@article{Spicer:2017gy,

title = {Compliance with minimum information guidelines in public metabolomics repositories},

author = {Rachel A Spicer and Reza Salek and Christoph Steinbeck},

url = {http://www.nature.com/articles/sdata2017137},

doi = {10.1038/sdata.2017.137},

year  = {2017},

date = {2017-01-01},

journal = {Scientific Data},

volume = {4},

pages = {sdata2017137},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schober:2017gg,

title = {nmrML: A Community Supported Open Data Standard for the Description, Storage, and Exchange of NMR Data},

author = {Daniel Schober and Daniel Jacob and Michael Wilson and Joseph A Cruz and Ana Marcu and Jason R Grant and Annick Moing and Catherine Deborde and Luis F de Figueiredo and Kenneth Haug and Philippe Rocca-Serra and John Easton and Timothy M D Ebbels and Jie Hao and Christian Ludwig and Ulrich L Günther and Antonio Rosato and Matthias S Klein and Ian A Lewis and Claudio Luchinat and Andrew R Jones and Arturas Grauslys and Martin Larralde and Masashi Yokochi and Naohiro Kobayashi and Andrea Porzel and Julian L Griffin and Mark R Viant and David S Wishart and Christoph Steinbeck and Reza M Salek and Steffen Neumann},

url = {http://pubs.acs.org/doi/10.1021/acs.analchem.7b02795},

doi = {10.1021/acs.analchem.7b02795},

year  = {2017},

date = {2017-01-01},

journal = {Analytical Chemistry},

volume = {90},

number = {1},

pages = {649--656},

publisher = {American Chemical Society},

abstract = {NMR is a widely used analytical technique with a growing number of repositories available. As a result, demands for a vendor-agnostic, open data format for long-term archiving of NMR data have emerged with the aim to ease and encourage sharing, comparison, and reuse of NMR data. Here we present nmrML, an open XML-based exchange and storage format for NMR spectral data. The nmrML format is intended to be fully compatible with existing NMR data for chemical, biochemical, and metabolomics experiments. nmrML can capture raw NMR data, spectral data acquisition parameters, and where available spectral metadata, such as chemical structures associated with spectral assignments. The nmrML format is compatible with pure-compound NMR data for reference spectral libraries as well as NMR data from complex biomixtures, i.e., metabolomics experiments. To facilitate format conversions, we provide nmrML converters for Bruker, JEOL and Agilent/Varian vendor formats. In addition, easy-to-use Web-based spectral viewing, proc...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Khoonsari:2017ds,

title = {Interoperable and scalable metabolomics data analysis with microservices},

author = {Payam Emami Khoonsari and Pablo Moreno and Sven Bergmann and Joachim Burman and Marco Capuccini and Matteo Carone and Marta Cascante and Pedro de Atauri and Carles Foguet and Alejandra González-Beltrán and Thomas Hankemeier and Kenneth Haug and Sijin He and Stephanie Herman and David Johnson and Namrata Kale and Anders Larsson and Steffen Neumann and Kristian Peters and Luca Pireddu and Philippe Rocca-Serra and Pierrick Roger and Rico Rueedi and Christoph Ruttkies and Noureddin Sadawi and Reza M Salek and Susanna-Assunta Sansone and Daniel Schober and Vitaly Selivanov and Etienne A Thévenot and Michael van Vliet and Gianluigi Zanetti and Christoph Steinbeck and Kim Kultima and Ola Spjuth},

url = {http://biorxiv.org/lookup/doi/10.1101/213603},

doi = {10.1101/213603},

year  = {2017},

date = {2017-01-01},

journal = {bioRxiv},

pages = {213603},

publisher = {Cold Spring Harbor Laboratory},

abstract = {<p>Developing a robust and performant data analysis workflow that integrates all necessary components whilst still being able to scale over multiple compute nodes is a challenging task. We here present a generic method based on the microservice architecture, where software tools are encapsulated as Docker containers that can be connected into scientific workflows and executed in parallel using the Kubernetes container orchestrator. The method was developed within the PhenoMeNal consortium to support flexible metabolomics data analysis and was designed as a virtual research environment which can be launched on-demand on cloud resources and desktop computers. IT-expertise requirements on the user side are kept to a minimum, and established workflows can be re-used effortlessly by any novice user. We validate our method on two mass spectrometry studies, one nuclear magnetic resonance spectroscopy study and one fluxomics study, showing that the method scales dynamically with increasing availability of computational resources. We achieved a complete integration of the major software suites resulting in the first turn-key workflow encompassing all steps for mass-spectrometry-based metabolomics including preprocessing, multivariate statistics, and metabolite identification. Microservices is a generic methodology that can serve any scientific discipline and opens up for new types of large-scale integrative science.</p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Spicer:2017cg,

title = {A lost opportunity for science: journals promote data sharing in metabolomics but do not enforce it},

author = {Rachel A Spicer and Christoph Steinbeck},

url = {https://link.springer.com/article/10.1007/s11306-017-1309-5},

doi = {10.1007/s11306-017-1309-5},

year  = {2017},

date = {2017-01-01},

journal = {Metabolomics},

volume = {14},

number = {1},

pages = {16},

publisher = {Springer US},

abstract = {Data sharing is being increasingly required by journals and has been heralded as a solution to the textquoteleftreplication crisistextquoteright. (i) Review data sharing policies of journals publishing the most metabolomics p},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Feunang:2016dp,

title = {ClassyFire: automated chemical classification with a comprehensive, computable taxonomy},

author = {Feunang, Yannick Djoumbou and Eisner, Roman and Knox, Craig and Chepelev, Leonid and Hastings, Janna and Owen, Gareth and Fahy, Eoin and Steinbeck, Christoph and Subramanian, Shankar and Bolton, Evan and Greiner, Russell and Wishart, David S},

url = {http://jcheminf.springeropen.com/articles/10.1186/s13321-016-0174-y},

doi = {10.1186/s13321-016-0174-y},

year  = {2016},

date = {2016-11-01},

journal = {Journal of cheminformatics},

volume = {8},

number = {1},

pages = {61},

publisher = {Springer International Publishing},

abstract = {Scientists have long been driven by the desire to describe, organize, classify, and compare objects using taxonomies and/or ontologies. In contrast to biology, geology, and many other scientific disciplines, the world of chemistry still lacks a standardized chemical ontology or taxonomy. Several attempts at chemical classification have been made; but they have mostly been limited to either manual, or semi-automated proof-of-principle applications. This is regrettable as comprehensive chemical classification and description tools could not only improve our understanding of chemistry but also improve the linkage between chemistry and many other fields. For instance, the chemical classification of a compound could help predict its metabolic fate in humans, its druggability or potential hazards associated with it, among others. However, the sheer number (tens of millions of compounds) and complexity of chemical structures is such that any manual classification effort would prove to be near impossible. We have developed a comprehensive, flexible, and computable, purely structure-based chemical taxonomy (ChemOnt), along with a computer program (ClassyFire) that uses only chemical structures and structural features to automatically assign all known chemical compounds to a taxonomy consisting of >4800 different categories. This new chemical taxonomy consists of up to 11 different levels (Kingdom, SuperClass, Class, SubClass, etc.) with each of the categories defined by unambiguous, computable structural rules. Furthermore each category is named using a consensus-based nomenclature and described (in English) based on the characteristic common structural properties of the compounds it contains. The ClassyFire webserver is freely accessible at http://classyfire.wishartlab.com/ . Moreover, a Ruby API version is available at https://bitbucket.org/wishartlab/classyfire_api , which provides programmatic access to the ClassyFire server and database. ClassyFire has been used to annotate over 77 million compounds and has already been integrated into other software packages to automatically generate textual descriptions for, and/or infer biological properties of over 100,000 compounds. Additional examples and applications are provided in this paper. ClassyFire, in combination with ChemOnt (ClassyFiretextquoterights comprehensive chemical taxonomy), now allows chemists and cheminformaticians to perform large-scale, rapid and automated chemical classification. Moreover, a freely accessible API allows easy access to more than 77 million textquotedblleftClassyFiretextquotedblright classified compounds. The results can be used to help annotate well studied, as well as lesser-known compounds. In addition, these chemical classifications can be used as input for data integration, and many other cheminformatics-related tasks.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Swainston:2016fm,

title = {libChEBI: an API for accessing the ChEBI database},

author = {Swainston, Neil and Hastings, Janna and Dekker, Adriano and Muthukrishnan, Venkatesh and May, John and Steinbeck, Christoph and Mendes, Pedro},

