@article{StaigerCadotKooteretal.2012,
  author    = {Staiger, Christine and Cadot, Sidney and Kooter, Raul and Dittrich, Marcus and M{\"u}ller, Tobias and Klau, Gunnar W. and Wessels, Lodewyk F. A.},
  title     = {A Critical Evaluation of Network and Pathway-Based Classifiers for Outcome Prediction in Breast Cancer},
  series = {PLoS One},
  volume    = {7},
  journal   = {PLoS One},
  number    = {4},
  doi       = {10.1371/journal.pone.0034796},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-131323},
  pages     = {e34796},
  year      = {2012},
  abstract  = {Recently, several classifiers that combine primary tumor data, like gene expression data, and secondary data sources, such as protein-protein interaction networks, have been proposed for predicting outcome in breast cancer. In these approaches, new composite features are typically constructed by aggregating the expression levels of several genes. The secondary data sources are employed to guide this aggregation. Although many studies claim that these approaches improve classification performance over single genes classifiers, the gain in performance is difficult to assess. This stems mainly from the fact that different breast cancer data sets and validation procedures are employed to assess the performance. Here we address these issues by employing a large cohort of six breast cancer data sets as benchmark set and by performing an unbiased evaluation of the classification accuracies of the different approaches. Contrary to previous claims, we find that composite feature classifiers do not outperform simple single genes classifiers. We investigate the effect of (1) the number of selected features; (2) the specific gene set from which features are selected; (3) the size of the training set and (4) the heterogeneity of the data set on the performance of composite feature and single genes classifiers. Strikingly, we find that randomization of secondary data sources, which destroys all biological information in these sources, does not result in a deterioration in performance of composite feature classifiers. Finally, we show that when a proper correction for gene set size is performed, the stability of single genes sets is similar to the stability of composite feature sets. Based on these results there is currently no reason to prefer prognostic classifiers based on composite features over single genes classifiers for predicting outcome in breast cancer.},
  language  = {en}
}
@article{PinkertSchultzReichardt2010,
  author    = {Pinkert, Stefan and Schultz, Joerg and Reichardt, Joerg},
  title     = {Protein Interaction Networks-More Than Mere Modules},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-68426},
  year      = {2010},
  abstract  = {It is widely believed that the modular organization of cellular function is reflected in a modular structure of molecular networks. A common view is that a ''module'' in a network is a cohesively linked group of nodes, densely connected internally and sparsely interacting with the rest of the network. Many algorithms try to identify functional modules in protein-interaction networks (PIN) by searching for such cohesive groups of proteins. Here, we present an alternative approach independent of any prior definition of what actually constitutes a ''module''. In a self-consistent manner, proteins are grouped into ''functional roles'' if they interact in similar ways with other proteins according to their functional roles. Such grouping may well result in cohesive modules again, but only if the network structure actually supports this. We applied our method to the PIN from the Human Protein Reference Database (HPRD) and found that a representation of the network in terms of cohesive modules, at least on a global scale, does not optimally represent the network's structure because it focuses on finding independent groups of proteins. In contrast, a decomposition into functional roles is able to depict the structure much better as it also takes into account the interdependencies between roles and even allows groupings based on the absence of interactions between proteins in the same functional role. This, for example, is the case for transmembrane proteins, which could never be recognized as a cohesive group of nodes in a PIN. When mapping experimental methods onto the groups, we identified profound differences in the coverage suggesting that our method is able to capture experimental bias in the data, too. For example yeast-two-hybrid data were highly overrepresented in one particular group. Thus, there is more structure in protein-interaction networks than cohesive modules alone and we believe this finding can significantly improve automated function prediction algorithms.},
  subject      = {Netzwerk},
  language  = {en}
}