Publications
Schulz-Trieglaff, Ole; Pfeifer, Nico; Gröpl, Clemens; Kohlbacher, Oliver; Reinert, Knut LC-MSsim - a simulation software for Liquid ChromatographyMass Spectrometry data BMC Bioinformatics, 9 , pp. 423, 2008. @article{LCMSSim, title = {LC-MSsim - a simulation software for Liquid ChromatographyMass Spectrometry data}, author = {Ole Schulz-Trieglaff and Nico Pfeifer and Clemens Gröpl and Oliver Kohlbacher and Knut Reinert}, url = {http://www.biomedcentral.com/1471-2105/9/423}, year = {2008}, date = {2008-01-01}, journal = {BMC Bioinformatics}, volume = {9}, pages = {423}, abstract = {Background Mass Spectrometry coupled to Liquid Chromatography (LC-MS) is commonly used to analyze the protein content of biological samples in large scale studies. The data resulting from an LC-MS experiment is huge, highly complex and noisy. Accordingly, it has sparked new developments in Bioinformatics, especially in the fields of algorithm development, statistics and software engineering. In a quantitative label-free mass spectrometry experiment, crucial steps are the detection of peptide features in the mass spectra and the alignment of samples by correcting for shifts in retention time. At the moment, it is difficult to compare the plethora of algorithms for these tasks. So far, curated benchmark data exists only for peptide identification algorithms but no data that represents a ground truth for the evaluation of feature detection, alignment and filtering algorithms. Results We present LC-MSsim, a simulation software for LC-ESI-MS experiments. It simulates ESI spectra on the MS level. It reads a list of proteins from a FASTA file and digests the protein mixture using a user-defined enzyme. The software creates an LC-MS data set using a predictor for the retention time of the peptides and a model for peak shapes and elution profiles of the mass spectral peaks. Our software also offers the possibility to add contaminants, to change the background noise level and includes a model for the detectability of peptides in mass spectra. After the simulation, LC-MSsim writes the simulated data to mzData, a public XML format. The software also stores the positions (monoisotopic m/z and retention time) and ion counts of the simulated ions in separate files. Conclusion LC-MSsim generates simulated LC-MS data sets and incorporates models for peak shapes and contaminations. Algorithm developers can match the results of feature detection and alignment algorithms against the simulated ion lists and meaningful error rates can be computed. We anticipate that LC-MSsim will be useful to the wider community to perform benchmark studies and comparisons between computational tools.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background Mass Spectrometry coupled to Liquid Chromatography (LC-MS) is commonly used to analyze the protein content of biological samples in large scale studies. The data resulting from an LC-MS experiment is huge, highly complex and noisy. Accordingly, it has sparked new developments in Bioinformatics, especially in the fields of algorithm development, statistics and software engineering. In a quantitative label-free mass spectrometry experiment, crucial steps are the detection of peptide features in the mass spectra and the alignment of samples by correcting for shifts in retention time. At the moment, it is difficult to compare the plethora of algorithms for these tasks. So far, curated benchmark data exists only for peptide identification algorithms but no data that represents a ground truth for the evaluation of feature detection, alignment and filtering algorithms. Results We present LC-MSsim, a simulation software for LC-ESI-MS experiments. It simulates ESI spectra on the MS level. It reads a list of proteins from a FASTA file and digests the protein mixture using a user-defined enzyme. The software creates an LC-MS data set using a predictor for the retention time of the peptides and a model for peak shapes and elution profiles of the mass spectral peaks. Our software also offers the possibility to add contaminants, to change the background noise level and includes a model for the detectability of peptides in mass spectra. After the simulation, LC-MSsim writes the simulated data to mzData, a public XML format. The software also stores the positions (monoisotopic m/z and retention time) and ion counts of the simulated ions in separate files. Conclusion LC-MSsim generates simulated LC-MS data sets and incorporates models for peak shapes and contaminations. Algorithm developers can match the results of feature detection and alignment algorithms against the simulated ion lists and meaningful error rates can be computed. We anticipate that LC-MSsim will be useful to the wider community to perform benchmark studies and comparisons between computational tools. |
Toussaint, Nora C; Dönnes, Pierre; Kohlbacher, Oliver A Mathematical Framework for the Selection of an Optimal Set of Peptides for Epitope-based Vaccines PLoS Comput. Biol., 4 (12), pp. e1000246, 2008. @article{OptVacDes, title = {A Mathematical Framework for the Selection of an Optimal Set of Peptides for Epitope-based Vaccines}, author = {Nora C Toussaint and Pierre Dönnes and Oliver Kohlbacher}, url = {http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1000246}, year = {2008}, date = {2008-01-01}, journal = {PLoS Comput. Biol.}, volume = {4}, number = {12}, pages = {e1000246}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Keller, Andreas C; Backes, Christina; Al-Awadhi, Maher; Gerasch, Andreas; Küntzer, Jan; Kohlbacher, Oliver; Kaufmann, Michael; Lenhof, Hans-Peter GeneTrailExpress: a web-based pipeline for the statistical evaluation of microarray experiments BMC Bioinformatics, 9 , pp. 552, 2008. @article{GTXP, title = {GeneTrailExpress: a web-based pipeline for the statistical evaluation of microarray experiments}, author = {Andreas C Keller and Christina Backes and Maher Al-Awadhi and Andreas Gerasch and Jan Küntzer and Oliver Kohlbacher and Michael Kaufmann and Hans-Peter Lenhof}, url = {http://www.biomedcentral.com/1471-2105/9/552}, year = {2008}, date = {2008-01-01}, journal = {BMC Bioinformatics}, volume = {9}, pages = {552}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Reinert, Knut; Huber, Christian; Marcus, Kathrin; Linial, Michal; Kohlbacher, Oliver 08101 Executive Summary and Abstracts Collection - Computational Proteomics Huber, Christian; Kohlbacher, Oliver; Linial, Michal; Marcus, Katrin; Reinert, Knut (Ed.): Computational Proteomics, Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany, Dagstuhl, Germany, 2008. @inproceedings{reinert_et_alDSP20081784, title = {08101 Executive Summary and Abstracts Collection - Computational Proteomics}, author = {Knut Reinert and Christian Huber and Kathrin Marcus and Michal Linial and Oliver Kohlbacher}, editor = {Christian Huber and Oliver Kohlbacher and Michal Linial and Katrin Marcus and Knut Reinert}, url = {http://drops.dagstuhl.de/opus/volltexte/2008/1784}, year = {2008}, date = {2008-01-01}, booktitle = {Computational Proteomics}, publisher = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany}, address = {Dagstuhl, Germany}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Timm, Wiebke; Scherbart, Alexandra; Böcker, Sebastian; Kohlbacher, Oliver; Nattkemper, Tim W Peak Intensity Prediction in MALDI-TOF Mass Spectrometry: A Machine Learning Study to Support Quantitative Proteomics BMC Bioinformatics, 9 , pp. 443, 2008. @article{MALDI-Int, title = {Peak Intensity Prediction in MALDI-TOF Mass Spectrometry: A Machine Learning Study to Support Quantitative Proteomics}, author = {Wiebke Timm and Alexandra Scherbart and Sebastian Böcker and Oliver Kohlbacher and Tim W Nattkemper}, url = {http://www.biomedcentral.com/1471-2105/9/443}, year = {2008}, date = {2008-01-01}, journal = {BMC Bioinformatics}, volume = {9}, pages = {443}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Reinert, Knut; Conrad, Tim; Kohlbacher, Oliver Bioinformatics Support for Mass Spectrometric Quality Control von Hagen, Jörg (Ed.): Proteomics Sample Preparation, Chapter 13.1, pp. 423-447, Wiley-VCH, Weinheim, 2008, (ISBN 978-3-527-31796-7). @inbook{ProteomicsSamplePreparationChapter, title = {Bioinformatics Support for Mass Spectrometric Quality Control}, author = {Knut Reinert and Tim Conrad and Oliver Kohlbacher}, editor = {Jörg von Hagen}, url = {http://eu.wiley.com/WileyCDA/WileyTitle/productCd-3527317961.html}, year = {2008}, date = {2008-01-01}, booktitle = {Proteomics Sample Preparation}, pages = {423-447}, publisher = {Wiley-VCH}, address = {Weinheim}, chapter = {13.1}, note = {ISBN 978-3-527-31796-7}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
