Features in HIV genotypes associated with failure in the computational prediction of patients' response to antiretroviral treatment

Rogério Santos Rosa, Ádamo Yesus Brito Silva, Viviane Martha Morais, Rafael Santos, Katia Silva Guimarães


HIV acts by attacking the immune system and gradually destroying the TCD4+ defense cells. Without adequate treatment, the carriers develop the most severe form of the infection, AIDS, when the patient can be afflicted by opportunistic diseases that inevitably lead to death. Fortunately, with the advent of the highly active antiretroviral therapy (HAART), the mortality of people with HIV is decreasing. However, mutations can occur in the genotype of the virus, generating drug-resistant phenotypes. Computational methods have been used to predict whether a given strain is drug-resistant, and to which drugs this resistance occurs, thereby increasing the chances of success of the prescribed treatment regimen. However, these methods are not always accurate in their task. In this context, by applying Feature Selection methods and estimating Decision Tree models, we investigated patterns in Protease and Reverse Transcriptase enzyme sequences, as well as in patients’ clinical data, which can lead to correct or incorrect computational prediction. As a result, we identified 21 features that are highly informative, 11 which tend to lead the methods to error, and eight that present both behaviors simultaneously, being able to predict the patient's response to therapy and at the same time may lead the predictor's methods to failure.


HIV; antiretroviral therapy; drug-resistance; phenotype; computational methods

Texto completo:

PDF (English)


ANTA, L. et al. Rilpivirine Resistance Mutations in HIV Patients Failing Non-Nucleoside Reverse Transcriptase Inhibitor-Based Therapies. AIDS, v. 27, n. 1, p. 81–85, 2013.

AVERT FUNDATION. Global HIV and AIDS Statistics, 2017.

BEERENWINKEL, N. et al. Computational methods for the design of effective therapies against drug resistant HIV strains. Bioinformatics, v. 21, n. 21, p. 3943–3950, 1 nov. 2005.

CHAWLA, N. V et al. SMOTE: Synthetic Minority Over-sampling Technique. J. Artif. Int. Res., v. 16, n. 1, p. 321–357, 2002.

DEFO, D.; KOUOTOU, E. A.; RICHIE, J. Failure to return to receive HIV-test results: the Cameroon experience. BMC Research Notes, v. 10, n. 1, 2017.

EGBE, T. O. et al. Cesarean delivery technique among HIV positive women with sub-optimal antenatal care uptake at the Douala General Hospital, Cameroon: case series report. BMC Research Notes, v. 10, n. 1, 2017.

HALL, M. A. et al. The WEKA data mining software: an update. SIGKDD Explorations, v. 11, n. 1, p. 10–18, 2009.

KULKARNI, R. et al. The HIV-1 Reverse Transcriptase M184I Mutation Enhances the E138K-Associated Resistance to Rilpivirine and Decreases Viral Fitness. JAIDS Journal of Acquired Immune Deficiency Syndromes, v. 59, n. 1, p. 47–54, 2012.

KUMAR, V.; MINZ, S. Feature Selection: A literature Review. Smart Computing Review, v. 4, n. 3, p. 211–229, 2014.

LARDER, B. et al. The development of artificial neural networks to predict virological response to combination HIV therapy. Antiviral Therapy, v. 12, n. 1, p. 15–24, 2007.

MAY, M. T. et al. Impact on life expectancy of HIV-1 positive individuals of CD4 R cell count and viral load response to antiretroviral therapy. AIDS (London, England), p. 1193–1202, 2014.

OZAHATA, M. C. et al. Data-intensive analysis of HIV mutations. BMC Bioinformatics, v. 16, n. 1, p. 35, 5 dez. 2015.

R DEVELOPMENT CORE TEAM. R: A Language and Environment for Statistical ComputingVienna, Austria, 2008. Disponível em:

REVELL, A. D. et al. Computational models can predict response to HIV therapy without a genotype and may reduce treatment failure in different resource-limited settings. Journal of Antimicrobial Chemotherapy, v. 68, n. 6, p. 1406–1414, 2013.

RHEE, S.-Y. et al. Human immunodeficiency virus reverse transcriptase and protease sequence database. Nucleic Acids Research, v. 31, n. 1, p. 298–303, 2003.

ROSA, R. S. et al. Insights on prediction of patients’ response to anti-HIV therapies through machine learning. 2014 International Joint Conference on Neural Networks (IJCNN). Anais...IEEE, jul. 2014Disponível em:

WANG, D. et al. A comparison of three computational modelling methods for the prediction of virological response to combination HIV therapy. Artificial Intelligence in Medicine, v. 47, n. 1, p. 63–74, 2009.

XU, H.-T. et al. Effect of mutations at position E138 in HIV-1 reverse transcriptase and their interactions with the M184I mutation on defining patterns of resistance to nonnucleoside reverse transcriptase inhibitors rilpivirine and etravirine. Antimicrobial agents and chemotherapy, v. 57, n. 7, p. 3100–9, 1 jul. 2013.

DOI: https://doi.org/10.24221/jeap.3.3.2018.2034.319-329


  • Não há apontamentos.

Direitos autorais 2018 Revista e Autor

Licença Creative Commons
Esta obra está licenciada sob uma licença Creative Commons Atribuição - Não comercial - Compartilhar igual 4.0 Internacional.