Longitudinal analysis for predicting amino acid changes in HIV-1 using association rule mining

The human immunodeficiency virus (HIV) remains a great challenge for humanity. HIV is characterised by high mutational rate, resulting in pathogenic variants that promotes the escape of immune response. In order to understand the correlations between amino acid mutations of the virus and quantify the evolutionary in HIV, we present a novel approach based on association rule mining (ARM) from protein sequence data taken at different time points. In this study, a longitudinal association rule mining (LARM) algorithm has been proposed. We collected the entire genome of 100 untreated HIV-1 infected patients over 3-5 years of infection, with 6-10 longitudinal samples per patient. We used the Los Alamos intra-patient search interface. Our experiments show the effectiveness of the proposed method in discovering major amino acid changes in comparison with the temporal analysis.