A Combinatorial Computational Approach for Drug Discovery Against AIDS: Machine Learning and Proteochemometrics
Computational methods have been widely used in drug discovery including identification of novel targets, studying drug target interactions, and in virtual screening of compounds against known targets. Machine learning techniques have been used in predictions of novel targets and drugs with greater accuracy compared to other methods. Machine learning algorithms have also been widely used in predicting the progression of disease, resistance of a drug to a virus, treatment efficacy prediction, and also in predicting the effectiveness of combinational therapy with respect to HIV-1. In this article, we have focused on some of the machine learning techniques in the context of viral disease. In brief, machine learning methods have great potential in drug discovery, drug repurposing, and in precision medicine.
KeywordsHuman immunodeficiency virus-1 (HIV-1) Machine learning (ML) Support vector machines (SVM) Decision tree (DT) Random Forest (RF) Artificial neural network (ANN) Proteochemometric modeling (PCM)
The corresponding author acknowledges the grant (No. VGST/GRD-533/2016-17/241) received from Karnataka Science and Technology Promotion Society (KSTePS), India, for supporting the ‘Centre for Interactive Biomolecular 3D-literacy (C-in-3D)’ under the VGST scheme – Centres of Innovative Science, Engineering and Education (CISEE) for the year 2016-17.
- 2.Chui M, Henke N, Miremadi M. Most of AI’s business uses will be in two areas. Harv Bus Rev. 2018. https://hbr.org/2018/07/most-of-ais-business-uses-will-be-in-two-areas.
- 8.Vapnik VN. Statistical learning theory. New York: John Wiley & Sons, Inc; 1998.Google Scholar
- 11.Singh Y, Mars M. Support vector machines to forecast changes in CD4 count of HIV-1 positive patients. Sci Res Essays. 2010;5(17):2384–90.Google Scholar
- 14.Breiman L. Classification and regression trees. Taylor & Francis Group, LLC 1984, Boca raton, FL, pp368Google Scholar
- 16.Muñoz-Moreno JA, Pérez-Álvarez N, Muñoz-Murillo A, Prats A, Garolera M, Jurado MÀ, Fumaz CR, Negredo E, Ferrer MJ, Clotet B. Classification models for neurocognitive impairment in HIV infection based on demographic and clinical variables. PLoS One. 2014;9(9):e107625. https://doi.org/10.1371/journal.pone.0107625.CrossRefPubMedPubMedCentralGoogle Scholar
- 18.Ho TK. The random subspace method for constructing decision forests. ITPAM. 1998;20:832–44.Google Scholar
- 22.Wang D, Larder B, Revell A, Montaner J, Harrigan R, De Wolf F, Lange J, Wegner S, Ruiz L, Pérez-Elías MJ, Emery S. A comparison of three computational modelling methods for the prediction of virological response to combination HIV therapy. Artif Intell Med. 2009;47(1):63–74. https://doi.org/10.1016/j.artmed.2009.05.002.CrossRefPubMedGoogle Scholar
- 23.Revell AD, Wang D, Wood R, Morrow C, Tempelman H, Hamers RL, Alvarez-Uria G, Streinu-Cercel A, Ene L, Wensing AM, DeWolf F. Computational models can predict response to HIV therapy without a genotype and may reduce treatment failure in different resource-limited settings. J Antimicrob Chemother. 2013;68(6):1406–14. https://doi.org/10.1093/jac/dkt041.CrossRefPubMedPubMedCentralGoogle Scholar
- 24.Larder BA, DeGruttola V, Hammer S, Harrigan R, Wegner S, Winslow D, Zazzi M. The international HIV resistance response database initiative: a new global collaborative approach to relating viral genotype and treatment to clinical outcome. In: Antiviral therapy, vol. 7. London: International Medical Press Ltd; 2002. p. S111.Google Scholar
- 26.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. Proc Natl Acad Sci. 2002;99(12):8271–6. https://doi.org/10.1073/pnas.112177799.CrossRefPubMedGoogle Scholar
- 27.Deeks SG, Hellmann NS, Grant RM, Parkin NT, Petropoulos CJ, Becker M, Symonds W, Chesney M, Volberding PA. Novel four-drug salvage treatment regimens after failure of a human immunodeficiency virus type 1 protease inhibitor-containing regimen: antiviral activity and correlation of baseline phenotypic drug susceptibility with virologic outcome. J Infect Dis. 1999;179(6):1375–81. https://doi.org/10.1086/314775.CrossRefPubMedGoogle Scholar
- 30.Weinberger KQ, Saul LK. Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res. 2009;10(Feb):207–44.Google Scholar
- 32.Hirsch MS, Günthard HF, Schapiro JM, Vézinet FB, Clotet B, Hammer SM, Johnson VA, Kuritzkes DR, Mellors JW, Pillay D, Yeni PG. Antiretroviral drug resistance testing in adult HIV-1 infection: 2008 recommendations of an International AIDS Society-USA panel. Clin Infect Dis. 2008;47(2):266–85. https://doi.org/10.1086/589297.CrossRefPubMedGoogle Scholar
- 33.Department of Health and Human Services Panel on Antiretroviral Guidelines for Adults and Adolescents. Guidelines for the use of antiretroviral agents in HIV-1-infected adults and adolescents. Washington, DC: Department of Health and Human Services; 2006.Google Scholar
- 44.Huang Q, Jin H, Liu Q, Wu Q, Kang H, Cao Z, Zhu R. Proteochemometric modeling of the bioactivity spectra of HIV-1 protease inhibitors by introducing protein-ligand interaction fingerprint. PLoS One. 2012;7(7):e41698. https://doi.org/10.1371/journal.pone.0041698.CrossRefPubMedPubMedCentralGoogle Scholar
- 47.van Westen GJ, Hendriks A, Wegner JK, IJzerman AP, van Vlijmen HW, Bender A. Significantly improved HIV inhibitor efficacy prediction employing proteochemometric models generated from antivirogram data. PLoS Comput Biol. 2013;9(2):e1002899. https://doi.org/10.1371/journal.pcbi.1002899.CrossRefPubMedPubMedCentralGoogle Scholar