Identification of Clinically Relevant HIV Vif Protein Motif Mutations through Machine Learning and Undersampling.

Human Immunodeficiency virus (HIV) and its clinical entity, the Acquired Immunodeficiency Syndrome (AIDS) continue to represent an important health burden worldwide. Although great advances have been made towards determining the way viral genetic diversity affects clinical outcome, genetic association studies have been hindered by the complexity of their interactions with the human host. This study provides an innovative approach for the identification and analysis of epidemiological associations between HIV Viral Infectivity Factor (Vif) protein mutations and four clinical endpoints (Viral load and CD4 T cell numbers at time of both clinical debut and on historical follow-up of patients. Furthermore, this study highlights an alternative approach to the analysis of imbalanced datasets, where patients without specific mutations outnumber those with mutations. Imbalanced datasets are still a challenge hindering the development of classification algorithms through machine learning. This research deals with Decision Trees, Naïve Bayes (NB), Support Vector Machines (SVMs), and Artificial Neural Networks (ANNs). This paper proposes a new methodology considering an undersampling approach to deal with imbalanced datasets and introduces two novel and differing approaches (MAREV-1 and MAREV-2). As theses approaches do not involve human pre-determined and hypothesis-driven combinations of motifs having functional or clinical relevance, they provide a unique opportunity to discover novel complex motif combinations of interest. Moreover, the motif combinations found can be analyzed through traditional statistical approaches avoiding statistical corrections for multiple tests.

Computational Forecasting Methodology for Acute Respiratory Infectious Disease Dynamics.

The study of infectious disease behavior has been a scientific concern for many years as early identification of outbreaks provides great advantages including timely implementation of public health measures to limit the spread of an epidemic. We propose a methodology that merges the predictions of (i) a computational model with machine learning, (ii) a projection model, and (iii) a proposed smoothed endemic channel calculation. The predictions are made on weekly acute respiratory infection (ARI) data obtained from epidemiological reports in Mexico, along with the usage of key terms in the Google search engine. The results obtained with this methodology were compared with state-of-the-art techniques resulting in reduced root mean squared percentage error (RMPSE) and maximum absolute percent error (MAPE) metrics, achieving a MAPE of 21.7%. This methodology could be extended to detect and raise alerts on possible outbreaks on ARI as well as for other seasonal infectious diseases.