Blum, Torsten; Kohlbacher, Oliver MetaRoute - fast search for relevant metabolic routes for interactive network navigation and visualization Bioinformatics, 24 (18), pp. 2108-2109, 2008. @article{MetaRoute, title = {MetaRoute - fast search for relevant metabolic routes for interactive network navigation and visualization}, author = {Torsten Blum and Oliver Kohlbacher}, url = {http://dx.doi.org/10.1093/bioinformatics/btn360}, year = {2008}, date = {2008-01-01}, journal = {Bioinformatics}, volume = {24}, number = {18}, pages = {2108-2109}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Böcker, Sebastian; Briesemeister, Sebastian; Klau, Gunnar W Exact Algorithms for Cluster Editing: Evaluation and Experiments Proc. of Workshop on Experimental Algorithms (WEA 2008), pp. 289–302, Springer, 2008. @inproceedings{boecker08exact, title = {Exact Algorithms for Cluster Editing: Evaluation and Experiments}, author = {Sebastian Böcker and Sebastian Briesemeister and Gunnar W Klau}, url = {http://dx.doi.org/10.1007/978-3-540-68552-4}, year = {2008}, date = {2008-01-01}, booktitle = {Proc. of Workshop on Experimental Algorithms (WEA 2008)}, volume = {5038}, pages = {289--302}, publisher = {Springer}, series = {Lect. Notes Comput. Sc.}, abstract = {We present empirical results for the Cluster Editing problem using exact methods from fixed-parameter algorithmics and linear programming. We investigate parameter-independent data reduction methods and find that effective preprocessing is possible if the number of edge modifications k is smaller than some multiple of |V|. In particular, combining parameter-dependent data reduction with lower and upper bounds we can effectively reduce graphs satisfying k <= 25 |V|. In addition to the fastest known fixed-parameter branching strategy for the problem, we investigate an integer linear program (ILP) formulation of the problem using a cutting plane approach. Our results indicate that both approaches are capable of solving large graphs with 1000 vertices and several thousand edge modifications. For the first time, complex and very large graphs such as biological instances allow for an exact solution, using a combination of the above techniques.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present empirical results for the Cluster Editing problem using exact methods from fixed-parameter algorithmics and linear programming. We investigate parameter-independent data reduction methods and find that effective preprocessing is possible if the number of edge modifications k is smaller than some multiple of |V|. In particular, combining parameter-dependent data reduction with lower and upper bounds we can effectively reduce graphs satisfying k <= 25 |V|. In addition to the fastest known fixed-parameter branching strategy for the problem, we investigate an integer linear program (ILP) formulation of the problem using a cutting plane approach. Our results indicate that both approaches are capable of solving large graphs with 1000 vertices and several thousand edge modifications. For the first time, complex and very large graphs such as biological instances allow for an exact solution, using a combination of the above techniques. |
Böcker, Sebastian; Briesemeister, Sebastian; Bui, Quang BaoAnh; Truss, Anke Going Weighted: Parameterized Algorithms for Cluster Editing Proc. of Conference on Combinatorial Optimization and Applications (COCOA 2008), pp. 1-12, Springer, 2008. @inproceedings{boecker08going, title = {Going Weighted: Parameterized Algorithms for Cluster Editing}, author = {Sebastian Böcker and Sebastian Briesemeister and Quang BaoAnh Bui and Anke Truss}, url = {http://dx.doi.org/10.1007/978-3-540-85097-7}, year = {2008}, date = {2008-01-01}, booktitle = {Proc. of Conference on Combinatorial Optimization and Applications (COCOA 2008)}, volume = {5165}, pages = {1-12}, publisher = {Springer}, series = {Lect. Notes Comput. Sc.}, abstract = {The goal of the Cluster Editing problem is to make the fewest changes to the edge set of an input graph such that the resulting graph is a disjoint union of cliques. This problem is NP-complete but recently, several parameterized algorithms have been proposed. In this paper we present a surprisingly simple branching strategy for Cluster Editing. We generalize the problem assuming that edge insertion and deletion costs are positive integers. We show that the resulting search tree has size O(1.82^k ) for edit cost k, resulting in the currently fastest parameterized algorithm for this problem. We have implemented and evaluated our approach, and find that it outperforms other parametrized algorithms for the problem.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The goal of the Cluster Editing problem is to make the fewest changes to the edge set of an input graph such that the resulting graph is a disjoint union of cliques. This problem is NP-complete but recently, several parameterized algorithms have been proposed. In this paper we present a surprisingly simple branching strategy for Cluster Editing. We generalize the problem assuming that edge insertion and deletion costs are positive integers. We show that the resulting search tree has size O(1.82^k ) for edit cost k, resulting in the currently fastest parameterized algorithm for this problem. We have implemented and evaluated our approach, and find that it outperforms other parametrized algorithms for the problem. |
Böcker, Sebastian; Briesemeister, Sebastian; Bui, Quang BaoAnh; Truss, Anke A fixed-parameter approach for Weighted Cluster Editing Proc. of Asia-Pacific Bioinformatics Conference (APBC 2008), pp. 211-220, Imperial College Press, 2008. @inproceedings{InproceedingsReference.2008-09-22.7125354507, title = {A fixed-parameter approach for Weighted Cluster Editing}, author = {Sebastian Böcker and Sebastian Briesemeister and Quang BaoAnh Bui and Anke Truss}, year = {2008}, date = {2008-01-01}, booktitle = {Proc. of Asia-Pacific Bioinformatics Conference (APBC 2008)}, volume = {5}, pages = {211-220}, publisher = {Imperial College Press}, series = {Series on Advances in Bioinformatics and Computational Biology}, abstract = {Clustering objects with respect to a given similarity or distance measure is a problem often encountered in computational biology. Several well-known clustering algorithms are based on transforming the input matrix into a weighted graph although the resulting Weighted Cluster Editing problem is computationally hard: here, we transform the input graph into a disjoint union of cliques such that the sum of weights of all modified edges is minimized. We present fixed-parameter algorithms for this problem which guarantee to find an optimal solution in provable worst-case running time.We introduce a new data reduction operation (merging vertices) that has no counterpart in the unweighted case and strongly cuts down running times in practice. We have applied our algorithms to both artificial and biological data. Despite the complexity of the problem, our method often allows exact computation of optimal solutions in reasonable running time.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Clustering objects with respect to a given similarity or distance measure is a problem often encountered in computational biology. Several well-known clustering algorithms are based on transforming the input matrix into a weighted graph although the resulting Weighted Cluster Editing problem is computationally hard: here, we transform the input graph into a disjoint union of cliques such that the sum of weights of all modified edges is minimized. We present fixed-parameter algorithms for this problem which guarantee to find an optimal solution in provable worst-case running time.We introduce a new data reduction operation (merging vertices) that has no counterpart in the unweighted case and strongly cuts down running times in practice. We have applied our algorithms to both artificial and biological data. Despite the complexity of the problem, our method often allows exact computation of optimal solutions in reasonable running time. |
Seebeck, Birte; Reulecke, Ingo; Kämper, Andreas; Rarey, Matthias Modeling of metal interaction geometries for protein-ligand docking Proteins: Struct., Funct., Bioinf., 71 (3), pp. 1237-1254, 2008. @article{metals, title = {Modeling of metal interaction geometries for protein-ligand docking}, author = {Birte Seebeck and Ingo Reulecke and Andreas Kämper and Matthias Rarey}, url = {http://dx.doi.org/10.1002/prot.21818}, year = {2008}, date = {2008-01-01}, journal = {Proteins: Struct., Funct., Bioinf.}, volume = {71}, number = {3}, pages = {1237-1254}, abstract = {The accurate modeling of metal coordination geometries plays an important role for structure-based drug design applied to metalloenzymes. For the development of a new metal interaction model, we perform a statistical analysis of metal interaction geometries that are relevant to protein-ligand complexes. A total of 43,061 metal sites of the Protein Data Bank (PDB), containing amongst others magnesium, calcium, zinc, iron, manganese, copper, cadmium, cobalt, and nickel, were evaluated according to their metal coordination geometry. Based on statistical analysis, we derived a model for the automatic calculation and definition of metal interaction geometries for the purpose of molecular docking analyses. It includes the identification of the metal-coordinating ligands, the calculation of the coordination geometry and the superposition of ideal polyhedra to identify the optimal positions for free coordination sites. The new interaction model was integrated in the docking software FlexX and evaluated on a data set of 103 metalloprotein-ligand complexes, which were extracted from the PDB. In a first step, the quality of the automatic calculation of the metal coordination geometry was analyzed. In 74% of the cases, the correct prediction of the coordination geometry could be determined on the basis of the protein structure alone. Secondly, the new metal interaction model was tested in terms of predicting protein-ligand complexes. In the majority of test cases, the new interaction model resulted in an improved docking accuracy of the top ranking placements.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The accurate modeling of metal coordination geometries plays an important role for structure-based drug design applied to metalloenzymes. For the development of a new metal interaction model, we perform a statistical analysis of metal interaction geometries that are relevant to protein-ligand complexes. A total of 43,061 metal sites of the Protein Data Bank (PDB), containing amongst others magnesium, calcium, zinc, iron, manganese, copper, cadmium, cobalt, and nickel, were evaluated according to their metal coordination geometry. Based on statistical analysis, we derived a model for the automatic calculation and definition of metal interaction geometries for the purpose of molecular docking analyses. It includes the identification of the metal-coordinating ligands, the calculation of the coordination geometry and the superposition of ideal polyhedra to identify the optimal positions for free coordination sites. The new interaction model was integrated in the docking software FlexX and evaluated on a data set of 103 metalloprotein-ligand complexes, which were extracted from the PDB. In a first step, the quality of the automatic calculation of the metal coordination geometry was analyzed. In 74% of the cases, the correct prediction of the coordination geometry could be determined on the basis of the protein structure alone. Secondly, the new metal interaction model was tested in terms of predicting protein-ligand complexes. In the majority of test cases, the new interaction model resulted in an improved docking accuracy of the top ranking placements. |
