@article{apweiler2010large,

title = {A large-scale protein-function database.},

author = {Apweiler, Rolf and Armstrong, Richard and Bairoch, Amos and Cornish-Bowden, Athel and Halling, Peter J and Hofmeyr, Jan-Hendrik S and Kettner, Carsten and Leyh, Thomas S and Rohwer, Johann and Schomburg, Dietmar and Steinbeck, Christoph and Tipton, Keith},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=20956966&retmode=ref&cmd=prlinks},

doi = {10.1038/nchembio.460},

year  = {2010},

date = {2010-11-01},

journal = {Nature Chemical Biology},

volume = {6},

number = {11},

pages = {785--785},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2010uk,

title = {What are chemical structures and their relations?},

author = {Hastings, Janna and Batchelor, Colin and Steinbeck, Christoph and Schulz, Stefan},

url = {http://dl.acm.org/citation.cfm?id=1804715.1804742},

isbn = {978-1-60750-534-1},

year  = {2010},

date = {2010-07-01},

pages = {257--270},

publisher = {IOS Press},

abstract = {Abstract In chemistry, advances in computational technologies have allowed research into molecules that have not been synthesized yet, and may never be, to become widespread. These are described in terms of their structures, which are expressed as chemical graphs. ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{griffin2010so,

title = {So what have data standards ever done for us? The view from metabolomics.},

author = {Griffin, Julian L and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=20587079&retmode=ref&cmd=prlinks},

doi = {10.1186/gm159},

year  = {2010},

date = {2010-01-01},

journal = {Genome medicine},

volume = {2},

number = {6},

pages = {38},

abstract = {The standardization of reporting of data promises to revolutionize biology by allowing community access to data generated in laboratories across the globe. This approach has already influenced genomics and transcriptomics. Projects that have previously been viewed as being too big to implement can now be distributed across multiple sites. There are now public databases for gene sequences, transcriptomic profiling and proteomic experiments. However, progress in the metabolomic community has seemed to falter recently, and whereas there are ontologies to describe the metadata for metabolomics there are still no central repositories for the datasets themselves. Here, we examine some of the challenges and potential benefits of further efforts towards data standardization in metabolomics and metabonomics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2010representing,

title = {Representing chemicals using OWL, description graphs and rules},

author = {Hastings, Janna and Dumontier, Michel and Hull, Duncan and Horridge, Matthew and Steinbeck, Christoph and Sattler, Ulrike and Stevens, Robert and H{ö}rne, Tertia and Britz, Katarina},

url = {http://researchspace.csir.co.za/dspace/handle/10204/4919},

year  = {2010},

date = {2010-01-01},

journal = {CEUR Workshop Proceedings},

volume = {614},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kuhn2010cdk,

title = {CDK-Taverna: an open workflow environment for cheminformatics.},

author = {Kuhn, Thomas and Willighagen, Egon L and Zielesny, Achim and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=20346188&retmode=ref&cmd=prlinks},

doi = {10.1186/1471-2105-11-159},

year  = {2010},

date = {2010-01-01},

journal = {BMC Bioinformatics},

volume = {11},

number = {1},

pages = {159},

publisher = {BioMed Central},

abstract = {BACKGROUND:Small molecules are of increasing interest for bioinformatics in areas such as metabolomics and drug discovery. The recent release of large open access chemistry databases generates a demand for flexible tools to process them and discover new knowledge. To freely support open science based on these data resources, it is desirable for the processing tools to be open source and available for everyone. 

 

RESULTS:Here we describe a novel combination of the workflow engine Taverna and the cheminformatics library Chemistry Development Kit (CDK) resulting in a open source workflow solution for cheminformatics. We have implemented more than 160 different workers to handle specific cheminformatics tasks. We describe the applications of CDK-Taverna in various usage scenarios. 

 

CONCLUSIONS:The combination of the workflow engine Taverna and the Chemistry Development Kit provides the first open source cheminformatics workflow solution for the biosciences. With the Taverna-community working towards a more powerful workflow engine and a more user-friendly user interface, CDK-Taverna has the potential to become a free alternative to existing proprietary workflow tools.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{de2010chemical,

title = {Chemical Entities of Biological Interest: an update.},

author = {De Matos, Paula and Alcantara, Rafael and Dekker, Adriano and Ennis, Marcus and Hastings, Janna and Haug, Kenneth and Spiteri, Inmaculada and Turner, Steve and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=19854951&retmode=ref&cmd=prlinks},

doi = {10.1093/nar/gkp886},

year  = {2010},

date = {2010-01-01},

journal = {Nucleic Acids Research},

volume = {38},

number = {Database issue},

pages = {D249--54},

abstract = {Chemical Entities of Biological Interest (ChEBI) is a freely available dictionary of molecular entities focused on 'small' chemical compounds. The molecular entities in question are either natural products or synthetic products used to intervene in the processes of living organisms. Genome-encoded macromolecules (nucleic acids, proteins and peptides derived from proteins by cleavage) are not as a rule included in ChEBI. In addition to molecular entities, ChEBI contains groups (parts of molecular entities) and classes of entities. ChEBI includes an ontological classification, whereby the relationships between molecular entities or classes of entities and their parents and/or children are specified. ChEBI is available online at http://www.ebi.ac.uk/chebi/. This article reports on new features in ChEBI since the last NAR report in 2007, including substructure and similarity searching, a submission tool for authoring of ChEBI datasets by the community and a 30-fold increase in the number of chemical structures stored in ChEBI.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2010substance,

title = {Substance concentrations as conditions for the realization of dispositions},

author = {Hastings, Janna and Steinbeck, Christoph and Jansen, Ludger and Schulz, Stefan},

