Exploration of unsupervised feature selection methods in relation to the prediction of cytokine release effect correlated to antibody features in RV144 vaccines

Computational methods such as clustering, classification and regression methods can be applied in immunoin-formatics to construct predictive models to reveal relationships between antibody features and their functional outcomes. This paper studies the effect of antibody features and the functional outcome obtained on RV144 vaccine recipients. The RV144 vaccine data set 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. Unlike semi-supervised and supervised feature selection methods, unsupervised feature selection methods provide unbiased approach as they are not dependent to response variable. In this paper, four different unsupervised feature selection methods are used in order to reveal the discriminating antibody features. Then, the support vector based methods are used in order to predict natural killer (NK) cell cytokine release effect. The results yield a high correlation coefficient as much as 0.59 and 0.72 for the support vector based regression (SVR) and classification (SVM) predictive models, respectively.