyaerts, M., Van Wesenbeeck, L., Verlinden, Y., Van Craenenbroeck, E. and Van Vlijmen, H. 2013. Quantitative prediction of integrase inhibitor resistance from genotype through consensus linear regression modeling. Virology Journal 10, 8, 1 - 12.
  21. Van Laethem, K., Geretti, A.M., Camacho, R. and Vandamme A.M. 2009. Algorithm for the use of genotypic HIV-1 resistance data (version Rega v8.0.2), from: http://rega.kuleuven.be/cev/avd/ software/rega-algorithm.
  22. Vermeiren, H., Van Craenenbroeck, E., Alen, P., Bacheler, L., G. Picchio, G. and Lecocq, P. 2007. Prediction of HIV-1 drug susceptibility phenotype from the viral genotype using linear regression modeling. J Virol Methods 145, 1, 47 - 55.
  23. Wang, D. and Larder, B. 2003. Enhanced prediction of lopinavir resistance from genotype by use of artificial neural networks. J Infect Dis. 188, 5, 653 - 660.
  24. Zweig, M.H. and Campbell, G. 1993. Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 39, 4, 561 - 577.
Download


Paper Citation


in Harvard Style

Martins Raposo L., Barcellos Arruda M., Brindeiro R. and Fonseca Nobre F. (2014). Probabilistic Neural Network for Predicting Resistance to HIV-Protease Inhibitor Nelfinavir . In Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2014) ISBN 978-989-758-012-3, pages 17-23. DOI: 10.5220/0004735900170023


in Bibtex Style

@conference{bioinformatics14,
author={Letícia Martins Raposo and Mônica Barcellos Arruda and Rodrigo de Moraes Brindeiro and Flavio Fonseca Nobre},
title={Probabilistic Neural Network for Predicting Resistance to HIV-Protease Inhibitor Nelfinavir},
booktitle={Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2014)},
year={2014},
pages={17-23},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004735900170023},
isbn={978-989-758-012-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2014)
TI - Probabilistic Neural Network for Predicting Resistance to HIV-Protease Inhibitor Nelfinavir
SN - 978-989-758-012-3
AU - Martins Raposo L.
AU - Barcellos Arruda M.
AU - Brindeiro R.
AU - Fonseca Nobre F.
PY - 2014
SP - 17
EP - 23
DO - 10.5220/0004735900170023