Logo des Repositoriums

Auflistung nach Autor:in "Mernberger, Marco"

1 - 3 von 3
  • Konferenzbeitrag
    Efficient similarity retrieval of protein binding sites based on histogram comparison
    (German Conference on Bioinformatics 2010, 2010) Fober, Thomas; Mernberger, Marco; Klebe, Gerhard; Hüllermeier, Eyke
    We propose a method for comparing protein structures or, more specifically, protein binding sites using a histogram-based representation that captures important geometrical and physico-chemical properties. In comparison to hitherto existing approaches in structural bioinformatics, especially methods from graph theory and computational geometry, our approach is computationally much more efficient. Moreover, despite its simplicity, it appears to capture and recover functional similarities surprisingly well.
  • Konferenzbeitrag
    Evolutionary Construction of Multiple Graph Alignments for the Structural Analysis of Biomolecules
    (German Conference on Bioinformatics, 2008) Fober, Thomas; Hüllermeier, Eyke; Mernberger, Marco
    The concept of multiple graph alignment has recently been introduced as a novel method for the structural analysis of biomolecules. Using inexact, approximate graph-matching techniques, this method enables the robust identification of approximately conserved patterns in biologically related structures. In particular, multiple graph alignments enable the characterization of functional protein families independent of sequence or fold homology. This paper first recalls the concept of multiple graph alignment and then addresses the problem of computing optimal alignments from an algorithmic point of view. In this regard, a method from the field of evolutionary algorithms is proposed and empirically compared to a hitherto existing greedy strategy. Empirically, it is shown that the former yields significantly better results than the latter, albeit at the cost of an increased runtime.
  • Konferenzbeitrag
    Graph-kernels for the comparative analysis of protein active sites
    (German conference on bioinformatics 2009, 2009) Fober, Thomas; Mernberger, Marco; Moritz, Ralph; Hüllermeier, Eyke
    Graphs are often used to describe and analyze the geometry and physicochemical composition of biomolecular structures, such as chemical compounds and protein active sites. A key problem in graph-based structure analysis is to define a measure of similarity that enables a meaningful comparison of such structures. In this regard, so-called kernel functions have recently attracted a lot of attention, especially since they allow for the application of a rich repertoire of methods from the field of kernel-based machine learning. Most of the existing kernel functions on graph structures, however, have been designed for the case of unlabeled and/or unweighted graphs. Since proteins are often more naturally and more exactly represented in terms of node-labeled and edge-weighted graphs, we propose corresponding extensions of existing graph kernels. Moreover, we propose an instance of the substructure fingerprint kernel suitability for the analysis of protein binding sites. The performance of these kernels is investigated by means of an experimental study in which graph kernels are used as similarity measures in the context of classification.