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Substance+concentrations+as+conditions+for+the+realization+of+dispositions&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5UIjSE-nE4gTnx4DACA},

year  = {2010},

date = {2010-01-01},

journal = {Semantic Applications in Life Sciences: Proceedings of the 4th International Workshop on Formal Biomedical Knowledge Representation, KR-MED},

pages = {9--10},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{batchelor2010ontological,

title = {Ontological dependence, dispositions and institutional reality in chemistry},

author = {Batchelor, Colin and Hastings, Janna and Steinbeck, Christoph},

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Ontological+dependence+dispositions+and+institutional+reality+in+chemistry&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5UOfuEcSJ4ATM8oH4Aw},

year  = {2010},

date = {2010-01-01},

journal = {Proceeding of the 2010 conference on Formal Ontology in Information Systems},

pages = {271--284},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rijnbeek:2009jy,

title = {OrChem - An open source chemistry search engine for Oracle(R).},

author = {Rijnbeek, Mark and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=20298521&retmode=ref&cmd=prlinks},

doi = {10.1186/1758-2946-1-17},

year  = {2009},

date = {2009-01-01},

journal = {Journal of cheminformatics},

volume = {1},

number = {1},

pages = {17},

abstract = {UNLABELLED:ABSTRACT: BACKGROUND:Registration, indexing and searching of chemical structures in relational databases is one of the core areas of cheminformatics. However, little detail has been published on the inner workings of search engines and their development has been mostly closed-source. We decided to develop an open source chemistry extension for Oracle, the de facto database platform in the commercial world. RESULTS:Here we present OrChem, an extension for the Oracle 11G database that adds registration and indexing of chemical structures to support fast substructure and similarity searching. The cheminformatics functionality is provided by the Chemistry Development Kit. OrChem provides similarity searching with response times in the order of seconds for databases with millions of compounds, depending on a given similarity cut-off. For substructure searching, it can make use of multiple processor cores on today's powerful database servers to provide fast response times in equally large data sets. AVAILABILITY:OrChem is free software and can be redistributed and/or modified under the terms of the GNU Lesser General Public License as published by the Free Software Foundation. All software is available via http://orchem.sourceforge.net.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{spjuth2009bioclipse,

title = {Bioclipse 2: a scriptable integration platform for the life sciences.},

author = {Spjuth, Ola and Alvarsson, Jonathan and Berg, Arvid and Eklund, Martin and Kuhn, Stefan and Masak, Carl and Torrance, Gilleain and Wagener, Johannes and Willighagen, Egon L and Steinbeck, Christoph and Wikberg, Jarl E S},

url = {http://www.biomedcentral.com/1471-2105/10/397},

doi = {10.1186/1471-2105-10-397},

year  = {2009},

date = {2009-01-01},

journal = {BMC Bioinformatics},

volume = {10},

number = {1},

pages = {397},

abstract = {BACKGROUND:Contemporary biological research integrates neighboring scientific domains to answer complex questions in fields such as systems biology and drug discovery. This calls for tools that are intuitive to use, yet flexible to adapt to new tasks. RESULTS:Bioclipse is a free, open source workbench with advanced features for the life sciences. Version 2.0 constitutes a complete rewrite of Bioclipse, and delivers a stable, scalable integration platform for developers and an intuitive workbench for end users. All functionality is available both from the graphical user interface and from a built-in novel domain-specific language, supporting the scientist in interdisciplinary research and reproducible analyses through advanced visualization of the inputs and the results. New components for Bioclipse 2 include a rewritten editor for chemical structures, a table for multiple molecules that supports gigabyte-sized files, as well as a graphical editor for sequences and alignments. CONCLUSION:Bioclipse 2 is equipped with advanced tools required to carry out complex analysis in the fields of bio- and cheminformatics. Developed as a Rich Client based on Eclipse, Bioclipse 2 leverages on today's powerful desktop computers for providing a responsive user interface, but also takes full advantage of the Web and networked (Web/Cloud) services for more demanding calculations or retrieval of data. The fact that Bioclipse 2 is based on an advanced and widely used service platform ensures wide extensibility, making it easy to add new algorithms, visualizations, as well as scripting commands. The intuitive tools for end users and the extensible architecture make Bioclipse 2 ideal for interdisciplinary and integrative research.Bioclipse 2 is released under the Eclipse Public License (EPL), a flexible open source license that allows additional plugins to be of any license. Bioclipse 2 is implemented in Java and supported on all major platforms; Source code and binaries are freely available at http://www.bioclipse.net.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Blinov:2008jf,

title = {Performance validation of neural network based (13)c NMR prediction using a publicly available data source.},

author = {Blinov, K A and Smurnyy, Y D and Elyashberg, M E and Churanova, T S and Kvasha, M and Steinbeck, C and Lefebvre, B A and Williams, A J},

url = {http://pubs.acs.org/doi/abs/10.1021/ci700363r},

doi = {10.1021/ci700363r},

year  = {2008},

date = {2008-03-01},

journal = {Journal of Chemical Information and Modeling},

volume = {48},

number = {3},

pages = {550--555},

publisher = {American Chemical Society},

abstract = {The validation of the performance of a neural network based 13C NMR prediction algorithm using a test set available from an open source publicly available database, NMRShiftDB, is described. The validation was performed using a version of the database containing ca. 214,000 chemical shifts as well as for two subsets of the database to compare performance when overlap with the training set is taken into account. The first subset contained ca. 93,000 chemical shifts that were absent from the ACDCNMR DB, the "excluded shift set" used for training of the neural network and the ACDCNMR prediction algorithm, while the second contained ca. 121,000 shifts that were present in the ACDCNMR DB training set, the "included shift set". This work has shown that the mean error between experimental and predicted shifts for the entire database is 1.59 ppm, while the mean deviation for the subset with included shifts is 1.47 and 1.74 ppm for excluded shifts. Since similar work has been reported online for another algorithm we compared the results with the errors determined using Robien's CNMR Neural Network Predictor using the entire NMRShiftDB for program validation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kuhn2008building,

title = {Building blocks for automated elucidation of metabolites: machine learning methods for NMR prediction.},

author = {Kuhn, Stefan and Egert, Bj{ö}rn and Neumann, Steffen and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=18817546&retmode=ref&cmd=prlinks},

doi = {10.1186/1471-2105-9-400},

year  = {2008},

date = {2008-01-01},

journal = {BMC Bioinformatics},

volume = {9},

number = {1},

pages = {400},

abstract = {BACKGROUND:Current efforts in Metabolomics, such as the Human Metabolome Project, collect structures of biological metabolites as well as data for their characterisation, such as spectra for identification of substances and measurements of their concentration. Still, only a fraction of existing metabolites and their spectral fingerprints are known. Computer-Assisted Structure Elucidation (CASE) of biological metabolites will be an important tool to leverage this lack of knowledge. Indispensable for CASE are modules to predict spectra for hypothetical structures. This paper evaluates different statistical and machine learning methods to perform predictions of proton NMR spectra based on data from our open database NMRShiftDB. RESULTS:A mean absolute error of 0.18 ppm was achieved for the prediction of proton NMR shifts ranging from 0 to 11 ppm. Random forest, J48 decision tree and support vector machines achieved similar overall errors. HOSE codes being a notably simple method achieved a comparatively good result of 0.17 ppm mean absolute error. CONCLUSION:NMR prediction methods applied in the course of this work delivered precise predictions which can serve as a building block for Computer-Assisted Structure Elucidation for biological metabolites.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{blinov2008performance,

title = {Performance Validation of Neural Network Based 13C NMR Prediction Using a Publicly Available Data Source},

author = {Blinov, K A and Smurnyy, Y D and Elyashberg, M E and Churanova, T S and Kvasha, M and Steinbeck, C and Lefebvre, B A and Williams, A J},

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Performance+Validation+of+Neural+Network+Based+13C+NMR+Prediction+Using+a+Publicly+Available+Data+Source&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5UPGdF7H14QT-oIDYDQ},

year  = {2008},

date = {2008-01-01},

journal = {Journal of Chemical Information and Modeling},

volume = {48},

number = {3},

pages = {550--555},

publisher = {ACS Publications},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kuhn2007chemical,

title = {Chemical Markup, XML, and the World Wide Web. 7. CMLSpect, an XML vocabulary for spectral data.},

author = {Kuhn, Stefan and Helmus, Tobias and Lancashire, Robert J and Murray-Rust, Peter and Rzepa, Henry S and Steinbeck, Christoph and Willighagen, Egon L},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=17887743&retmode=ref&cmd=prlinks},

doi = {10.1021/ci600531a},

year  = {2007},

date = {2007-01-01},

journal = {Journal of Chemical Information and Modeling},

volume = {47},

number = {6},

pages = {2015--2034},

abstract = {CMLSpect is an extension of Chemical Markup Language (CML) for managing spectral and other analytical data. It is designed to be flexible enough to contain a wide variety of spectral data. The paper describes the CMLElements used and gives practical examples for common types of spectra. In addition it demonstrates how different views of the data can be expressed and what problems still exist.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{spjuth2007bioclipse,

title = {Bioclipse: an open source workbench for chemo- and bioinformatics.},

author = {Spjuth, Ola and Helmus, Tobias and Willighagen, Egon L and Kuhn, Stefan and Eklund, Martin and Wagener, Johannes and Murray-Rust, Peter and Steinbeck, Christoph and Wikberg, Jarl E S},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=17316423&retmode=ref&cmd=prlinks},

