Prototype based Classification in Bioinformatics Frank-M. Schleif*, schleif@informatik.uni-leipzig.de Thomas Villmann, villmann@informatik.uni-leipzig.de Barbara Hammer, hammer@in.tu-clausthal.de Dept. of Medicine, University of Leipzig, Germany Dept. of Computer Science, Technical University of Clausthal, Germany INTRODUCTION Bioinformatics has become an important tool to support clinical and biological research and the analysis of functional data, is a common task in bioinformatics (Schleif, 2006). Gene analysis in form of micro array analysis (Schena, 1995) and protein analysis (Twyman, 2004) are the most important fields leading to multiple sub omics-disciplines like pharmacogenomics, glycoproteomics or metabolomics. Measurements of such studies are high dimensional functional data with few samples for specific problems (Pusch, 2005). This leads to new challenges in the data analysis. Spectra of mass spectrometric measurements are such functional data requiring an appropriate analysis (Schleif, 2006). Here we focus on the determination of classification models for such data. In general, the spectra are transformed into a vector space followed by training a classifier (Haykin, 1999). Hereby the functional nature of the data is typically lost. We present a method which takes this specific data aspects into account. A wavelet encoding (Mallat, 1999) is applied onto the spectral data leading to a compact functional representation. Subsequently the Supervised Neural Gas classifier (Hammer, 2005) is applied, capable to handle functional metrics as introduced by Lee & Verleysen (Lee, 2005). This allows the classifier to utilize the functional nature of the data in the modelling process. The presented method is applied to clinical proteome data showing good results and can be used as a bioinformatics method for biomarker discovery. BACKGROUND Applications of mass spectrometry (ms) in clinical proteomics have gained tremendous visibility in the scientific and clinical community (Villanueva, 2004) (Ketterlinus, 2005). One major objective is the search for potential classification models for cancer studies, with strong requirements for validated signal patterns (Ransohoff, 2005). Primal optimistic results as given in (Petricoin, 2002) are now considered more carefully, because the complexity of the task of biomarker discovery and an appropriate data processing has been observed to be more challenging than expected (Ransohoff, 2005). Consequently the main recent work in this field is focusing on optimization and standardisation. This includes the biochemical part (e.g. Baumann, 2005), the measurement (Orchard, 2003) and the subsequently data analysis (Morris, 2005)(Schleif 2006).