url = {http://jcheminf.springeropen.com/articles/10.1186/s13321-016-0123-9},

doi = {10.1186/s13321-016-0123-9},

year  = {2016},

date = {2016-03-01},

journal = {Journal of cheminformatics},

volume = {8},

number = {1},

pages = {1},

publisher = {Springer International Publishing},

abstract = {ChEBI is a database and ontology of chemical entities of biological interest. It is widely used as a source of identifiers to facilitate unambiguous reference to chemical entities within biological models, databases, ontologies and literature. ChEBI contains a wealth of chemical data, covering over 46,500 distinct chemical entities, and related data such as chemical formula, charge, molecular mass, structure, synonyms and links to external databases. Furthermore, ChEBI is an ontology, and thus provides meaningful links between chemical entities. Unlike many other resources, ChEBI is fully human-curated, providing a reliable, non-redundant collection of chemical entities and related data. While ChEBI is supported by a web service for programmatic access and a number of download files, it does not have an API library to facilitate the use of ChEBI and its data in cheminformatics software.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rahman:2016gb,

title = {Reaction Decoder Tool (RDT): extracting features from chemical reactions},

author = {Rahman, Syed Asad and Torrance, Gilliean and Baldacci, Lorenzo and Cuesta, Sergio Mart{'i}nez and Fenninger, Franz and Gopal, Nimish and Choudhary, Saket and May, John W and Holliday, Gemma L and Steinbeck, Christoph and Thornton, Janet M},

url = {http://bioinformatics.oxfordjournals.org/content/early/2016/03/26/bioinformatics.btw096.full},

doi = {10.1093/bioinformatics/btw096},

year  = {2016},

date = {2016-02-01},

journal = {Bioinformatics},

volume = {32},

number = {13},

pages = {btw096--2066},

publisher = {Oxford University Press},

abstract = {Summary: Extracting chemical features like Atom–Atom Mapping (AAM), Bond Changes (BCs) and Reaction Centres from biochemical reactions helps us understand the chemical composition of enzymatic reactions. Reaction Decoder is a robust command line tool , ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Emwas:2016bw,

title = {Recommendations and Standardization of Biomarker Quantification Using NMR-Based Metabolomics with Particular Focus on Urinary Analysis},

author = {Emwas, Abdul-Hamid and Roy, Raja and McKay, Ryan T and Ryan, Danielle and Brennan, Lorraine and Tenori, Leonardo and Luchinat, Claudio and Gao, Xin and Zeri, Ana Carolina and Gowda, G A Nagana and Raftery, Daniel and Steinbeck, Christoph and Salek, Reza M and Wishart, David S},

url = {http://pubs.acs.org/doi/10.1021/acs.jproteome.5b00885},

doi = {10.1021/acs.jproteome.5b00885},

year  = {2016},

date = {2016-01-01},

journal = {Journal of Proteome Research},

volume = {15},

number = {2},

pages = {acs.jproteome.5b00885--373},

publisher = {American Chemical Society},

abstract = {NMR-based metabolomics has shown considerable promise in disease diagnosis and biomarker discovery because it allows one to nondestructively identify and quantify large numbers of novel metabolite biomarkers in both biofluids and tissues. Precise metabolite quantification is a prerequisite to move any chemical biomarker or biomarker panel from the lab to the clinic. Among the biofluids commonly used for disease diagnosis and prognosis, urine has several advantages. It is abundant, sterile, and easily obtained, needs little sample preparation, and does not require invasive medical procedures for collection. Furthermore, urine captures and concentrates many textquotedblleftunwantedtextquotedblright or textquotedblleftundesirabletextquotedblright compounds throughout the body, providing a rich source of potentially useful disease biomarkers; however, incredible variation in urine chemical concentrations makes analysis of urine and identification of useful urinary biomarkers by NMR challenging. We discuss a number of the most significant issues regarding NMR-based urina...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Levin:2016tv,

title = {From Databases to Big Data},

author = {Levin, N and Salek, R M and Steinbeck, C},

url = {http://books.google.com/books?hl=en&lr=&id=0OLIBAAAQBAJ&oi=fnd&pg=PA317&dq=From+Databases+to+Big+Data&ots=I6kLl-uYLn&sig=j9rkubDvLxQYjNpEmZaaUsFIkuM},

year  = {2016},

date = {2016-01-01},

journal = {Metabolic Phenotyping in łdots},

abstract = {Biomedical sciences have arrived in the age of big data. The rate at which data are being produced is increasing exponentially, and there is mounting enthusiasm over the generation, collection, and use of data to address longstanding questions about human ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wohlgemuth:2016iq,

