@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{AnkenbrandWeberBeckeretal.2016, author = {Ankenbrand, Markus J. and Weber, Lorenz and Becker, Dirk and F{\"o}rster, Frank and Bemm, Felix}, title = {TBro: visualization and management of de novo transcriptomes}, series = {Database}, volume = {2016}, journal = {Database}, doi = {10.1093/database/baw146}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-147954}, pages = {baw146}, year = {2016}, abstract = {RNA sequencing (RNA-seq) has become a powerful tool to understand molecular mechanisms and/or developmental programs. It provides a fast, reliable and cost-effective method to access sets of expressed elements in a qualitative and quantitative manner. Especially for non-model organisms and in absence of a reference genome, RNA-seq data is used to reconstruct and quantify transcriptomes at the same time. Even SNPs, InDels, and alternative splicing events are predicted directly from the data without having a reference genome at hand. A key challenge, especially for non-computational personnal, is the management of the resulting datasets, consisting of different data types and formats. Here, we present TBro, a flexible de novo transcriptome browser, tackling this challenge. TBro aggregates sequences, their annotation, expression levels as well as differential testing results. It provides an easy-to-use interface to mine the aggregated data and generate publication-ready visualizations. Additionally, it supports users with an intuitive cart system, that helps collecting and analysing biological meaningful sets of transcripts. TBro's modular architecture allows easy extension of its functionalities in the future. Especially, the integration of new data types such as proteomic quantifications or array-based gene expression data is straightforward. Thus, TBro is a fully featured yet flexible transcriptome browser that supports approaching complex biological questions and enhances collaboration of numerous researchers.}, language = {en} } @article{KunzLiangNillaetal.2016, author = {Kunz, Meik and Liang, Chunguang and Nilla, Santosh and Cecil, Alexander and Dandekar, Thomas}, title = {The drug-minded protein interaction database (DrumPID) for efficient target analysis and drug development}, series = {Database}, volume = {2016}, journal = {Database}, doi = {10.1093/database/baw041}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-147369}, pages = {baw041}, year = {2016}, abstract = {The drug-minded protein interaction database (DrumPID) has been designed to provide fast, tailored information on drugs and their protein networks including indications, protein targets and side-targets. Starting queries include compound, target and protein interactions and organism-specific protein families. Furthermore, drug name, chemical structures and their SMILES notation, affected proteins (potential drug targets), organisms as well as diseases can be queried including various combinations and refinement of searches. Drugs and protein interactions are analyzed in detail with reference to protein structures and catalytic domains, related compound structures as well as potential targets in other organisms. DrumPID considers drug functionality, compound similarity, target structure, interactome analysis and organismic range for a compound, useful for drug development, predicting drug side-effects and structure-activity relationships.}, language = {en} }