Raub, Stephan; Steffen, Andreas; Kämper, Andreas; Marian, Christel M AIScore - Chemically diverse empirical scoring function employing quantum chemical binding energies of hydrogen-bonded complexes J. Chem. Inf. Model., 48 (7), pp. 1492-1510, 2008. @article{aiscore, title = {AIScore - Chemically diverse empirical scoring function employing quantum chemical binding energies of hydrogen-bonded complexes}, author = {Stephan Raub and Andreas Steffen and Andreas Kämper and Christel M Marian}, url = {http://dx.doi.org/10.1021/ci7004669}, year = {2008}, date = {2008-01-01}, journal = {J. Chem. Inf. Model.}, volume = {48}, number = {7}, pages = {1492-1510}, abstract = {In this work we report on a novel scoring function that is based on the LUDI model and focuses on the prediction of binding affinities. AIScore extends the original FlexX scoring function using a chemically diverse set of hydrogen-bonded interactions derived from extensive quantum chemical ab initio calculations. Furthermore, we introduce an algorithmic extension for the treatment of multifurcated hydrogen bonds (XFurcate). Charged and resonance-assisted hydrogen bond energies and hydrophobic interactions as well as a scaling factor for implicit solvation were fitted to experimental data. To this end, we assembled a set of 101 protein-ligand complexes with known experimental binding affinities. Tightly bound water molecules in the active site were considered to be an integral part of the binding pocket. Compared to the original FlexX scoring function, AIScore significantly improves the prediction of the binding free energies of the complexes in their native crystal structures. In combination with XFurcate, AIScore yields a Pearson correlation coefficient of R P = 0.87 on the training set. In a validation run on the PDBbind test set we achieved an R P value of 0.46 for 799 attractively scored complexes, compared to a value of R P = 0.17 and 739 bound complexes obtained with the FlexX original scoring function. The redocking capability of AIScore, on the other hand, does not fully reach the good performance of the original FlexX scoring function. This finding suggests that AIScore should rather be used for postscoring in combination with the standard FlexX incremental ligand construction scheme.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In this work we report on a novel scoring function that is based on the LUDI model and focuses on the prediction of binding affinities. AIScore extends the original FlexX scoring function using a chemically diverse set of hydrogen-bonded interactions derived from extensive quantum chemical ab initio calculations. Furthermore, we introduce an algorithmic extension for the treatment of multifurcated hydrogen bonds (XFurcate). Charged and resonance-assisted hydrogen bond energies and hydrophobic interactions as well as a scaling factor for implicit solvation were fitted to experimental data. To this end, we assembled a set of 101 protein-ligand complexes with known experimental binding affinities. Tightly bound water molecules in the active site were considered to be an integral part of the binding pocket. Compared to the original FlexX scoring function, AIScore significantly improves the prediction of the binding free energies of the complexes in their native crystal structures. In combination with XFurcate, AIScore yields a Pearson correlation coefficient of R P = 0.87 on the training set. In a validation run on the PDBbind test set we achieved an R P value of 0.46 for 799 attractively scored complexes, compared to a value of R P = 0.17 and 739 bound complexes obtained with the FlexX original scoring function. The redocking capability of AIScore, on the other hand, does not fully reach the good performance of the original FlexX scoring function. This finding suggests that AIScore should rather be used for postscoring in combination with the standard FlexX incremental ligand construction scheme. |
Hildebrandt, Andreas; Kohlbacher, Oliver; Lenhof, Hans-Peter Modeling Protein–Protein and Protein–DNA Docking Lengauer, Thomas (Ed.): Bioinformatics - From Genomes to Drugs, Chapter 17, pp. 601-650, Wiley-VCH, 2007. @inbook{DockingChapter, title = {Modeling Protein–Protein and Protein–DNA Docking}, author = {Andreas Hildebrandt and Oliver Kohlbacher and Hans-Peter Lenhof}, editor = {Thomas Lengauer}, url = {http://www.wiley-vch.de/publish/en/books/specialOffer/3-527-31278-1/?sID=}, year = {2007}, date = {2007-01-01}, booktitle = {Bioinformatics - From Genomes to Drugs}, pages = {601-650}, publisher = {Wiley-VCH}, chapter = {17}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
Hildebrandt, Andreas; Rjasanow, Sergej; Blossey, Ralf; Kohlbacher, Oliver; Lenhof, Hans-Peter Electrostatic potentials of proteins in water: a structured continuum approach Bioinformatics, 23 (2), pp. e99-e100, 2007. @article{NonlocalESECCB06, title = {Electrostatic potentials of proteins in water: a structured continuum approach}, author = {Andreas Hildebrandt and Sergej Rjasanow and Ralf Blossey and Oliver Kohlbacher and Hans-Peter Lenhof}, doi = {https://doi.org/10.1093/bioinformatics/btl312}, year = {2007}, date = {2007-01-01}, journal = {Bioinformatics}, volume = {23}, number = {2}, pages = {e99-e100}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Kohlbacher, Oliver; Reinert, Knut; Gröpl, Clemens; Lange, Eva; Pfeifer, Nico; Schulz-Trieglaff, Ole; Sturm, Marc TOPP - The OpenMS Proteomics Pipeline Bioinformatics, 23 (2), pp. e191-e197, 2007. @article{TOPP, title = {TOPP - The OpenMS Proteomics Pipeline}, author = {Oliver Kohlbacher and Knut Reinert and Clemens Gröpl and Eva Lange and Nico Pfeifer and Ole Schulz-Trieglaff and Marc Sturm}, url = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/2/e191}, year = {2007}, date = {2007-01-01}, journal = {Bioinformatics}, volume = {23}, number = {2}, pages = {e191-e197}, abstract = {Motivation: Experimental techniques in proteomics have seen rapid development over the last few years. Volume and complexity of the data have both been growing at a similar rate. Accordingly, data management and analysis are one of the major challenges in proteomics. Flexible algorithms are required to handle changing experimental setups and to assist in developing and validating new methods. In order to facilitate these studies, it would be desirable to have a flexible ‘toolbox’ of versatile and user-friendly applications allowing for rapid construction of computational workflows in proteomics. Results: We describe a set of tools for proteomics data analysis—TOPP, The OpenMS Proteomics Pipeline. TOPP provides a set of computational tools which can be easily combined into analysis pipelines even by non-experts and can be used in proteomics workflows. These applications range from useful utilities (file format conversion, peak picking) over wrapper applications for known applications (e.g. Mascot) to completely new algorithmic techniques for data reduction and data analysis. We anticipate that TOPP will greatly facilitate rapid prototyping of proteomics data evaluation pipelines. As such, we describe the basic concepts and the current abilities of TOPP and illustrate these concepts in the context of two example applications: the identification of peptides from a raw dataset through database search and the complex analysis of a standard addition experiment for the absolute quantitation of biomarkers. The latter example demonstrates TOPP's ability to construct flexible analysis pipelines in support of complex experimental setups. Availability: The TOPP components are available as open-source software under the lesser GNU public license (LGPL). Source code is available from the project website at www.OpenMS.de}, keywords = {}, pubstate = {published}, tppubtype = {article} } Motivation: Experimental techniques in proteomics have seen rapid development over the last few years. Volume and complexity of the data have both been growing at a similar rate. Accordingly, data management and analysis are one of the major challenges in proteomics. Flexible algorithms are required to handle changing experimental setups and to assist