title = {SPLASH, a hashed identifier for mass spectra},

author = {Wohlgemuth, Gert and Mehta, Sajjan S and Mejia, Ramon F and Neumann, Steffen and Pedrosa, Diego and Pluskal, Tom{'a}{v s} and Schymanski, Emma L and Willighagen, Egon L and Wilson, Michael and Wishart, David S and Arita, Masanori and Dorrestein, Pieter C and Bandeira, Nuno and Wang, Mingxun and Schulze, Tobias and Salek, Reza M and Steinbeck, Christoph and Nainala, Venkata Chandrasekhar and Mistrik, Robert and Nishioka, Takaaki and Fiehn, Oliver},

url = {http://www.nature.com/doifinder/10.1038/nbt.3689},

doi = {10.1038/nbt.3689},

year  = {2016},

date = {2016-01-01},

journal = {Nature Biotechnology},

volume = {34},

number = {11},

pages = {1099--1101},

abstract = {... SPLASH , a hashed identifier for mass spectra. ... We designed the SPLASH (SPectraL hASH) as an unambiguous, database-independent spectrum identifier that fulfills the criteria outlined above and offers some additional functionality. ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kale:2016ku,

title = {MetaboLights: An Open-Access Database Repository for Metabolomics Data.},

author = {Kale, Namrata S and Haug, Kenneth and Conesa, Pablo and Jayseelan, Kalaivani and Moreno, Pablo and Rocca-Serra, Philippe and Nainala, Venkata Chandrasekhar and Spicer, Rachel A and Williams, Mark and Li, Xuefei and Salek, Reza M and Griffin, Julian L and Steinbeck, Christoph},

url = {http://doi.wiley.com/10.1002/0471250953.bi1413s53},

doi = {10.1002/0471250953.bi1413s53},

issn = {1934-340X},

year  = {2016},

date = {2016-01-01},

journal = {Current protocols in bioinformatics / editoral board, Andreas D. Baxevanis ... [et al.]},

volume = {53},

pages = {14.13.1--14.13.18},

publisher = {John Wiley & Sons, Inc.},

address = {Hoboken, NJ, USA},

abstract = {MetaboLights is the first general purpose, open-access database repository for cross-platform and cross-species metabolomics research at the European Bioinformatics Institute (EMBL-EBI). Based upon the open-source ISA framework, MetaboLights provides Metabolomics Standard Initiative (MSI) compliant metadata and raw experimental data associated with metabolomics experiments. Users can upload their study datasets into the MetaboLights Repository. These studies are then automatically assigned a stable and unique identifier (e.g., MTBLS1) that can be used for publication reference. The MetaboLights Reference Layer associates metabolites with metabolomics studies in the archive and is extensively annotated with data fields such as structural and chemical information, NMR and MS spectra, target species, metabolic pathways, and reactions. The database is manually curated with no specific release schedules. MetaboLights is also recommended by journals for metabolomics data deposition. This unit provides a guide to using MetaboLights, downloading experimental data, and depositing metabolomics datasets using user-friendly submission tools. textcopyright 2016 by John Wiley & Sons, Inc.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Edison:2016bd,

title = {The Time Is Right to Focus on Model Organism Metabolomes.},

author = {Edison, Arthur S and Hall, Robert D and Junot, Christophe and Karp, Peter D and Kurland, Irwin J and Mistrik, Robert and Reed, Laura K and Saito, Kazuki and Salek, Reza M and Steinbeck, Christoph and Sumner, Lloyd W and Viant, Mark R},

url = {http://www.mdpi.com/2218-1989/6/1/8},

doi = {10.3390/metabo6010008},

year  = {2016},

date = {2016-01-01},

journal = {Metabolites},

volume = {6},

number = {1},

pages = {8},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Model organisms are an essential component of biological and biomedical research that can be used to study specific biological processes. These organisms are in part selected for facile experimental study. However, just as importantly, intensive study of a small number of model organisms yields important synergies as discoveries in one area of science for a given organism shed light on biological processes in other areas, even for other organisms. Furthermore, the extensive knowledge bases compiled for each model organism enable systems-level understandings of these species, which enhance the overall biological and biomedical knowledge for all organisms, including humans. Building upon extensive genomics research, we argue that the time is now right to focus intensively on model organism metabolomes. We propose a grand challenge for metabolomics studies of model organisms: to identify and map all metabolites onto metabolic pathways, to develop quantitative metabolic models for model organisms, and to relate organism metabolic pathways within the context of evolutionary metabolomics, i.e., phylometabolomics. These efforts should focus on a series of established model organisms in microbial, animal and plant research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{RoccaSerra:2015fn,

