Prognostic Prediction Using Clinical Expression Time Series: Towards a Supervised Learning Approach Based on Meta-biclusters

Abstract

AbstractBiclustering has been recognized as a remarkably effective method for discovering local temporal expression patterns and unraveling potential regulatory mechanisms, critical to understand complex biomedical processes, such as disease progression and drug response. In this work, we propose a classification approach based on meta-biclusters (a set of similar biclusters) applied to prognostic prediction. We use real clinical expression time series to predict the response of patients with multiple sclerosis to treatment with Interferon-β . The main advantages of this strategy are the interpretability of the results and the reduction of data dimensionality, due to biclustering. Preliminary results anticipate the possibility of recognizing the most promising genes and time points explaining different types of response profiles, according to clinical knowledge. The impact on the classification accuracy of different techniques for unsupervised discretization of the data is studied.KeywordsSupport Vector MachineGood ResponderPrognostic PredictionSupervise Learn ApproachExpression Time SeriesThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.