Exploring Mutational Pathways of HIV Using Genetic Algorithm

The Human Immunodeficiency virus (HIV) is caused due to the failure of the immune system that leads to life threatening infections and cancer. Even though most drug resistance mutations have been identified throughout, the dynamics and temporal patterns of these mutations can still be explored. In order to explore the drug resistance mutation, Temporal Bayesian Networks (TNBN) algorithm is used where data is extracted from Stanford HIV drug resistance database. TNBN work needs more iterative process and training data for accurate information and it has failed to compare two different mixture treatments along with the temporal occurrence of drug resistant mutations, in order to predict the most effective treatment. The proposed work performs P_GA (Prediction Genetic Algorithm) which is a prediction scheme with the slotted training dataset changing values. The study shows the proposed techniques provides better results than existing temporal node Bayesian network scheme in terms of accuracy.