title = {Data standards can boost metabolomics research, and if there is a will, there is a way},

author = {Rocca-Serra, Philippe and Salek, Reza M and Arita, Masanori and Correa, Elon and Dayalan, Saravanan and Gonz{'a}lez-Beltr{'a}n, Alejandra and Ebbels, Tim and Goodacre, Royston and Hastings, Janna and Haug, Kenneth and Koulman, Albert and Nikolski, Macha and Oresic, Matej and Sansone, Susanna-Assunta and Schober, Daniel and Smith, James and Steinbeck, Christoph and Viant, Mark R and Neumann, Steffen},

url = {"http://dx.doi.org/10.1007/s11306-015-0879-3},

doi = {10.1007/s11306-015-0879-3},

year  = {2015},

date = {2015-11-01},

journal = {Metabolomics},

volume = {12},

number = {1},

pages = {1--13},

publisher = {Springer US},

abstract = {Metabolomics, doi:10.1007/s11306-015-0879-3},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2015bqa,

title = {ChEBI in 2016: Improved services and an expanding collection of metabolites.},

author = {Hastings, Janna and Owen, Gareth and Dekker, Adriano and Ennis, Marcus and Kale, Namrata and Muthukrishnan, Venkatesh and Turner, Steve and Swainston, Neil and Mendes, Pedro and Steinbeck, Christoph},

url = {http://nar.oxfordjournals.org/content/early/2015/10/13/nar.gkv1031.full},

doi = {10.1093/nar/gkv1031},

year  = {2015},

date = {2015-10-01},

journal = {Nucleic Acids Research},

volume = {44},

number = {D1},

pages = {gkv1031--D1219},

publisher = {Oxford University Press},

abstract = {ChEBI is a database and ontology containing information about chemical entities of biological interest. It currently includes over 46 000 entries, each of which is classified within the ontology and assigned multiple annotations including (where relevant) a chemical structure, database cross-references, synonyms and literature citations. All content is freely available and can be accessed online at http://www.ebi.ac.uk/chebi. In this update paper, we describe recent improvements and additions to the ChEBI offering. We have substantially extended our collection of endogenous metabolites for several organisms including human, mouse, Escherichia coli and yeast. Our front-end has also been reworked and updated, improving the user experience, removing our dependency on Java applets in favour of embedded JavaScript components and moving from a monthly release update to a 'live' website. Programmatic access has been improved by the introduction of a library, libChEBI, in Java, Python and Matlab. Furthermore, we have added two new tools, namely an analysis tool, BiNChE, and a query tool for the ontology, OntoQuery.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Beisken:2015fj,

title = {SpeckTackle: JavaScript charts for spectroscopy.},

author = {Beisken, Stephan and Conesa, Pablo and Haug, Kenneth and Salek, Reza M and Steinbeck, Christoph},

url = {http://www.jcheminf.com/content/7/1/17},

doi = {10.1186/s13321-015-0065-7},

year  = {2015},

date = {2015-01-01},

journal = {Journal of cheminformatics},

volume = {7},

number = {1},

pages = {17},

publisher = {Chemistry Central Ltd},

abstract = {BACKGROUND:Spectra visualisation from methods such as mass spectroscopy, infrared spectroscopy or nuclear magnetic resonance is an essential part of every web-facing spectral resource. The development of an intuitive and versatile visualisation tool is a time- and resource-intensive task, however, most databases use their own embedded viewers and new databases continue to develop their own viewers. 

 

RESULTS:We present SpeckTackle, a custom-tailored JavaScript charting library for spectroscopy in life sciences. SpeckTackle is cross-browser compatible and easy to integrate into existing resources, as we demonstrate for the MetaboLights database. Its default chart types cover common visualisation tasks following the de facto 'look and feel' standards for spectra visualisation. 

 

CONCLUSIONS:SpeckTackle is released under GNU LGPL to encourage uptake and reuse within the community. The latest version of the library including examples and documentation on how to use and extend the library with additional chart types is available online in its public repository.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Moreno:2015gx,

title = {BiNChE: A web tool and library for chemical enrichment analysis based on the ChEBI ontology},

author = {Moreno, Pablo and Beisken, Stephan and Harsha, Bhavana and Muthukrishnan, Venkatesh and Tudose, Ilinca and Dekker, Adriano and Dornfeldt, Stefanie and Taruttis, Franziska and Grosse, Ivo and Hastings, Janna and Neumann, Steffen and Steinbeck, Christoph},

url = {http://www.biomedcentral.com/1471-2105/16/56},

doi = {10.1186/s12859-015-0486-3},

year  = {2015},

date = {2015-01-01},

journal = {BMC Bioinformatics},

volume = {16},

number = {1},

pages = {56},

publisher = {BioMed Central Ltd},

abstract = {Ontology-based enrichment analysis aids in the interpretation and understanding of large-scale biological data. Ontologies are hierarchies of biologically relevant groupings. Using ontology annotations, which link ontology classes to biological entities, enrichment analysis methods assess whether there is a significant over or under representation of entities for ontology classes. While many tools exist that run enrichment analysis for protein sets annotated with the Gene Ontology, there are only a few that can be used for small molecules enrichment analysis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Salek:2015eo,

title = {COordination of Standards in MetabOlomicS (COSMOS): facilitating integrated metabolomics data access},

author = {Salek, Reza M and Neumann, Steffen and Schober, Daniel and Hummel, Jan and Billiau, Kenny and Kopka, Joachim and Correa, Elon and Reijmers, Theo and Rosato, Antonio and Tenori, Leonardo and Turano, Paola and Marin, Silvia and Deborde, Catherine and Jacob, Daniel and Rolin, Dominique and Dartigues, Benjamin and Conesa, Pablo and Haug, Kenneth and Rocca-Serra, Philippe and O'Hagan, Steve and Hao, Jie and van Vliet, Michael and Sysi-Aho, Marko and Ludwig, Christian and Bouwman, Jildau and Cascante, Marta and Ebbels, Timothy and Griffin, Julian L and Moing, Annick and Nikolski, Macha and Oresic, Matej and Sansone, Susanna-Assunta and Viant, Mark R and Goodacre, Royston and Günther, Ulrich L and Hankemeier, Thomas and Luchinat, Claudio and Walther, Dirk and Steinbeck, Christoph},

url = {http://link.springer.com/article/10.1007/s11306-015-0810-y/fulltext.html},

doi = {10.1007/s11306-015-0810-y},

year  = {2015},

date = {2015-01-01},

journal = {Metabolomics},

volume = {11},

number = {6},

pages = {1--11},

publisher = {Springer US},

abstract = {Abstract Metabolomics has become a crucial phenotyping technique in a range of research fields including medicine, the life sciences, biotechnology and the environmental sciences. This necessitates the transfer of experimental information between research groups, as ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2015jc,

title = {eNanoMapper: harnessing ontologies to enable data integration for nanomaterial risk assessment.},

author = {Hastings, Janna and Jeliazkova, Nina and Owen, Gareth and Tsiliki, Georgia and Munteanu, Cristian R and Steinbeck, Christoph and Willighagen, Egon},

url = {http://www.jbiomedsem.com/content/6/1/10},

doi = {10.1186/s13326-015-0005-5},

year  = {2015},

date = {2015-01-01},

journal = {Journal of biomedical semantics},

volume = {6},

number = {1},

pages = {10},

publisher = {BioMed Central Ltd},

abstract = {Engineered nanomaterials (ENMs) are being developed to meet specific application needs in diverse domains across the engineering and biomedical sciences (e.g. drug delivery). However, accompanying the exciting proliferation of novel nanomaterials is a challenging race to understand and predict their possibly detrimental effects on human health and the environment. The eNanoMapper project (www.enanomapper.net) is creating a pan-European computational infrastructure for toxicological data management for ENMs, based on semantic web standards and ontologies. Here, we describe the development of the eNanoMapper ontology based on adopting and extending existing ontologies of relevance for the nanosafety domain. The resulting eNanoMapper ontology is available at http://purl.enanomapper.net/onto/enanomapper.owl. We aim to make the re-use of external ontology content seamless and thus we have developed a library to automate the extraction of subsets of ontology content and the assembly of the subsets into an integrated whole. The library is available (open source) at http://github.com/enanomapper/slimmer/. Finally, we give a comprehensive survey of the domain content and identify gap areas. ENM safety is at the boundary between engineering and the life sciences, and at the boundary between molecular granularity and bulk granularity. This creates challenges for the definition of key entities in the domain, which we also discuss.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Morgat:2015jo,

title = {Updates in Rhea--a manually curated resource of biochemical reactions.},

author = {Morgat, Anne and Axelsen, Kristian B and Lombardot, Thierry and Alcantara, Rafael and Aimo, Lucila and Zerara, Mohamed and Niknejad, Anne and Belda, Eugeni and Hyka-Nouspikel, Nevila and Coudert, Elisabeth and Redaschi, Nicole and Bougueleret, Lydie and Steinbeck, Christoph and Xenarios, Ioannis and Bridge, Alan},

url = {http://nar.oxfordjournals.org/lookup/doi/10.1093/nar/gku961},

doi = {10.1093/nar/gku961},

year  = {2015},

date = {2015-01-01},

journal = {Nucleic Acids Research},

volume = {43},

number = {Database issue},

pages = {D459--64},

publisher = {Oxford University Press},

abstract = {Rhea (http://www.ebi.ac.uk/rhea) is a comprehensive and non-redundant resource of expert-curated biochemical reactions described using species from the ChEBI (Chemical Entities of Biological Interest) ontology of small molecules. Rhea has been designed for the functional annotation of enzymes and the description of genome-scale metabolic networks, providing stoichiometrically balanced enzyme-catalyzed reactions (covering the IUBMB Enzyme Nomenclature list and additional reactions), transport reactions and spontaneously occurring reactions. Rhea reactions are extensively curated with links to source literature and are mapped to other publicly available enzyme and pathway databases such as Reactome, BioCyc, KEGG and UniPathway, through manual curation and computational methods. Here we describe developments in Rhea since our last report in the 2012 database issue of Nucleic Acids Research. These include significant growth in the number of Rhea reactions and the inclusion of reactions involving complex macromolecules such as proteins, nucleic acids and other polymers that lie outside the scope of ChEBI. Together these developments will significantly increase the utility of Rhea as a tool for the description, analysis and reconciliation of genome-scale metabolic models.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Griss:2014kc,

title = {The mzTab data exchange format: communicating mass-spectrometry-based proteomics and metabolomics experimental results to a wider audience.},

author = {Griss, Johannes and Jones, Andrew R and Sachsenberg, Timo and Walzer, Mathias and Gatto, Laurent and Hartler, J{ü}rgen and Thallinger, Gerhard G and Salek, Reza M and Steinbeck, Christoph and Neuhauser, Nadin and Cox, J{ü}rgen and Neumann, Steffen and Fan, Jun and Reisinger, Florian and Xu, Qing-Wei and Del-Toro, Noemi and P{'e}rez-Riverol, Yasset and Ghali, Fawaz and Bandeira, Nuno and Xenarios, Ioannis and Kohlbacher, Oliver and Vizca{'i}no, Juan Antonio and Hermjakob, Henning},

url = {http://www.mcponline.org/cgi/doi/10.1074/mcp.O113.036681},

doi = {10.1074/mcp.O113.036681},

year  = {2014},

date = {2014-10-01},

journal = {Molecular & Cellular Proteomics},

volume = {13},

number = {10},

pages = {2765--2775},

publisher = {American Society for Biochemistry and Molecular Biology},

abstract = {The HUPO Proteomics Standards Initiative has developed several standardized data formats to facilitate data sharing in mass spectrometry (MS)-based proteomics. These allow researchers to report their complete results in a unified way. However, at present, there is no format to describe the final qualitative and quantitative results for proteomics and metabolomics experiments in a simple tabular format. Many downstream analysis use cases are only concerned with the final results of an experiment and require an easily accessible format, compatible with tools such as Microsoft Excel or R. We developed the mzTab file format for MS-based proteomics and metabolomics results to meet this need. mzTab is intended as a lightweight supplement to the existing standard XML-based file formats (mzML, mzIdentML, mzQuantML), providing a comprehensive summary, similar in concept to the supplemental material of a scientific publication. mzTab files can contain protein, peptide, and small molecule identifications together with experimental metadata and basic quantitative information. The format is not intended to store the complete experimental evidence but provides mechanisms to report results at different levels of detail. These range from a simple summary of the final results to a representation of the results including the experimental design. This format is ideally suited to make MS-based proteomics and metabolomics results available to a wider biological community outside the field of MS. Several software tools for proteomics and metabolomics have already adapted the format as an output format. The comprehensive mzTab specification document and extensive additional documentation can be found online.},

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}

}