A supervised feature selection framework in relation to prediction of antibody feature-function activity relationships in RV144 vaccines

Abstract

Identification of functional characteristics of the virus-antibody interplay in individuals can provide insight to the development of effective vaccines against HIV virus. In order to reveal the functional interactions between human immune system and HIV virus, computational methods such as clustering, classification, feature selection and regression methods can be utilised to construct predictive models. The purpose of this study is to predict the associations between antibody features and effector function activities on RV144 vaccine recipients. The RV144 vaccine dataset contains 100 data samples in which 20 of them are the placebo samples and 80 of them are the vaccine injected samples. Each data sample has twenty antibody features that consist of features related to IgG subclass and antigen specificity. In this study, we proposed a novel supervised feature selection framework to identify the discriminating antibody features from RV144 vaccine dataset. Then, the Support Vector Regression is utilised to quantitatively predict the association between antibody features (IgGs) and effector function activities. Three different cell-mediated assays are utilised in this study to characterise effector function activities: antibody dependent cellular phagocytosis (ADCP), antibody dependent cellular cytotoxicity (ADCC), and natural killer cell cytokine release. Promising experimental results on these three cell-based assays have validated the effectiveness of our proposed framework. The prediction performance of proposed feature selection framework is compared to the previous studies which utilised the RV144 dataset for the same purpose.