Prototype based machine learning for clinical proteomics

Clinical proteomics opens the way towards new insights into many diseases on a level of detail not available before. One of the most promising measurement techniques supporting this approach is mass spectrometry based clinical proteomics. The analysis of the high dimensional data obtained from mass spectrometry asks for sophisticated, problem adequate preprocessing and data analysis approaches. Ideally, automatic analysis tools provide insight into their behavior and the ability to extract further information, relevant for an understanding of the clinical data or applications such as biomarker discovery. Prototype based algorithms constitute efficient, intuitive and powerful machine learning methods which are very well suited to deal with high dimensional data and which allow good insight into their behavior by means of prototypical data locations. They have already successfully been applied to various problems in bioinformatics. The goal of this thesis is to extend prototype based methods, in such a way that they become suitable machine learning tools for typical problems in clinical proteomics. To achieve better adapted classification borders, tailored to the specific data distributions which occur in clinical proteomics, the prototype based algorithms are extended by local relevance determination and other problem specific metrics. Fuzzy classification is introduced into prototype approaches to allow for the integration of insecure class label information and to provide the possibility to judge the safety of the classification as it is typically needed in clinical domains. Further margin based active learning is developed to achieve a faster training and better generalization ability ideally suited for the often complex classification problems in clinical research. All algorithms are extensively tested for several clinical data sets in the context of cancer research, including publicly available benchmark data sets as well as recent clinical data sets obtained by state-of-the-art biotechnology.