Machine learning approaches to study HIV / AIDS infection : A Review

  title={Machine learning approaches to study HIV / AIDS infection : A Review},
  author={Sweta Kumari and Usha Chouhan and Sunil Kumar Suryawanshi},
In this review, PubMed database has been explored to elucidate the problems related to HIV/AIDS, which have been solved previously using various machine learning approaches and some other techniques. Literatures from the epidemic years of HIV/AIDS till February, 2017 have been examined and problems such as prediction of HIV/AIDS protease cleavage sites and inhibitors, prediction of coreceptors usage for viral entry, development of anti-viral agents and prediction of response, resistance and… 

Figures and Tables from this paper

Futuristic Methods for Determining HIV Co-receptor Use
Advances in surface plasmon resonance, biolayer interferometry and glycol-FRET technologies will be fundamental for real time investigation of molecular mechanisms involvement in Env-receptor interactions, which will enhance the understanding of coreceptor usage and viral tropism determinants.
Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa
A potential use of the XGBoost algorithm with socio-behavioural-driven data at substantially identifying HIV predictors and predicting individuals at high risk of infection for targeted screening is provided.
Use of Artificial Intelligence and Machine Learning for Discovery of Drugs for Neglected Tropical Diseases
Neglected tropical diseases continue to create high levels of morbidity and mortality in a sizeable fraction of the world’s population, despite ongoing research into new treatments. Some of the most
Precision medicine and digital phenotyping: Digital medicine's way from more data to better health
The analysis shows how digital data informs potentials as well as challenges of precision medicine and digital phenotyping: a better health care for (some) individuals connected with individualisation and responsibilisation for all, with a prognosed shift from reactive to preventive medicine.


Multilabel classification for exploiting cross-resistance information in HIV-1 drug resistance prediction
Based on multilabel classification models and cross-resistance information, this study was able to significantly improve overall prediction accuracy for all drugs, and identified drug-specific patterns within the reverse transcriptase sequences that can be used to determine an optimal order of the classifiers within the classifier chains.
Predicting Response to Antiretroviral Treatment by Machine Learning: The EuResist Project
Next-generation treatment response prediction engines may valuably assist the HIV specialist in the challenging task of establishing effective regimens for patients harboring drug-resistant virus strains.
Computational models for prediction of response to antiretroviral therapies.
This review describes the state-of-the-art in statistical, machine learning, and expert-advised computational methods for the evaluation and optimization of combination antiretroviral therapy, with
Prediction of Co-Receptor Usage of HIV-1 from Genotype
A two-level machine learning approach that in the first level considers two different properties important for protein-protein binding derived from structural models of V3 and V3 sequences and quantifies the importance for co-receptor usage of a pocket that probably is responsible for binding sulfated tyrosine.
Virtual Screening Models for Prediction of HIV-1 RT Associated RNase H Inhibition
Flexible docking experiments is the model of choice in terms of best retrieval of active from inactive compounds and efficiency and efficacy schemes and shape similarity, machine learning and FLAP models could also be used for further validation or filtration in virtual screening processes.
Pathogenesis of macrophage tropic HIV-1.
Evidence is highlighted supporting the hypothesis that enhanced M-tropism of R5 HIV-1 results from adaptive viral evolution, resulting in HIV-2 variants that have increased ability to utilize relatively low levels of CD4 and CCR5 expressed on macrophages, and suggests that these late-emerging, R5 viral strains have reduced sensitivity to entry inhibitors, and increased able to cause CD4+ T-lymphocyte loss.
The biology of CCR5 and CXCR4
  • G. Alkhatib
  • Biology, Chemistry
    Current opinion in HIV and AIDS
  • 2009
The coreceptor discoveries revealed new insights into host and viral factors influencing HIV transmission and disease, and new drugs that promote CCR5 and CXCR4 internalization, independent of cellular signaling, might provide clinical benefits with minimum side effects.
Evidence for the cure of HIV infection by CCR5Δ32/Δ32 stem cell transplantation.
Successful reconstitution of CD4(+) T cells at the systemic level as well as in the gut mucosal immune system after CCR5Δ32/Δ 32 stem cell transplantation is demonstrated, suggesting that cure of HIV has been achieved in this patient.
IDEPI: Rapid Prediction of HIV-1 Antibody Epitopes and Other Phenotypic Features from Sequence Data Using a Flexible Machine Learning Platform
Drawing upon open-source general-purpose machine learning algorithms and libraries, the software package IDEPI (IDentify EPItopes) for learning genotype-to-phenotype predictive models from sequences with known phenotypes achieves performance similar to or better than that of previously published approaches on four well-studied problems.
Development of anti-viral agents using molecular modeling and virtual screening techniques.
The role of computational chemistry in the development of small molecules as agents against HIV integrase, HIV-1 protease, HIV -1 reverse transcriptase, the influenza virus M2 channel protein, influenza virus neuraminidase, SARS coronavirus main proteinase and spike protein, thymidine kinases of herpes viruses, hepatitis c virus proteins and other flaviviruses are discussed.