doi = {10.1186/1471-2105-8-59},

year  = {2007},

date = {2007-01-01},

journal = {BMC Bioinformatics},

volume = {8},

number = {1},

pages = {59},

abstract = {BACKGROUND:There is a need for software applications that provide users with a complete and extensible toolkit for chemo- and bioinformatics accessible from a single workbench. Commercial packages are expensive and closed source, hence they do not allow end users to modify algorithms and add custom functionality. Existing open source projects are more focused on providing a framework for integrating existing, separately installed bioinformatics packages, rather than providing user-friendly interfaces. No open source chemoinformatics workbench has previously been published, and no successful attempts have been made to integrate chemo- and bioinformatics into a single framework. RESULTS:Bioclipse is an advanced workbench for resources in chemo- and bioinformatics, such as molecules, proteins, sequences, spectra, and scripts. It provides 2D-editing, 3D-visualization, file format conversion, calculation of chemical properties, and much more; all fully integrated into a user-friendly desktop application. Editing supports standard functions such as cut and paste, drag and drop, and undo/redo. Bioclipse is written in Java and based on the Eclipse Rich Client Platform with a state-of-the-art plugin architecture. This gives Bioclipse an advantage over other systems as it can easily be extended with functionality in any desired direction. CONCLUSION:Bioclipse is a powerful workbench for bio- and chemoinformatics as well as an advanced integration platform. The rich functionality, intuitive user interface, and powerful plugin architecture make Bioclipse the most advanced and user-friendly open source workbench for chemo- and bioinformatics. Bioclipse is released under Eclipse Public License (EPL), an open source license which sets no constraints on external plugin licensing; it is totally open for both open source plugins as well as commercial ones. Bioclipse is freely available at http://www.bioclipse.net.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{willighagen2007userscripts,

title = {Userscripts for the life sciences},

author = {Willighagen, E L and O'Boyle, N M and Gopalakrishnan, H and Jiao, D and Guha, R and Steinbeck, C and Wild, D J},

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Userscripts+for+the+life+sciences&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5UMyfGsfU4QS6voDYBA},

year  = {2007},

date = {2007-01-01},

journal = {BMC Bioinformatics},

volume = {8},

number = {1},

pages = {487},

publisher = {BioMed Central Ltd},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schenk:2007kha,

title = {Geminal bismethylation prevents polyketide oxidation and dimerization in the benastatin pathway.},

author = {Schenk, Ang{'e}la and Xu, Zhongli and Pfeiffer, Corina and Steinbeck, Christoph and Hertweck, Christian},

url = {http://doi.wiley.com/10.1002/anie.200702033},

doi = {10.1002/anie.200702033},

year  = {2007},

date = {2007-01-01},

journal = {Angewandte Chemie. International Ed. in English},

volume = {46},

number = {37},

pages = {7035--7038},

publisher = {WILEY-VCH Verlag},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2006recent,

title = {Recent Developments of The Chemistry Development Kit (CDK) - An Open-Source Java Library for Chemo- and Bioinformatics},

author = {Steinbeck, Christoph and Hoppe, Christian and Kuhn, Stefan and Guha, Rajarshi and Willighagen, Egon L},

url = {http://dx.doi.org/10.2174/138161206777585274},

doi = {10.2174/138161206777585274},

year  = {2006},

date = {2006-01-01},

journal = {Current pharmaceutical design},

volume = {12},

number = {17},

pages = {2111--2120},

publisher = {Bentham Science Publishers},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hoppe2006classification,

title = {Classification and comparison of ligand-binding sites derived from grid-mapped knowledge-based potentials},

author = {Hoppe, C and Steinbeck, C and Wohlfahrt, G},

url = {http://dx.doi.org/10.1016/j.jmgm.2005.09.013},

doi = {10.1016/j.jmgm.2005.09.013},

year  = {2006},

date = {2006-01-01},

journal = {Journal of Molecular Graphics & Modelling},

volume = {24},

number = {5},

pages = {328--340},

publisher = {Elsevier},

abstract = {We describe the application of knowledge-based potentials implemented in the MOE program to compare the ligand-binding sites of several proteins. The binding probabilities for a polar and a hydrophobic probe are calculated on a grid to allow easy comparison of binding sites of superimposed related proteins. The method is fast and simple enough to simultaneously use structural information of multiple proteins of a target family. The method can be used to rapidly cluster proteins into subfamilies according to the similarity of hydrophobic and polar fields of their ligand-binding sites. Regions of the binding site which are common within a protein family can be identified and analysed for the design of family-targeted libraries or those which differ for improvement of ligand selectivity. The field-based hierarchical clustering is demonstrated for three protein families: the ligand-binding domains of nuclear receptors, the ATP-binding sites of protein kinases and the substrate binding sites of proteases. More detailed comparisons are presented for serine proteases of the chymotrypsin family, for the peroxisome proliferator-activated receptor subfamily of nuclear receptors and for progesterone and androgen receptor. The results are in good accordance with structure-based analysis and highlight important differences of the binding sites, which have been also described in the literature.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{guha2006blue,

title = {The Blue Obelisk - Interoperability in Chemical Informatics},

author = {Guha, Rajarshi and Howard, Michael T and Hutchison, Geoffrey R and Murray-Rust, Peter and Rzepa, Henry and Steinbeck, Christoph and Wegner, Joerg and Willighagen, Egon L},

url = {http://dx.doi.org/10.1021/ci050400b},

doi = {10.1021/ci050400b},

year  = {2006},

date = {2006-01-01},

journal = {Journal of Chemical Information and Modeling},

volume = {46},

number = {3},

pages = {991--998},

publisher = {ACS Publications},

abstract = {The Blue Obelisk Movement (http://www.blueobelisk.org/) is the name used by a diverse Internet group promoting reusable chemistry via open source software development, consistent and complimentary chemoinformatics research, open data, and open standards. We outline recent examples of cooperation in the Blue Obelisk group: a shared dictionary of algorithms and implementations in chemoinformatics algorithms drawing from our various software projects; a shared repository of chemoinformatics data including elemental properties, atomic radii, isotopes, atom typing rules, and so forth; and Web services for the platform-independent use of chemoinformatics programs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{NMRShiftDB2005,

title = {Eine offene NMR-Datenbank},

author = {Steinbeck, C and Kuhn, Stefan},

year  = {2005},

date = {2005-09-01},

journal = {Nachrichten Aus Der Chemie},

volume = {53},

pages = {1039--1040},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:2004do,

title = {NMRShiftDB -- compound identification and structure elucidation support through a free community-built web database.},

author = {Steinbeck, Christoph and Kuhn, Stefan},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=15464159&retmode=ref&cmd=prlinks},

doi = {10.1016/j.phytochem.2004.08.027},

year  = {2004},

date = {2004-10-01},

journal = {Phytochemistry},

volume = {65},

number = {19},

pages = {2711--2717},

abstract = {Compound identification and support for computer-assisted structure elucidation via a free community-built web database for organic structures and their NMR data is described. The new database NMRShiftDB is available on . As the first NMR database, NMRShiftDB allows not only open access to the database but also open and peer reviewed submission of datasets, enabling the natural products community to build its first free repository of assigned 1H and 13C NMR spectra. In addition to the open access, the underlying database software is built solely from free software and is available under an open source license. This allows collaborating laboratories to fully replicate the database and to create a highly available network of NMRShiftDB mirrors. The database contains about 10,000 structures and assigned spectra, with new datasets constantly added. Its functionality includes (sub-) spectra and (sub-) structure searches as well as shift prediction of 13C spectra based on the current database material.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2004recent,

title = {Recent developments in automated structure elucidation of natural products},

author = {Steinbeck, C},

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Recent+developments+in+automated+structure+elucidation+of+natural+products&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5UKjFHoaF4ASe-YDgAg},

year  = {2004},

date = {2004-01-01},

journal = {Natural Product Reports},

volume = {21},

number = {4},

pages = {512--518},

publisher = {Royal Society of Chemistry},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{han2004evolutionary,

title = {Evolutionary-algorithm-based strategy for computer-assisted structure elucidation},

author = {Han, Y Q and Steinbeck, C},

url = {http://dx.doi.org/10.1021/ci034132y},

doi = {10.1021/ci034132y},

year  = {2004},

date = {2004-01-01},

journal = {Journal of Chemical Information & Computer Sciences},

volume = {44},

number = {2},

pages = {489--498},

publisher = {ACS Publications},

abstract = {An evolutionary algorithm (EA) using a graph-based data structure to explore the molecular constitution space is presented. The EA implementation proves to be a promising alternative to deterministic approaches to the problem of computer-assisted structure elucidation (CASE). While not relying on any external database, the EA-guided CASE program SENECA is able to find correct solutions within calculation times comparable to that of other CASE expert systems. The implementation presented here significantly expands the size limit of constitutional optimization problems treatable with evolutionary algorithms by introducing novel efficient graph-based genetic operators. The new EA-based search strategy is discussed including the underlying data structures, component design, parameter optimization, and evolution process control. Typical structure elucidation examples are given to demonstrate the algorithm's performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2003nmrshiftdb,

title = {NMRShiftDB - Constructing a free chemical information system with open-source components},

author = {Steinbeck, C and Krause, S and Kuhn, S},

url = {http://dx.doi.org/10.1021/ci0341363},

doi = {10.1021/ci0341363},

year  = {2003},

date = {2003-01-01},

journal = {Journal of Chemical Information & Computer Sciences},

volume = {43},

number = {6},

pages = {1733--1739},

publisher = {ACS Publications},

abstract = {The process of designing and implementing NMRShiftDB, an open-source, open-content database for chemical structures and their NMR data based solely on free software is described. NMRShiftDB is available to the community on http://www.nmrshiftdb.org. It allows for open submission and retrieval of data sets by its user community. The software and the content itself is freely distributable, allowing for the establishment of a highly available mirror system of databases in collaborating laboratories.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2003chemistry,

title = {The Chemistry Development Kit (CDK): An open-source Java library for chemo- and bioinformatics},

author = {Steinbeck, C and Han, Y Q and Kuhn, S and Horlacher, O and Luttmann, E and Willighagen, E},

url = {http://dx.doi.org/10.1021/ci025584y},

doi = {10.1021/ci025584y},

year  = {2003},

date = {2003-01-01},

journal = {Journal of Chemical Information & Computer Sciences},

volume = {43},

number = {2},

pages = {493--500},

publisher = {ACS Publications},

abstract = {The Chemistry Development Kit (CDK) is a freely available open-source Java library for Structural Chemo- and Bioinformatics. Its architecture and capabilities as well as the development as an open-source project by a team of international collaborators from academic and industrial institutions is described. The CDK provides methods for many common tasks in molecular informatics, including 2D and 3D rendering of chemical structures, I/O routines, SMILES parsing and generation, ring searches, isomorphism checking, structure diagram generation, etc. Application scenarios as well as access information for interested users and potential contributors are given. [References: 48]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:2001uq,

title = {The automation of natural product structure elucidation.},

author = {Steinbeck, C},

url = {http://europepmc.org/abstract/MED/11560068},

year  = {2001},

date = {2001-05-01},

journal = {Current Opinion in Drug Discovery and Development},

volume = {4},

number = {3},

pages = {338--342},

abstract = {The last two or three years have seen exciting developments in the field of computer-assisted structure elucidation (CASE) with a number of programs becoming commercially or freely available. This was the conditio sine qua non for CASE to be widely applied in the daily work of bench chemists and spectroscopists. A number of promising applications have been published in the area of structure generators, deterministic and stochastic CASE tools and property predictions, including the automatic distinction between natural products and artificial compounds, as well as the determination of 3-D structure from a connection table based on IR spectroscopy. Advancements in coupling techniques between chromatographic and spectroscopic methods demonstrate progress towards a fully automated structure elucidation or identification process starting at the earliest steps of obtaining crude extracts.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{yankep2001further,

title = {Further isoflavonoid metabolites from Millettia griffoniana (Bail)},

author = {Yankep, E and Mbafor, J T and Fomum, Z T and Steinbeck, C and Messanga, B B and Nyasse, B and Budzikiewicz, H and Lenz, C and Schmickler, H},

url = {http://dx.doi.org/10.1016/S0031-9422(00)00400-3},

doi = {10.1016/S0031-9422(00)00400-3},

year  = {2001},

date = {2001-01-01},

journal = {Phytochemistry},

volume = {56},

number = {4},

pages = {363--368},

publisher = {Elsevier},

abstract = {Three new isoflavonoids, griffonianone A (1), B (2) and C (4) were isolated from the root bark of Millettia griffoniama, along with the known maximaisoflavone G (5) and 7-hydroxy-6-methoxy-3',4'-methylenedioxyisoflavone (6). Their structures were assigned on the basis of spectroscopic data and chemical transformations. (C) 2001 Elsevier Science Ltd. All rights reserved. [References: 13]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2001seneca,

title = {SENECA: A platform-independent, distributed, and parallel system for computer-assisted structure elucidation in organic chemistry},

author = {Steinbeck, C},

url = {http://dx.doi.org/10.1021/ci000407n},

doi = {10.1021/ci000407n},

year  = {2001},

date = {2001-01-01},

journal = {Journal of Chemical Information & Computer Sciences},

volume = {41},

number = {6},

pages = {1500--1507},

publisher = {ACS Publications},

abstract = {The program package SENECA for Computer-Assisted Structure Elucidation (CASE) of organic molecules is described. SENECA is written completely in the programming language Java and divided into a server, a client, and a gatekeeper part. While the client allows for input of spectroscopic information, the server part performs the actual structure elucidation by stochastically walking through constitution space while optimizing the molecule toward agreement with given spectral properties. The convergence is guided by simulated annealing. The gatekeeper administers a list of server processes, which can be retrieved by the client. The package is completely platform-independent and its server part can be distributed over the Internet or an intranet using a heterogeneous network of almost any number and type of computers, thus allowing for parallel CASE computations on ordinary networks, present in almost any institution. [References: 23]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{krause2000jchempaint,

title = {JChemPaint - Using the Collaborative Forces of the Internet to Develop a Free Editor for 2D Chemical Structures},

author = {Krause, Stefan and Willighagen, Egon and Steinbeck, Christoph},

url = {http://www.mdpi.org/molecules/papers/50100093.pdf},

year  = {2000},

date = {2000-01-01},

journal = {Molecules},

volume = {5},

number = {1},

pages = {93--98},

publisher = {Molecular Diversity Preservation International},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ho1999solution,

title = {Solution structure of the aminoacyl-capped oligodeoxyribonucleotide duplex (W-TGCGCAC)(2)},

author = {Ho, W C and Steinbeck, C and Richert, C},

url = {http://dx.doi.org/10.1021/bi991169w},

doi = {10.1021/bi991169w},

year  = {1999},

date = {1999-01-01},

journal = {Biochemistry},

volume = {38},

number = {39},

pages = {12597--12606},

publisher = {ACS Publications},

abstract = {Reported here is the solution structure of the aminoacyl-DNA duplex (W-TGCGCAC)(2). This duplex forms a continuously pi-stacked helix consisting of both nucleobases and amino acid side chains. According to NMR and UV analyses, the duplex melts in a cooperative transition and with 1.3-1.8% greater hyperchromicity than the control duplex (TGCGCAC)(2). A van't Hoff analysis of UV melting points at different concentrations shows that the two tryptophan residues contribute 4.8 kcal/mol to the Delta H degrees of complex formation at 10 mM salt concentration and less than 1 kcal/mol at 150 mM I salt. The entropic cost for duplex association in the presence of the amino acid residues is 13 cal/molK greater than that for the control at 10 mM salt concentration, and 3 cal/molK lower than that of the control at 0.15 ionic strength. The conformation of W-TGCGCAC in duplex form, determined via restrained torsion angle molecular dynamics, shows an undisturbed B-form DNA duplex with dangling 3'-termini. The tryptophanyl residue at the 5'-terminus packs tightly against T2 and the proximal part of adenine, without engaging in hydrogen bonding. While not providing strong enthalpic net stabilization of the duplex, the tryptophan "cap" on the duplex does seem to reduce the fraying at the termini, indicating a subtle balance of entropic and enthalpic factors contributing to the molecular dynamics. The structure also shows that, at least in the present sequence context, stacking on the terminal base pair is more favorable than intercalation, probably because the enthalpic cost associated with breaking up the stacking between DNA base pairs cannot be paid for by favorable pi-stacking interactions with the indole ring of tryptophan. These results are of importance for understanding stacking interactions in protein-DNA complexes, particularly those in enzyme-substrate complexes involving exposed nucleobases. [References: 69]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Zhang:1998ci,

title = {Alkaloids from Thalictrum przewalskii.},

author = {Zhang, G L and Rucker, G and Breitmeier, E and Mayer, R and Steinbeck, C},

url = {http://www.thieme-connect.de/DOI/DOI?10.1055/s-2006-957396},

doi = {10.1055/s-2006-957396},

year  = {1998},

date = {1998-01-01},

journal = {Planta Medica},

volume = {64},

number = {2},

pages = {165--171},

publisher = {textcopyright Georg Thieme Verlag Stuttgart textperiodcentered New York},

abstract = {Nine new alkaloids przewaline, przewalskine, przewalskinine, przewalstine, przewalstinine, przewalstidine, przewalstidinine, przewalidine chloride, and 8-hydroxypseudocoptisine chloride were isolated from Thalictrum przewalskii Maxim., together with the known alkaloids berberinium chloride, magnoflorine chloride, N-methylpalaudinium chloride, thalphenine chloride, and N-methylnantenium chloride. Their structures were determined by spectroscopy including EI-MS, FAB-MS, (1)H-NMR, (13)C-NMR, C,H-COSY, C,H-COLOC, HMQC and HMBC techniques.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:1998fj,

title = {The Role of Ionic Backbones in RNA Structure:~ An Unusually Stable Non-WatsontextminusCrick Duplex of a Nonionic Analog in an Apolar Medium},

author = {Christoph Steinbeck and Clemens Richert},

url = {https://pubs.acs.org/doi/10.1021/ja9817951},

doi = {10.1021/ja9817951},

year  = {1998},

date = {1998-01-01},

journal = {Journal of the American Chemical Society},

volume = {120},

number = {45},

pages = {11576--11580},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck1997identification,

title = {Identification of two chromenes from Calea serrata by semiautomatic structure elucidation},

author = {Steinbeck, C and Spitzer, V and Starosta, M and von Poser, G},

url = {http://dx.doi.org/10.1021/np960742z},

doi = {10.1021/np960742z},

year  = {1997},

date = {1997-01-01},

journal = {Journal of Natural Products},

volume = {60},

number = {6},

pages = {627--628},

publisher = {ACS Publications},

abstract = {The isolation and semiautomatic structure identification of the two chromenes, eupatoriochromene (1) and preconene II (2), from the aerial parts of Calea serrata is described. The structure elucidation was performed on the basis of 1D and 2D NMR methods using the recently published computer program LUCY. Neither compound has been isolated from Calea serrata previously. [References: 5]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{berlin1997spectrometrically,

title = {Spectrometrically monitored selection experiments - quantitative laser desorption mass spectrometry of small chemical libraries},

author = {Berlin, K and Jain, R K and Tetzlaff, C and Steinbeck, C and Richert, C},

url = {http://dx.doi.org/10.1016/S1074-5521(97)90237-4},

doi = {10.1016/S1074-5521(97)90237-4},

year  = {1997},

date = {1997-01-01},

journal = {Chemistry & Biology},

volume = {4},

number = {1},

pages = {63--77},

publisher = {Elsevier},

abstract = {Background: Selection experiments involving chemical libraries are routinely used in the pharmaceutical industry for finding and optimizing lead compounds, In principle, almost any process involving a binding event or a reaction could be probed systematically with chemical libraries prepared by combinatorial synthesis, Traditionally, however, the vast majority of library members cannot be monitored during the selection, making a systematic correlation of structure and activity difficult, To interpret selection experiments on the level of all library components, monitoring technologies are required that give a unique and quantitative spectroscopic signal for every compound in a mixture. Results: Quantitative matrix-assisted laser desorption mass spectrometry of libraries of porphyrins and peptide-DNA hybrids consisting of 2-35 compounds is described. Porphyrin libraries were subjected to in vitro selections for liposome incorporation and binding to a protein pocket, it was shown that meso-hydroxyphenyl substituted porphyrins, known high activity photosensitizers of tumors, are preferentially incorporated in liposome membranes. A mixture of peptide-DNA hybrids was assayed for the nuclease stability of its components. Conclusions: Small libraries of non-isobaric compounds can be exhaustively or near-exhaustively monitored by mass spectrometry. Monitored selection experiments can yield detailed structure-activity maps in a single experiment, speeding up drug discovery and the probing of biochemically relevant recognition events. It is proposed that monitored assays for target binding, membrane partitioning, and biostability could be run in parallel, to select drug candidates combining several favorable properties in 'multidimensional' selection experiments. [References: 42]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck1997masp,

title = {Masp - a Program Predicting Mass Spectra of Combinatorial Libraries},

author = {Steinbeck, C and Berlin, K and Richert, C},

url = {http://dx.doi.org/10.1021/ci960160n},

doi = {10.1021/ci960160n},

year  = {1997},

date = {1997-01-01},

journal = {Journal of Chemical Information & Computer Sciences},

volume = {37},

number = {3},

pages = {449--457},

publisher = {ACS Publications},

abstract = {MASP, a program predicting fragmentation-free mass spectra of libraries prepared by combinatorial synthesis, is presented. MASP combines user-defined building blocks with a nonvariable core molecule and calculates isotopically resolved mass spectra. Peak overlap and the abundance of major and minor isotope peaks can be examined interactively and read from a color display of the spectrum. Further, MASP exhaustively screens a Meta-Library Space to identify libraries with minimum peak overlap and maximum diversity. Diversity can be defined by the user, e.g., as size, hydrophobicity, or hydrogen bonding capability. The usefulness of such a screen for the design of libraries is demonstrated for meso-substituted tetraphenylporphyrins and peptides with a meta-library space of up to 3080 libraries and 625 compounds per library. The program operates on a PC platform under MS Windows 95. It may be useful for drug discovery and optimization studies that employ methods of combinatorial synthesis and mass spectrometry-guided in vitro selection. [References: 16]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:1996vs,

title = {LUCY-ein Programm zur Konstitutionsermittlung aus NMR-Korrelationsexperimenten Mein łdots},

author = {Steinbeck, C},

url = {http://www3.interscience.wiley.com/journal/112392792/abstract},

year  = {1996},

date = {1996-01-01},

journal = {Angewandte Chemie},

abstract = {9525-9533. Korrelationsexperimenten** wurde speziell zur Verwendung von HMBC-Daten entworfen.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Berlin1996,

title = {Synthesis of carba-porphyrinoids from tripyrranes and unsaturated dialdehydes},

author = {Berlin, K and Steinbeck, C and Breitmaier, E},

year  = {1996},

date = {1996-01-01},

journal = {Synthesis-Stuttgart},

number = {3},

pages = {336 ff.},

abstract = {Hitherto unknown triaza[18]annulenes 3-5 and 7-10 are synthesized by cyclocondensation of tripyrranes 2 with azulene-1,3-dicarboxaldehyde (1) or cycloheptatriene-1,6-dicarboxaldehyde (6). Their spectroscopical properties with respect to 18 pi aromaticity are discussed. [References: 26]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck1996lucy,

title = {Lucy - A Program For Structure Elucidation From NMR Correlation Experiments},

author = {Steinbeck, C},

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Lucy+A+Program+For+Structure+Elucidation+From+NMR+Correlation+Experiments&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5UIOoLMrm4QT1ooEw},

year  = {1996},

date = {1996-01-01},

journal = {Angewandte Chemie International Edition in English},

volume = {35},

number = {17},

pages = {1984--1986},

publisher = {Wiley Online Library},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:1995ve,

title = {A 4-methyl-7-hydroxyphthalide glycoside and other constituents from Quillaja saponaria molina.},

author = {Steinbeck, C and Schneider, C and Rotscheidt, K and Breitmaier, E},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=7492375&retmode=ref&cmd=prlinks},

year  = {1995},

date = {1995-11-01},

journal = {Phytochemistry},

volume = {40},

number = {4},

pages = {1313--1315},

abstract = {A so far unknown 4-methyl-7-hydroxyphthalideglycoside has been isolated from the methanol extract of the bark of Quillaja saponaria molina. Its structure has been established from NMR experiments as 7-O(-)[beta-glucopyranosyl-(1-->6)-beta-arabinopyranosyl]-7-hydrox y-4-methy l -1[3H]-isobenzofuranone. Two known compounds, 3,4,5-trimethoxyphenyl-beta-D-glucopyranoside and lyoniresinol-3 alpha-O-beta-D-glycopyranoside were also identified.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{zhang1995alkaloids,

title = {Alkaloids from Dactylicapnos torulosa},

author = {Zhang, G L and Rucker, G and Breitmaier, E and Nieger, M and Mayer, R and Steinbeck, C},

url = {http://dx.doi.org/10.1016/0031-9422(95)00192-A},

doi = {10.1016/0031-9422(95)00192-A},

year  = {1995},

date = {1995-01-01},

journal = {Phytochemistry},

volume = {40},

number = {1},

pages = {299--305},

publisher = {Elsevier},

abstract = {Phytochemical investigation of Dactylicapnos torulosa yielded two known compounds,(-)-cis-N-methyl-stylopiumchloride and hydrastinine chloride; and five new alkaloids, dactyline, 8-hydroxydihydrosanguinarine and dactylidine, as well as dactylicapnosine and dactylicapnosinine with novel C-N-O-C moieties. All structures were elucidated by spectroscopical methods. The structure of dactylicapnosine was also determined by single crystal X-ray diffraction analysis. [References: 18]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid34404468,

title = {DECIMER 1.0: deep learning for chemical image recognition using transformers},

author = {Kohulan Rajan and Achim Zielesny and Christoph Steinbeck},

doi = {10.1186/s13321-021-00538-8},

issn = {1758-2946},

journal = {J Cheminform},

volume = {13},

number = {1},

pages = {61},

abstract = {The amount of data available on chemical structures and their properties has increased steadily over the past decades. In particular, articles published before the mid-1990 are available only in printed or scanned form. The extraction and storage of data from those articles in a publicly accessible database are desirable, but doing this manually is a slow and error-prone process. In order to extract chemical structure depictions and convert them into a computer-readable format, Optical Chemical Structure Recognition (OCSR) tools were developed where the best performing OCSR tools are mostly rule-based. The DECIMER (Deep lEarning for Chemical ImagE Recognition) project was launched to address the OCSR problem with the latest computational intelligence methods to provide an automated open-source software solution. Various current deep learning approaches were explored to seek a best-fitting solution to the problem. In a preliminary communication, we outlined the prospect of being able to predict SMILES encodings of chemical structure depictions with about 90% accuracy using a dataset of 50-100 million molecules. In this article, the new DECIMER model is presented, a transformer-based network, which can predict SMILES with above 96% accuracy from depictions of chemical structures without stereochemical information and above 89% accuracy for depictions with stereochemical information.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}