in developing and validating new methods. In order to facilitate these studies, it would be desirable to have a flexible ‘toolbox’ of versatile and user-friendly applications allowing for rapid construction of computational workflows in proteomics. Results: We describe a set of tools for proteomics data analysis—TOPP, The OpenMS Proteomics Pipeline. TOPP provides a set of computational tools which can be easily combined into analysis pipelines even by non-experts and can be used in proteomics workflows. These applications range from useful utilities (file format conversion, peak picking) over wrapper applications for known applications (e.g. Mascot) to completely new algorithmic techniques for data reduction and data analysis. We anticipate that TOPP will greatly facilitate rapid prototyping of proteomics data evaluation pipelines. As such, we describe the basic concepts and the current abilities of TOPP and illustrate these concepts in the context of two example applications: the identification of peptides from a raw dataset through database search and the complex analysis of a standard addition experiment for the absolute quantitation of biomarkers. The latter example demonstrates TOPP's ability to construct flexible analysis pipelines in support of complex experimental setups. Availability: The TOPP components are available as open-source software under the lesser GNU public license (LGPL). Source code is available from the project website at www.OpenMS.de |
Shatkay, Hagit; Höglund, Annette; Brady, Scott; Blum, Torsten; Dönnes, Pierre; Kohlbacher, Oliver SherLoc : High-Accuracy Prediction of Protein Subcellular Localization by Integrating Text and Protein Sequence Data. Bioinformatics, 23 (11), pp. 1410-1417, 2007. @article{SherLoc, title = {SherLoc : High-Accuracy Prediction of Protein Subcellular Localization by Integrating Text and Protein Sequence Data.}, author = {Hagit Shatkay and Annette Höglund and Scott Brady and Torsten Blum and Pierre Dönnes and Oliver Kohlbacher}, url = {http://bioinformatics.oxfordjournals.org/cgi/content/short/23/11/1410}, year = {2007}, date = {2007-01-01}, journal = {Bioinformatics}, volume = {23}, number = {11}, pages = {1410-1417}, abstract = {MOTIVATION: Knowing the localization of a protein within the cell helps elucidate its role in biological processes, its function and its potential as a drug target. Thus, subcellular localization prediction is an active research area. Numerous localization prediction systems are described in the literature; some focus on specific localizations or organisms, while others attempt to cover a wide range of localizations. RESULTS: We introduce SherLoc, a new comprehensive system for predicting the localization of eukaryotic proteins. It integrates several types of sequence and text-based features. While applying the widely used support vector machines (SVMs), SherLoc's main novelty lies in the way in which it selects its text sources and features, and integrates those with sequence-based features. We test SherLoc on previously used datasets, as well as on a new set devised specifically to test its predictive power, and show that SherLoc consistently improves on previous reported results. We also report the results of applying SherLoc to a large set of yet-unlocalized proteins. AVAILABILITY: SherLoc, along with Supplementary Information, is available at: http://www-bs.informatik.uni-tuebingen.de/Services/SherLoc}, keywords = {}, pubstate = {published}, tppubtype = {article} } MOTIVATION: Knowing the localization of a protein within the cell helps elucidate its role in biological processes, its function and its potential as a drug target. Thus, subcellular localization prediction is an active research area. Numerous localization prediction systems are described in the literature; some focus on specific localizations or organisms, while others attempt to cover a wide range of localizations. RESULTS: We introduce SherLoc, a new comprehensive system for predicting the localization of eukaryotic proteins. It integrates several types of sequence and text-based features. While applying the widely used support vector machines (SVMs), SherLoc's main novelty lies in the way in which it selects its text sources and features, and integrates those with sequence-based features. We test SherLoc on previously used datasets, as well as on a new set devised specifically to test its predictive power, and show that SherLoc consistently improves on previous reported results. We also report the results of applying SherLoc to a large set of yet-unlocalized proteins. AVAILABILITY: SherLoc, along with Supplementary Information, is available at: http://www-bs.informatik.uni-tuebingen.de/Services/SherLoc |
Sturm, Marc; Quinten, Sascha; Huber, Christian G; Kohlbacher, Oliver A statistical learning approach to the modeling of chromatographic retention of oligonucleotides incorporating sequence and secondary structure data Nucl. Acids Res., 35 (12), pp. 4195-4202, 2007. @article{NAROligoRTPred, title = {A statistical learning approach to the modeling of chromatographic retention of oligonucleotides incorporating sequence and secondary structure data}, author = {Marc Sturm and Sascha Quinten and Christian G Huber and Oliver Kohlbacher}, url = {http://nar.oxfordjournals.org/cgi/content/short/35/12/4195}, year = {2007}, date = {2007-01-01}, journal = {Nucl. Acids Res.}, volume = {35}, number = {12}, pages = {4195-4202}, abstract = {We propose a new model for predicting the retention time of oligonucleotides. The model is based on ν support vector regression using features derived from base sequence and predicted secondary structure of oligonucleotides. Because of the secondary structure information, the model is applicable even at relatively low temperatures where the secondary structure is not suppressed by thermal denaturing. This makes the prediction of oligonucleotide retention time for arbitrary temperatures possible, provided that the target temperature lies within the temperature range of the training data. We describe different possibilities of feature calculation from base sequence and secondary structure, present the results and compare our model to existing models.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We propose a new model for predicting the retention time of oligonucleotides. The model is based on ν support vector regression using features derived from base sequence and predicted secondary structure of oligonucleotides. Because of the secondary structure information, the model is applicable even at relatively low temperatures where the secondary structure is not suppressed by thermal denaturing. This makes the prediction of oligonucleotide retention time for arbitrary temperatures possible, provided that the target temperature lies within the temperature range of the training data. We describe different possibilities of feature calculation from base sequence and secondary structure, present the results and compare our model to existing models. |
Küntzer, Jan; Backes, Christina; Blum, Torsten; Gerasch, Andreas; Kaufmann, Michael; Kohlbacher, Oliver; Lenhof, Hans-Peter BNDB - The Biochemical Network Database BMC Bioinformatics, 8 , pp. 367, 2007. @article{BNDB, title = {BNDB - The Biochemical Network Database}, author = {Jan Küntzer and Christina Backes and Torsten Blum and Andreas Gerasch and Michael Kaufmann and Oliver Kohlbacher and Hans-Peter Lenhof}, url = {http://www.biomedcentral.com/1471-2105/8/367/abstract}, year = {2007}, date = {2007-01-01}, journal = {BMC Bioinformatics}, volume = {8}, pages = {367}, abstract = {Background Technological advances in high-throughput techniques and efficient data acquisition methods have resulted in a massive amount of life science data. The data is stored in numerous databases that have been established over the last decades and are essential resources for scientists nowadays. However, the diversity of the databases and the underlying data models make it difficult to combine this information for solving complex problems in systems biology. Currently, researchers typically have to browse several, often highly focused, databases to obtain the required information. Hence, there is a pressing need for more efficient systems for integrating, analyzing, and interpreting these data. The standardization and virtual consolidation of the databases is a major challenge resulting in a unified access to a variety of data sources. Results We present the Biochemical Network Database (BNDB), a powerful relational database platform, allowing a complete semantic integration of an extensive collection of external databases. BNDB is built upon a comprehensive and extensible object model called BioCore, which is powerful enough to model most known biochemical processes and at the same time easily extensible to be adapted to new biological concepts. Besides a webinterface for the search and curation of the data, a Java-based viewer (BiNA) provides a powerful platform-independent visualization and navigation of the data. BiNA uses sophisticated graph layout algorithms for an interactive visualization and navigation of BNDB. Conclusions BNDB allows a simple, unified access to a variety of external data sources. Its tight integration with the biochemical network library BN++ offers the possibility for import, integration, analysis, and visualization of the data. BNDB is freely accessible at http://www.bndb.org.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background Technological advances in high-throughput techniques and efficient data acquisition methods have resulted in a massive amount of life science data. The data is stored in numerous databases that have been established over the last decades and are essential resources for scientists nowadays. However, the diversity of the databases and the underlying data models make it difficult to combine this information for solving complex problems in systems biology. Currently, researchers typically have to browse several, often highly focused, databases to obtain the required information. Hence, there is a pressing need for more efficient systems for integrating, analyzing, and interpreting these data. The standardization and virtual consolidation of the databases is a major challenge resulting in a unified access to a variety of data sources. Results We present the Biochemical Network Database (BNDB), a powerful relational database platform, allowing a complete semantic integration of an extensive collection of external databases. BNDB is built upon a comprehensive and extensible object model called BioCore, which is powerful enough to model most known biochemical processes and at the same time easily extensible to be adapted to new biological concepts. Besides a webinterface for the search and curation of the data, a Java-based viewer (BiNA) provides a powerful platform-independent visualization and navigation of the data. BiNA uses sophisticated graph layout algorithms for an interactive visualization and navigation of BNDB. Conclusions BNDB allows a simple, unified access to a variety of external data sources. Its tight integration with the biochemical network library BN++ offers the possibility for import, integration, analysis, and visualization of the data. BNDB is freely accessible at http://www.bndb.org. |
Pfeifer, Nico; Leinenbach, Andreas; Huber, Christian G; Kohlbacher, Oliver Statistical learning of peptide retention behavior in chromatographic separations: A new kernel-based approach for computational proteomics BMC Bioinformatics, 8 , pp. 468, 2007. @article{ReentrantCondPRL, title = {Statistical learning of peptide retention behavior in chromatographic separations: A new kernel-based approach for computational proteomics}, author = {Nico Pfeifer and Andreas Leinenbach and Christian G Huber and Oliver Kohlbacher}, url = {http://www.biomedcentral.com/1471-2105/8/468/abstract}, year = {2007}, date = {2007-01-01}, journal = {BMC Bioinformatics}, volume = {8}, pages = {468}, abstract = {Background High-throughput peptide and protein identification technologies have benefited tremendously from strategies based on tandem mass spectrometry (MS/MS) in combination with database searching algorithms. A major problem with existing methods lies within the significant number of false positive and false negative annotations. So far, standard algorithms for protein identification do not use the information gained from separation processes usually involved in peptide analysis, such as retention time information, which are readily available from chromatographic separation of the sample. Identification can thus be improved by comparing measured retention times to predicted retention times. Current prediction models are derived from a set of measured test analytes but they usually require large amounts of training data. Results We introduce a new kernel function which can be applied in combination with support vector machines to a wide range of computational proteomics problems. We show the performance of this new approach by applying it to the prediction of peptide adsorption/elution behavior in strong anion-exchange solid-phase extraction (SAX-SPE) and ion-pair reversed-phase high-performance liquid chromatography (IP-RP-HPLC). Furthermore, the predicted retention times are used to improve spectrum identifications by a p-value-based filtering approach. The approach was tested on a number of different datasets and shows excellent performance while requiring only very small training sets (about 40 peptides instead of thousands). Using the retention time predictor in our retention time filter improves the fraction of correctly identified peptide mass spectra significantly. Conclusion The proposed kernel function is well-suited for the prediction of chromatographic separation in computational proteomics and requires only a limited amount of training data. The performance of this new method is demonstrated by applying it to peptide retention time prediction in IP-RP-HPLC and prediction of peptide sample fractionation in SAX-SPE. Finally, we incorporate the predicted chromatographic behavior in a p-value based filter to improve peptide identifications based on liquid chromatography-tandem mass spectrometry.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background High-throughput peptide and protein identification technologies have benefited tremendously from strategies based on tandem mass spectrometry (MS/MS) in combination with database searching algorithms. A major problem with existing methods lies within the significant number of false positive and false negative annotations. So far, standard algorithms for protein identification do not use the information gained from separation processes usually involved in peptide analysis, such as retention time information, which are readily available from chromatographic separation of the sample. Identification can thus be improved by comparing measured retention times to predicted retention times. Current prediction models are derived from a set of measured test analytes but they usually require large amounts of training data. Results We introduce a new kernel function which can be applied in combination with support vector machines to a wide range of computational proteomics problems. We show the performance of this new approach by applying it to the prediction of peptide adsorption/elution behavior in strong anion-exchange solid-phase extraction (SAX-SPE) and ion-pair reversed-phase high-performance liquid chromatography (IP-RP-HPLC). Furthermore, the predicted retention times are used to improve spectrum identifications by a p-value-based filtering approach. The approach was tested on a number of different datasets and shows excellent performance while requiring only very small training sets (about 40 peptides instead of thousands). Using the retention time predictor in our retention time filter improves the fraction of correctly identified peptide mass spectra significantly. Conclusion The proposed kernel function is well-suited for the prediction of chromatographic separation in computational proteomics and requires only a limited amount of training data. The performance of this new method is demonstrated by applying it to peptide retention time prediction in IP-RP-HPLC and prediction of peptide sample fractionation in SAX-SPE. Finally, we incorporate the predicted chromatographic behavior in a p-value based filter to improve peptide identifications based on liquid chromatography-tandem mass spectrometry. |
Blum, Torsten; Kohlbacher, Oliver Finding relevant biotransformation routes in weighted metabolic networks using atom mapping rules Proceedings of the German Conference on Bioinformatics (GCB 2007), 2007. (BibTeX) @inproceedings{InproceedingsReference.2007-08-08.8627613444, title = {Finding relevant biotransformation routes in weighted metabolic networks using atom mapping rules}, author = {Torsten Blum and Oliver Kohlbacher}, year = {2007}, date = {2007-01-01}, publisher = {Proceedings of the German Conference on Bioinformatics (GCB 2007)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Mitschke, Jan; Fuss, Janina; Blum, Torsten; Höglund, Annette; Reski, Ralf; Kohlbacher, Oliver; Rensing, Stefan Prediction of dual protein targeting to plant organelles Proceedings of the German Conference on Bioinformatics (GCB 2007), 2007. (BibTeX) @inproceedings{copy_of_ATP, title = {Prediction of dual protein targeting to plant organelles}, author = {Jan Mitschke and Janina Fuss and Torsten Blum and Annette Höglund and Ralf Reski and Oliver Kohlbacher and Stefan Rensing}, year = {2007}, date = {2007-01-01}, publisher = {Proceedings of the German Conference on Bioinformatics (GCB 2007)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Steffen, Andreas; Thiele, Carolin; Tietze, Simon; Strassnig, Christian; Kämper, Andreas; Lengauer, Thomas; Wenz, Gerhard; Apostolakis, Joannis Improved cyclodextrin-based receptors for camptothecin by inverse virtual screening Chem. Eur. J., 13 (24), pp. 6801-6809, 2007. @article{camptothecin, title = {Improved cyclodextrin-based receptors for camptothecin by inverse virtual screening}, author = {Andreas Steffen and Carolin Thiele and Simon Tietze and Christian Strassnig and Andreas Kämper and Thomas Lengauer and Gerhard Wenz and Joannis Apostolakis}, url = {http://dx.doi.org/10.1002/chem.200700661}, year = {2007}, date = {2007-01-01}, journal = {Chem. Eur. J.}, volume = {13}, number = {24}, pages = {6801-6809}, abstract = {We report the computer-aided optimization of a synthetic receptor for a given guest molecule, based on inverse virtual screening of receptor libraries. As an example, a virtual set of beta-cyclodextrin (beta-CD) derivatives was generated as receptor candidates for the anticancer drug camptothecin. We applied the two docking tools AutoDock and GlamDock to generate camptothecin complexes of every candidate receptor. Scoring functions were used to rank all generated complexes. From the 10 % top-ranking candidates nine were selected for experimental validation. They were synthesized by reaction of heptakis-[6-deoxy-6-iodo]-beta-CD with a thiol compound to form the hepta-substituted beta-CDs. The stabilities of the camptothecin complexes obtained from solubility measurements of five of the nine CD derivatives were significantly higher than for any other CD derivative known from literature. The remaining four CD derivatives were insoluble in water. In addition, corresponding mono-substituted CD derivatives were synthesized that also showed improved binding constants. Among them the 9-H-purine derivative was the best, being comparable to the investigated hepta-substituted beta-CDs. Since the measured binding free energies correlated satisfactorily with the calculated scores, the applied scoring functions appeared to be appropriate for the selection of promising candidates for receptor synthesis.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We report the computer-aided optimization of a synthetic receptor for a given guest molecule, based on inverse virtual screening of receptor libraries. As an example, a virtual set of beta-cyclodextrin (beta-CD) derivatives was generated as receptor candidates for the anticancer drug camptothecin. We applied the two docking tools AutoDock and GlamDock to generate camptothecin complexes of every candidate receptor. Scoring functions were used to rank all generated complexes. From the 10 % top-ranking candidates nine were selected for experimental validation. They were synthesized by reaction of heptakis-[6-deoxy-6-iodo]-beta-CD with a thiol compound to form the hepta-substituted beta-CDs. The stabilities of the camptothecin complexes obtained from solubility measurements of five of the nine CD derivatives were significantly higher than for any other CD derivative known from literature. The remaining four CD derivatives were insoluble in water. In addition, corresponding mono-substituted CD derivatives were synthesized that also showed improved binding constants. Among them the 9-H-purine derivative was the best, being comparable to the investigated hepta-substituted beta-CDs. Since the measured binding free energies correlated satisfactorily with the calculated scores, the applied scoring functions appeared to be appropriate for the selection of promising candidates for receptor synthesis. |
Steffen, Andreas; Karasz, Maximilian; Thiele, Carolin; Lengauer, Thomas; Kämper, Andreas; Wenz, Gerhard; Apostolakis, Joannis Combined similarity and QSPR virtual screening for guest molecules of beta-cyclodextrin New J. Chem., 31 (11), pp. 1941-1949, 2007. @article{cdguests, title = {Combined similarity and QSPR virtual screening for guest molecules of beta-cyclodextrin}, author = {Andreas Steffen and Maximilian Karasz and Carolin Thiele and Thomas Lengauer and Andreas Kämper and Gerhard Wenz and Joannis Apostolakis}, url = {http://dx.doi.org/10.1039/b707856k}, year = {2007}, date = {2007-01-01}, journal = {New J. Chem.}, volume = {31}, number = {11}, pages = {1941-1949}, abstract = {We describe a similarity-based screening approach combined with a quantitative prediction of affinity based on physicochemical descriptors, for the efficient identification of new, high affinity guest molecules of beta-cyclodextrin (beta-CD). Four known beta-CD guest molecules were chosen as query molecules. A subset of the ZINC database with 117 695 molecular entries served as the screening library. For each query the 150 most similar molecules were identified by virtual screening against this library with a graph-based similarity algorithm. Subsequently these molecules were scored by means of a QSPR model. The best-scoring, commercially available molecules were selected for experimental verification (14 in total). Binding free energies were determined by isothermal microcalorimetry (ITC). For three of the four queries, at least one ligand with a higher binding affinity than the corresponding query was found. The approach is a promising high throughput alternative to structure-based virtual screening. While beta-CD was chosen as a test case because of its technical relevance and the availability of many binding data, the applied methodology is transferable to other host–guest systems.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We describe a similarity-based screening approach combined with a quantitative prediction of affinity based on physicochemical descriptors, for the efficient identification of new, high affinity guest molecules of beta-cyclodextrin (beta-CD). Four known beta-CD guest molecules were chosen as query molecules. A subset of the ZINC database with 117 695 molecular entries served as the screening library. For each query the 150 most similar molecules were identified by virtual screening against this library with a graph-based similarity algorithm. Subsequently these molecules were scored by means of a QSPR model. The best-scoring, commercially available molecules were selected for experimental verification (14 in total). Binding free energies were determined by isothermal microcalorimetry (ITC). For three of the four queries, at least one ligand with a higher binding affinity than the corresponding query was found. The approach is a promising high throughput alternative to structure-based virtual screening. While beta-CD was chosen as a test case because of its technical relevance and the availability of many binding data, the applied methodology is transferable to other host–guest systems. |
Neumann, Dirk; Kohlbacher, Oliver; Merkwirth, Christian; Lengauer, Thomas A fully computational model for predicting percutaneous drug absorption J. Chem. Inf. Model., 46 (1), pp. 424–429, 2006. @article{PercutaneousAbs, title = {A fully computational model for predicting percutaneous drug absorption}, author = {Dirk Neumann and Oliver Kohlbacher and Christian Merkwirth and Thomas Lengauer}, url = {http://pubs.acs.org/cgi-bin/sample.cgi/jcisd8/2006/46/i01/abs/ci050332t.html}, year = {2006}, date = {2006-01-01}, journal = {J. Chem. Inf. Model.}, volume = {46}, number = {1}, pages = {424--429}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Moll, Andreas; Hildebrandt, Andreas; Lenhof, Hans-Peter; Kohlbacher, Oliver BALLView: A tool for research and education in molecular modeling Bioinformatics, 22 (3), pp. 365–366, 2006. @article{BALLView, title = {BALLView: A tool for research and education in molecular modeling}, author = {Andreas Moll and Andreas Hildebrandt and Hans-Peter Lenhof and Oliver Kohlbacher}, url = {http://bioinformatics.oxfordjournals.org/cgi/reprint/bti818v1}, year = {2006}, date = {2006-01-01}, journal = {Bioinformatics}, volume = {22}, number = {3}, pages = {365--366}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Baldes, Christiane; König, Petra; Neumann, Dirk; Lenhof, Hans-Peter; Kohlbacher, Oliver; Lehr, Claus-Michael Development of a fluorescence-based assay for screening of modulators of human Organic Anion Transporter 1B3 (OATP1B3) Eur J Pharm Biopharm., 62 (1), pp. 39–43, 2006. @article{OATP13, title = {Development of a fluorescence-based assay for screening of modulators of human Organic Anion Transporter 1B3 (OATP1B3)}, author = {Christiane Baldes and Petra König and Dirk Neumann and Hans-Peter Lenhof and Oliver Kohlbacher and Claus-Michael Lehr}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=16129589&query_hl=1}, year = {2006}, date = {2006-01-01}, journal = {Eur J Pharm Biopharm.}, volume = {62}, number = {1}, pages = {39--43}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Lange, Eva; Gröpl, Clemens; Reinert, Knut; Kohlbacher, Oliver; Hildebrandt, Andreas High-Accuracy Peak Picking of Proteomics Data using Wavelet Techniques Proceedings of the Pacific Symposium on Biocomputing (PSB 2006), 2006. @inproceedings{PSB2006_Peaks, title = {High-Accuracy Peak Picking of Proteomics Data using Wavelet Techniques}, author = {Eva Lange and Clemens Gröpl and Knut Reinert and Oliver Kohlbacher and Andreas Hildebrandt}, url = {http://helix-web.stanford.edu/psb06/lange.pdf}, year = {2006}, date = {2006-01-01}, booktitle = {Proceedings of the Pacific Symposium on Biocomputing (PSB 2006)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Mayr, Bettina; Kohlbacher, Oliver; Reinert, Knut; Sturm, Marc; Gröpl, Clemens; Lange, Eva; Klein, Christoph; Huber, Christian G Absolute Myoglobin Quantitation in Serum by Combining Two-Dimensional Liquid Chromatography-Electrospray Ionization Mass Spectrometry and Novel Data Analysis Algorithms J. Proteome Res., 5 , pp. 414–421, 2006. @article{MyoExptl, title = {Absolute Myoglobin Quantitation in Serum by Combining Two-Dimensional Liquid Chromatography-Electrospray Ionization Mass Spectrometry and Novel Data Analysis Algorithms}, author = {Bettina Mayr and Oliver Kohlbacher and Knut Reinert and Marc Sturm and Clemens Gröpl and Eva Lange and Christoph Klein and Christian G Huber}, url = {http://dx.doi.org/10.1021/pr050344u}, year = {2006}, date = {2006-01-01}, journal = {J. Proteome Res.}, volume = {5}, pages = {414--421}, abstract = {To measure myoglobin, a marker for myocardial infarction, directly in human serum, two-dimensional liquid chromatography in combination with electrospray ionization mass spectrometry was applied as an analytical method. High-abundant serum proteins were depleted by strong anion-exchange chromatography. The myoglobin fraction was digested and injected onto a 60 mm × 0.2 mm i.d. monolithic capillary column for quantitation of selected peptides upon mass spectrometric detection. The addition of known amounts of myoglobin to the serum sample was utilized for calibration, and horse myoglobin was added as an internal standard to improve reproducibility. Calibration graphs were linear and facilitated the reproducible and accurate determination of the myoglobin amount present in serum. Manual data evaluation using integrated peak areas and an automated multistage algorithm fitting two-dimensional models of peptide elution profiles and isotope patterns to the mass spectrometric raw data were compared. When the automated method was applied, a myoglobin concentration of 460 pg/μL serum was determined with a maximum relative deviation from the theoretical value of 10.1% and a maximum relative standard deviation of 13.4%.