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 respect to the virologic outcomes in HIV-1-infected patients. Currently employed methodologies are based on the paradigm for which mutations present in patient viral genotypes, selected either by treatment or already transmitted to the patient as resistant mutants, are the major drivers of virologic outcomes. Genotypic interpretation systems have been designed with the prime objective of characterizing the resistance to individual drugs, deriving scores from the association of viral genotypes with in vitro phenotypic drug susceptibility or in vivo response to treatment. Nevertheless, the very large range of possible drug combinations and of viral mutational patterns leads to an extremely complex scenario, making prediction of in vivo treatment response extremely challenging. To deal with such complexity, machine learning methods are being increasingly explored, thanks to the availability of exponentially growing HIV data bases in recent years. The combination of genotypic interpretation systems with other laboratory markers, treatment history, past clinical events, and the usage of data-driven techniques has dramatically raised the confidence in predicting virologic outcomes. A few of these systems have been implemented as free web-services, indicating ranks of suitable combination antiretroviral therapy regimens given a patient's clinical background. Future perspectives in the field foresee the extension of therapy optimization systems to newly approved antiretroviral drug targets and the prediction of other clinical outcomes, rather than the sole virologic response.

Prosperi, M., DE LUCA, A. (2012). Computational models for prediction of response to antiretroviral therapies. AIDS REVIEWS, 14(2), 145-153.

Computational models for prediction of response to antiretroviral therapies

DE LUCA, ANDREA
2012-01-01

Abstract

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 respect to the virologic outcomes in HIV-1-infected patients. Currently employed methodologies are based on the paradigm for which mutations present in patient viral genotypes, selected either by treatment or already transmitted to the patient as resistant mutants, are the major drivers of virologic outcomes. Genotypic interpretation systems have been designed with the prime objective of characterizing the resistance to individual drugs, deriving scores from the association of viral genotypes with in vitro phenotypic drug susceptibility or in vivo response to treatment. Nevertheless, the very large range of possible drug combinations and of viral mutational patterns leads to an extremely complex scenario, making prediction of in vivo treatment response extremely challenging. To deal with such complexity, machine learning methods are being increasingly explored, thanks to the availability of exponentially growing HIV data bases in recent years. The combination of genotypic interpretation systems with other laboratory markers, treatment history, past clinical events, and the usage of data-driven techniques has dramatically raised the confidence in predicting virologic outcomes. A few of these systems have been implemented as free web-services, indicating ranks of suitable combination antiretroviral therapy regimens given a patient's clinical background. Future perspectives in the field foresee the extension of therapy optimization systems to newly approved antiretroviral drug targets and the prediction of other clinical outcomes, rather than the sole virologic response.
2012
Prosperi, M., DE LUCA, A. (2012). Computational models for prediction of response to antiretroviral therapies. AIDS REVIEWS, 14(2), 145-153.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/1011579
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo