Predicting Human Immunodeficiency Virus (HIV) Drug Resistance Using Recurrent Neural Networks

  • Isis Bonet
  • María M. García
  • Yvan Saeys
  • Yves Van de Peer
  • Ricardo Grau
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4527)


Predicting HIV resistance to drugs is one of many problems for which bioinformaticians have implemented and trained machine learning methods, such as neural networks. Predicting HIV resistance would be much easier if we could directly use the three-dimensional (3D) structure of the targeted protein sequences, but unfortunately we rarely have enough structural information available to train a neural network. Fur-thermore, prediction of the 3D structure of a protein is not straightforward. However, characteristics related to the 3D structure can be used to train a machine learning algorithm as an alternative to take into account the information of the protein folding in the 3D space. Here, starting from this philosophy, we select the amino acid energies as features to predict HIV drug resistance, using a specific topology of a neural network. In this paper, we demonstrate that the amino acid ener-gies are good features to represent the HIV genotype. In addi-tion, it was shown that Bidirectional Recurrent Neural Networks can be used as an efficient classification method for this prob-lem. The prediction performance that was obtained was greater than or at least comparable to results obtained previously. The accuracies vary between 81.3% and 94.7%.


Support Vector Machine Machine Learning Algorithm Recurrent Neural Network Context Layer Protease Inhibitor Resistance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Sevin, A.D., DeGruttola, V., Nijhuis, M., Schapiro, J.M., Foulkes, A.S., Para, M.F., Boucher, C.A.B.: Methods for investigation of the relationship between drug-susceptibility phenotype and human immunodeficiency virus type 1 genotype with applications to aids clinical trials group 333. Journal Of Infectious Diseases 182(1), 59–67 (2000)CrossRefGoogle Scholar
  2. 2.
    Scmidt, B., Walter, H., Moschik, B.: Simple algorithm derived from ageno-/phenotypic database to predict HIV-1 protease inhibitor resistance. AIDS 14, 1731–1738 (2000)CrossRefGoogle Scholar
  3. 3.
    Wang, D.C., Larder, B.: Enhanced prediction of lopinavir resistance from genotype by use of artificial neural networks. Journal Of Infectious Diseases 188(5), 653–660 (2003)CrossRefGoogle Scholar
  4. 4.
    Beerenwinkel, N., Schmidt, B., Walter, H., Kaiser, R., Lengauer, T., Hoffmann, D., Korn, K., Selbig, J.: Diversity and complexity of hiv-1 drug resistance: A bioinformatics approach to predicting phenotype from genotype. PNAS 99(12), 8271–8276 (2002)CrossRefGoogle Scholar
  5. 5.
    James, R.: Predicting Human Immunodeficiency Virus Type 1 Drug Resistance from Genotype Using Machine Learning. Msc thesis, University of Edinburgh (2004)Google Scholar
  6. 6.
    Rabinowitz, M., Myers, L., Banjevic, M., Chan, A., Sweetkind-Singer, J., Haberer, J., McCann, K., Wolkowicz, R.: Accurate prediction of hiv-1 drug response from the reverse transcriptase and protease amino acid sequences using sparse models created by convex optimization. Bioinformatics 22(5), 541–549 (2006)CrossRefGoogle Scholar
  7. 7.
    Cao, Z.W., Han, L.Y., Zheng, C.J., Ji, Z.L., Chen, X., Lin, H.H., Chen, Y.Z.: Computer prediction of drug resistance mutations in proteins. Drug Discovery Today 10(7), 521–529 (2005)CrossRefGoogle Scholar
  8. 8.
    Beerenwinkel, N., Daumer, M., Oette, M., Korn, K., Hoffmann, D., Kaiser, R., Lengauer, T., Selbig, J., Walter, H.: Geno2pheno: estimating phenotypic drug resistance from hiv-1 genotypes. Nucl. Acids Res. 31(13), 3850–3855 (2003)CrossRefGoogle Scholar
  9. 9.
    Miyazawa, S., Jernigan, R.L.: Protein stability for single substitution mutants and the extent of local compactness in the denatured state. Protein Eng. 7, 1209–1220 (1994)CrossRefGoogle Scholar
  10. 10.
    Miyazawa, S., Jernigan, R.L.: Residue potentials with a favorable contact pair term and an unfavorable high packing density term, for simulation and threading. J. Mol. Biol. 256, 623–644 (1996)CrossRefGoogle Scholar
  11. 11.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)MATHGoogle Scholar
  12. 12.
    Chang, C., Lin, C.: Libsvm (2001)Google Scholar
  13. 13.
    Rumelhart, D.E., Hinton, A.G.E., Williams, A.R.J.: Learning internal representations by error propagation. In: Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, pp. 318–362. MIT Press, Cambridge (1986)Google Scholar
  14. 14.
    Bonet Cruz, I., Díaz Sardiñas, A., Bello Pérez, R., Sardiñas Oliva, Y.: Learning optimization in a MLP neural network applied to OCR. In: Coello Coello, C.A., de Albornoz, Á., Sucar, L.E., Battistutti, O.C. (eds.) MICAI 2002. LNCS (LNAI), vol. 2313, pp. 292–300. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  15. 15.
    Tsoi, A., Back, A.: Discrete time recurrent neural network architectures: A unifying review. Neurocomputing 15, 183–223 (1997)MATHCrossRefGoogle Scholar
  16. 16.
    Baldi, P., Soren, B.: Bioinformatics: The Machine Learning Approach, 2nd edn. MIT Press, Cambridge (2001)MATHGoogle Scholar
  17. 17.
    Werbos, P.J.: Backpropagation through time: What it does and how to do it. Proceedings of the IEEE 78, 1550–1560 (1990)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Isis Bonet
    • 1
  • María M. García
    • 1
  • Yvan Saeys
    • 2
  • Yves Van de Peer
    • 2
  • Ricardo Grau
    • 1
  1. 1.Center of Studies on Informatics, Central University of Las VillasCuba
  2. 2.Department of Plant Systems Biology, Flanders Interuniversity Institute for Biotechnology (VIB), Ghent UniversityBelgium

Personalised recommendations