}, keywords = {}, pubstate = {published}, tppubtype = {article} } To measure myoglobin, a marker for myocardial infarction, directly in human serum, two-dimensional liquid chromatography in combination with electrospray ionization mass spectrometry was applied as an analytical method. High-abundant serum proteins were depleted by strong anion-exchange chromatography. The myoglobin fraction was digested and injected onto a 60 mm × 0.2 mm i.d. monolithic capillary column for quantitation of selected peptides upon mass spectrometric detection. The addition of known amounts of myoglobin to the serum sample was utilized for calibration, and horse myoglobin was added as an internal standard to improve reproducibility. Calibration graphs were linear and facilitated the reproducible and accurate determination of the myoglobin amount present in serum. Manual data evaluation using integrated peak areas and an automated multistage algorithm fitting two-dimensional models of peptide elution profiles and isotope patterns to the mass spectrometric raw data were compared. When the automated method was applied, a myoglobin concentration of 460 pg/μL serum was determined with a maximum relative deviation from the theoretical value of 10.1% and a maximum relative standard deviation of 13.4%. |
Moll, Andreas; Hildebrandt, Andreas; Lenhof, Hans-Peter; Kohlbacher, Oliver BALLView: An object-oriented molecular visualization and modeling framework J. Comput.-Aided Mol. Des., 19 (11), pp. 791, 2006. @article{BV.JCAMD, title = {BALLView: An object-oriented molecular visualization and modeling framework}, author = {Andreas Moll and Andreas Hildebrandt and Hans-Peter Lenhof and Oliver Kohlbacher}, url = {http://dx.doi.org/10.1007/s10822-005-9027-x}, year = {2006}, date = {2006-01-01}, journal = {J. Comput.-Aided Mol. Des.}, volume = {19}, number = {11}, pages = {791}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Sturm, Marc; Quinten, Sascha; Huber, Christian G; Kohlbacher, Oliver A machine learning approach for prediction of DNA and peptide retention times Huber, Christian; Kohlbacher, Oliver; Reinert, Knut (Ed.): Proceedings of the Dagstuhl Seminar on Computational Proteomics 2005, Internationales Begegnungs- und Forschungszentrum (IBFI), Schloss Dagstuhl, Germany, 2006. @inproceedings{DNA-RT-Dagstuhl-2006, title = {A machine learning approach for prediction of DNA and peptide retention times}, author = {Marc Sturm and Sascha Quinten and Christian G Huber and Oliver Kohlbacher}, editor = {Christian Huber and Oliver Kohlbacher and Knut Reinert}, url = {http://drops.dagstuhl.de/opus/volltexte/2006/548}, year = {2006}, date = {2006-01-01}, booktitle = {Proceedings of the Dagstuhl Seminar on Computational Proteomics 2005}, publisher = {Internationales Begegnungs- und Forschungszentrum (IBFI), Schloss Dagstuhl, Germany}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Kerzmann, Andreas; Neumann, Dirk; Kohlbacher, Oliver SLICK - Scoring and Energy Functions for Protein-Carbohydrate Interactions J. Chem. Inf. Model., 46 , pp. 1635-1642, 2006. @article{SLICK, title = {SLICK - Scoring and Energy Functions for Protein-Carbohydrate Interactions}, author = {Andreas Kerzmann and Dirk Neumann and Oliver Kohlbacher}, url = {http://dx.doi.org/10.1021/ci050422y}, year = {2006}, date = {2006-01-01}, journal = {J. Chem. Inf. Model.}, volume = {46}, pages = {1635-1642}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Küntzer, Jan; Blum, Torsten; Gerasch, Andreas; Backes, Christina; Hildebrandt, Andreas; Kaufmann, Michael; Kohlbacher, Oliver; Lenhof, Hans-Peter BN++ - A Biological Information System Proceedings of the 3rd International Workshop Integrative Bioinformatics, Rothamsted Research, 2006. @inproceedings{InproceedingsReference.2006-07-28.1716726743, title = {BN++ - A Biological Information System}, author = {Jan Küntzer and Torsten Blum and Andreas Gerasch and Christina Backes and Andreas Hildebrandt and Michael Kaufmann and Oliver Kohlbacher and Hans-Peter Lenhof}, url = {http://www.rothamsted.bbsrc.ac.uk/bab/conf/ibiof/abslister.php}, year = {2006}, date = {2006-01-01}, booktitle = {Proceedings of the 3rd International Workshop Integrative Bioinformatics}, publisher = {Rothamsted Research}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Huson, Daniel H; Kohlbacher, Oliver; Lupas, Andrei; Nieselt, Kay; Zell, Andreas German Conference on Bioinformatics Gesellschaft für Informatik e.V., Bonner Köllen Verlag, 2006. @book{BookReference.2006-09-27.8017853040, title = {German Conference on Bioinformatics}, author = {Daniel H Huson and Oliver Kohlbacher and Andrei Lupas and Kay Nieselt and Andreas Zell}, url = {http://www.gi-ev.de/service/publikationen/lni/gi-edition-lecture-notes-in-informatics-lni-p-83/}, year = {2006}, date = {2006-01-01}, volume = {P-83}, publisher = {Gesellschaft für Informatik e.V.}, address = {Bonner Köllen Verlag}, keywords = {}, pubstate = {published}, tppubtype = {book} } |
Kohlbacher, Oliver; Quinten, Sascha; Sturm, Marc; Mayr, Bettina; Huber, Christian Structure-Activity Relationships in Chromatography: Retention Prediction of Oligonucleotides with Support Vector Regression Angew. Chemie Int. Ed., 45 (42), pp. 7009-7012, 2006. @article{AngewOligos, title = {Structure-Activity Relationships in Chromatography: Retention Prediction of Oligonucleotides with Support Vector Regression}, author = {Oliver Kohlbacher and Sascha Quinten and Marc Sturm and Bettina Mayr and Christian Huber}, url = {http://dx.doi.org/10.1002/anie.200602561}, year = {2006}, date = {2006-01-01}, journal = {Angew. Chemie Int. Ed.}, volume = {45}, number = {42}, pages = {7009-7012}, abstract = {Secondary structures of biopolymers have a significant influence on their molecular interactions with surfaces. With the aid of machine learning through support vector regression, the retention of oligonucleotides was modeled in ion-pair reversed-phase chromatography with high prediction accuracy (see diagram).}, keywords = {}, pubstate = {published}, tppubtype = {article} } Secondary structures of biopolymers have a significant influence on their molecular interactions with surfaces. With the aid of machine learning through support vector regression, the retention of oligonucleotides was modeled in ion-pair reversed-phase chromatography with high prediction accuracy (see diagram). |
Peifer, Christian; Krasowski, Agata; Hämmerle, Nina; Kohlbacher, Oliver; Dannhardt, Gerd; Totzke, Frank; Schächtele, Christoph; Laufer, Stefan Profile and Molecular Modeling of 3-(Indole-3-yl)-4-(3,4,5-trimethoxyphenyl)-1 H-pyrrole-2,5-dione (1) as a Highly Selective VEGF-R2/3 Inhibitor J. Med. Chem., 49 (25), pp. 7549-7553, 2006. @article{VEGFR-2, title = {Profile and Molecular Modeling of 3-(Indole-3-yl)-4-(3,4,5-trimethoxyphenyl)-1 H-pyrrole-2,5-dione (1) as a Highly Selective VEGF-R2/3 Inhibitor}, author = {Christian Peifer and Agata Krasowski and Nina Hämmerle and Oliver Kohlbacher and Gerd Dannhardt and Frank Totzke and Christoph Schächtele and Stefan Laufer}, url = {http://dx.doi.org/10.1021/jm0609871}, year = {2006}, date = {2006-01-01}, journal = {J. Med. Chem.}, volume = {49}, number = {25}, pages = {7549-7553}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Höglund, Annette; Blum, Torsten; Brady, Scott; Dönnes, Pierre; Miguel, John San; Rocheford, Matthew; Kohlbacher, Oliver; Shatkay, Hagit Significantly improved prediction of subcellular localization by integrating text and protein sequence data Proceedings of the Pacific Symposium on Biocomputing (PSB 2006), PSB, 2006. @inproceedings{psb2006_TextLoc, title = {Significantly improved prediction of subcellular localization by integrating text and protein sequence data}, author = {Annette Höglund and Torsten Blum and Scott Brady and Pierre Dönnes and John San Miguel and Matthew Rocheford and Oliver Kohlbacher and Hagit Shatkay}, url = {http://helix-web.stanford.edu/psb06/hoglund.pdf}, year = {2006}, date = {2006-01-01}, booktitle = {Proceedings of the Pacific Symposium on Biocomputing (PSB 2006)}, publisher = {PSB}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Höglund, Annette; Dönnes, Pierre; Blum, Torsten; Adolph, Hans-Werner; Kohlbacher, Oliver MultiLoc: prediction of protein subcellular localization using N-terminal targeting sequences, sequence motifs, and amino acid composition Bioinformatics, 22 (10), pp. 1158-65, 2006. @article{MultiLocGCB, title = {MultiLoc: prediction of protein subcellular localization using N-terminal targeting sequences, sequence motifs, and amino acid composition}, author = {Annette Höglund and Pierre Dönnes and Torsten Blum and Hans-Werner Adolph and Oliver Kohlbacher}, url = {http://bioinformatics.oxfordjournals.org/cgi/reprint/btl002v1}, year = {2006}, date = {2006-01-01}, journal = {Bioinformatics}, volume = {22}, number = {10}, pages = {1158-65}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Dönnes, Pierre; Kohlbacher, Oliver SVMHC: a server for prediction of MHC-binding peptides Nucleic Acids Res., 34 , pp. W194-W197, 2006. @article{SVMHC_NAR, title = {SVMHC: a server for prediction of MHC-binding peptides}, author = {Pierre Dönnes and Oliver Kohlbacher}, url = {http://nar.oxfordjournals.org/cgi/content/full/34/suppl_2/W194}, year = {2006}, date = {2006-01-01}, journal = {Nucleic Acids Res.}, volume = {34}, pages = {W194-W197}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Reinert, Knut; Kohlbacher, Oliver; Gröpl, Clemens; Lange, Eva; Schulz-Trieglaff, Ole; Sturm, Marc; Pfeifer, Nico OpenMS - A Framework for Quantitative HPLC/MS-Based Proteomics Huber, Christian G; Kohlbacher, Oliver; Reinert, Knut (Ed.): Computational Proteomics, Internationales Begegnungs- und Forschungszentrum fuer Informatik (IBFI), Schloss Dagstuhl, Germany, 2006. @inproceedings{OpenMSDagstuhl, title = {OpenMS - A Framework for Quantitative HPLC/MS-Based Proteomics}, author = {Knut Reinert and Oliver Kohlbacher and Clemens Gröpl and Eva Lange and Ole Schulz-Trieglaff and Marc Sturm and Nico Pfeifer}, editor = {Christian G Huber and Oliver Kohlbacher and Knut Reinert}, url = {http://drops.dagstuhl.de/opus/volltexte/2006/546}, year = {2006}, date = {2006-01-01}, booktitle = {Computational Proteomics}, publisher = {Internationales Begegnungs- und Forschungszentrum fuer Informatik (IBFI), Schloss Dagstuhl, Germany}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Gröpl, Clemens; Lange, Eva; Reinert, Knut; Kohlbacher, Oliver; Sturm, Marc; Huber, Christian; Mayr, Bettina; Klein, Christoph Algorithms for the automated absolute quantification of diagnostic markers in complex proteomics samples Glen, Diederichs Kohlbacher Fischer Berthold K O I M R (Ed.): Proceedings of the 1st Symposium on Computational Life Sciences (CLS 2005), pp. 151–161, Springer LNBI 3695, 2005. @inproceedings{MyoCLS2005, title = {Algorithms for the automated absolute quantification of diagnostic markers in complex proteomics samples}, author = {Clemens Gröpl and Eva Lange and Knut Reinert and Oliver Kohlbacher and Marc Sturm and Christian Huber and Bettina Mayr and Christoph Klein}, editor = {Diederichs Kohlbacher Fischer K O I M. Berthold R. Glen}, url = {www.complife.org}, year = {2005}, date = {2005-01-01}, booktitle = {Proceedings of the 1st Symposium on Computational Life Sciences (CLS 2005)}, pages = {151--161}, publisher = {Springer LNBI 3695}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Höglund, Annette; Dönnes, Pierre; Blum, Torsten; Adolph, Hans-Werner; Kohlbacher, Oliver Using N-terminal targeting sequences, amino acid composition, and sequence motifs for predicting protein subcellular localization Kurtz, Matthias Rarey Andrew Torda Stefan (Ed.): Proceedings of the German Conference on Bioinformatics (GCB 2005), pp. 45–59, GI, 2005. @inproceedings{MultiLoc_GCB05, title = {Using N-terminal targeting sequences, amino acid composition, and sequence motifs for predicting protein subcellular localization}, author = {Annette Höglund and Pierre Dönnes and Torsten Blum and Hans-Werner Adolph and Oliver Kohlbacher}, editor = {Matthias Rarey Andrew Torda Stefan Kurtz}, url = {MultiLoc_2005.pdf}, year = {2005}, date = {2005-01-01}, booktitle = {Proceedings of the German Conference on Bioinformatics (GCB 2005)}, pages = {45--59}, publisher = {GI}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Klein, Christoph L; Kohlbacher, Oliver; Huber, Christian; Reinert, Knut Reference methods and materials in standardisation and quality assurance FEBS J., 272 (S1), 2005, (in press). (BibTeX) @article{RefMat, title = {Reference methods and materials in standardisation and quality assurance}, author = {Christoph L Klein and Oliver Kohlbacher and Christian Huber and Knut Reinert}, year = {2005}, date = {2005-01-01}, journal = {FEBS J.}, volume = {272}, number = {S1}, note = {in press}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Rausch, Christian; Weber, Tilmann; Kohlbacher, Oliver; Wohlleben, Wolfgang; Huson, Daniel Specificity prediction of adenylation domains in nonribosomal peptide synthetases (NRPS) using Transductive Support Vector Machines (TSVM) Nucl. Acids Res., 33 (18), pp. 5799-5808, 2005. @article{NRPSPred, title = {Specificity prediction of adenylation domains in nonribosomal peptide synthetases (NRPS) using Transductive Support Vector Machines (TSVM)}, author = {Christian Rausch and Tilmann Weber and Oliver Kohlbacher and Wolfgang Wohlleben and Daniel Huson}, url = {http://www.pubmedcentral.gov/articlerender.fcgi?tool=pubmed&pubmedid=16221976}, year = {2005}, date = {2005-01-01}, journal = {Nucl. Acids Res.}, volume = {33}, number = {18}, pages = {5799-5808}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Berthold, Michael; Glen, Robert; Diederichs, Kay; Kohlbacher, Oliver; Fischer, Ingrid Computational Life Sciences Springer Lecture notes in Bioinformatics, 2005. @book{CLS2005b, title = {Computational Life Sciences}, author = {Michael Berthold and Robert Glen and Kay Diederichs and Oliver Kohlbacher and Ingrid Fischer}, url = {http://www.springeronline.com/3-540-29104-0}, year = {2005}, date = {2005-01-01}, volume = {3695}, publisher = {Springer Lecture notes in Bioinformatics}, keywords = {}, pubstate = {published}, tppubtype = {book} } |
Moll, Andreas; Hildebrandt, Andreas; Kerzmann, Andreas; Lenhof, Hans-Peter; Kohlbacher, Oliver BALLView - An Open Source Tool for Molecular Modeling and Visualization Haasis, Klumpp Spath D D K (Ed.): Tagungsband zum doIT Software-Forschungstag 2005, pp. 203–214, MFG Stiftung, Stuttgart, 2005. (BibTeX) @inproceedings{InproceedingsReference.2006-01-19.8468200784, title = {BALLView - An Open Source Tool for Molecular Modeling and Visualization}, author = {Andreas Moll and Andreas Hildebrandt and Andreas Kerzmann and Hans-Peter Lenhof and Oliver Kohlbacher}, editor = {Klumpp D D. Spath K. Haasis}, year = {2005}, date = {2005-01-01}, booktitle = {Tagungsband zum doIT Software-Forschungstag 2005}, pages = {203--214}, publisher = {MFG Stiftung}, address = {Stuttgart}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Höglund, A; Dönnes, P; Adolph, HW; Kohlbacher, O From prediction of subcellular localization to functional classification: Discrimination of DNA-packing and other nuclear proteins Online Journal of Bioinformatics, 6 (1), pp. 51-64, 2005. @article{lokeroref, title = {From prediction of subcellular localization to functional classification: Discrimination of DNA-packing and other nuclear proteins}, author = {A Höglund and P Dönnes and HW Adolph and O Kohlbacher}, url = {http://www.comcen.com.au/~journals/dnapackingabs2005.htm}, year = {2005}, date = {2005-01-01}, journal = {Online Journal of Bioinformatics}, volume = {6}, number = {1}, pages = {51-64}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Supper, Jochen; Dönnes, Pierre; Kohlbacher, Oliver Analysis of MHC-Peptide Binding Using Amino Acid Property-Based Decision Rules Springer Lecture Notes in Computer Science (LNCS), 3686 , pp. 446-453, 2005. @article{MHCDR, title = {Analysis of MHC-Peptide Binding Using Amino Acid Property-Based Decision Rules}, author = {Jochen Supper and Pierre Dönnes and Oliver Kohlbacher}, url = {https://link.springer.com/content/pdf/10.1007/11551188_48.pdf}, year = {2005}, date = {2005-01-01}, journal = {Springer Lecture Notes in Computer Science (LNCS)}, volume = {3686}, pages = {446-453}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Dönnes, Pierre; Kohlbacher, Oliver Integrated modelling of the major events in the MHC class I antigen processing pathway Protein Sci., 14 (8), pp. 2132-2140, 2005. @article{WAPP, title = {Integrated modelling of the major events in the MHC class I antigen processing pathway}, author = {Pierre Dönnes and Oliver Kohlbacher}, url = {http://dx.doi.org/10.1110/ps.051352405}, year = {2005}, date = {2005-01-01}, journal = {Protein Sci.}, volume = {14}, number = {8}, pages = {2132-2140}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Schuler, Mathias M; Dönnes, Pierre; Nastke, Maria-Dorothea; Kohlbacher, Oliver; Rammensee, Hans-Georg; Stevanovic, Stefan SNEP: SNP-derived Epitope Prediction program for minor H antigens. Immunogenetics, 57 (11), pp. 816-820, 2005. @article{SNEP, title = {SNEP: SNP-derived Epitope Prediction program for minor H antigens.}, author = {Mathias M Schuler and Pierre Dönnes and Maria-Dorothea Nastke and Oliver Kohlbacher and Hans-Georg Rammensee and Stefan Stevanovic}, url = {http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s00251-005-0054-5}, year = {2005}, date = {2005-01-01}, journal = {Immunogenetics}, volume = {57}, number = {11}, pages = {816-820}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Schuler, Mathias; Dönnes, Pierre; Nastke, Maria; Kohlbacher, Oliver; Rammensee, H-G; Stevanovic, Stefan SNEP: SNP-derived Epitope Prediction program for minor H antigens Kabelitz, Dietrich (Ed.): Joint Annual Meeting of the German and Scandinavian Societies of Immunology, 21-24 September 2005, Kiel, Germany, pp. 361-622, Immunobiology 210(6-8), 2005. (BibTeX) @inproceedings{InproceedingsReference.2006-01-03.7145695050, title = {SNEP: SNP-derived Epitope Prediction program for minor H antigens}, author = {Mathias Schuler and Pierre Dönnes and Maria Nastke and Oliver Kohlbacher and H-G Rammensee and Stefan Stevanovic}, editor = {Dietrich Kabelitz}, year = {2005}, date = {2005-01-01}, booktitle = {Joint Annual Meeting of the German and Scandinavian Societies of Immunology, 21-24 September 2005, Kiel, Germany}, pages = {361-622}, publisher = {Immunobiology 210(6-8)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |