Statistical Comparison of Machine Learning Techniques for Treatment Optimisation of Drug-Resistant HIV-1

Predicting the in-vivo effect of genotypic drug resistance of Human Immunodeficiency Virus type-1 (HIV-1) on response to antiretroviral therapies represents a major clinical issue. Different machine learning and feature selection methods are applied for the classification of treatment success, based on viral genotype, therapy and derived input features. The robustness of results is assessed through statistical validation. The procedures described are intended to be a general methodology in the challenging context of biology and medical science data mining.