Publications

@article{publ2001984494,

title = {Interoperable and scalable data analysis with microservices: Applications in Metabolomics.},

author = {P Emami Khoonsari and P Moreno and S Bergmann and J Burman and M Capuccini and M Carone and M Cascante and P de Atauri and C Foguet and A Gonzalez-Beltran and T Hankemeier and K Haug and S He and S Herman and D Johnson and A Larsson and N Kale and K Peters and S Neumann and P Rocca-Serra and L Pireddu and R Rueedi and P Roger and N Sadawi and C Ruttkies and SA Sansone and RM Salek and V Selivanov and D Schober and EA Thévenot and M van Vliet and G Zanetti and C Steinbeck and K Kultima and O Spjuth},

doi = {10.1093/bioinformatics/btz160},

year  = {2019},

date = {2019-01-01},

address = {Oxford},

abstract = {The PhenoMeNal consortium maintains a web portal (https://portal.phenomenal-h2020.eu) providing a GUI for launching the virtual research environment. The GitHub repository https://github.com/phnmnl/ hosts the source code of all projects. 

Supplementary data are available at Bioinformatics online. 

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 introduce 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 using the Kubernetes container orchestrator. 

We developed a virtual research environment which facilitates rapid integration of new tools and developing scalable and interoperable workflows for performing metabolomics data analysis. The environment can be launched on-demand on cloud resources and desktop computers. IT-expertise requirements on the user side are kept to a minimum, and workflows can be re-used effortlessly by any novice user. We validate our method in the field of metabolomics on two mass spectrometry, one nuclear magnetic resonance spectroscopy and one fluxomics study. We showed that the method scales dynamically with increasing availability of computational resources. We demonstrated that the method facilitates interoperability using integration of the major software suites resulting in a turn-key workflow encompassing all steps for mass-spectrometry-based metabolomics including preprocessing, statistics, and identification. Microservices is a generic methodology that can serve any scientific discipline and opens up for new types of large-scale integrative science. 

AVAILABILITY AND IMPLEMENTATION 

SUPPLEMENTARY INFORMATION 

MOTIVATION 

RESULTS},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Fritsch:2019dt,

title = {ErtlFunctionalGroupsFinder: automated rule-based functional group detection with the Chemistry Development Kit (CDK)},

author = {Sebastian Fritsch and Stefan Neumann and Jonas Schaub and Christoph Steinbeck and Achim Zielesny},

url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0361-8},

doi = {10.1186/s13321-019-0361-8},

year  = {2019},

date = {2019-01-01},

journal = {Journal of cheminformatics},

volume = {11},

number = {1},

pages = {37},

publisher = {BioMed Central},

abstract = {The Ertl algorithm for automated functional groups (FG) detection and extraction of organic molecules is implemented on the basis of the Chemistry Development Kit (CDK). A distinct impact of the chosen CDK aromaticity model is demonstrated by an FG analysis of the ChEMBL database compounds. The average performance of less than a millisecond for a single-molecule FG extraction allows for fast processing of even large compound databases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck60376927,

title = {NaPLeS: a natural products likeness scorer—web application and database},

author = {Christoph Steinbeck and Maria Sorokina and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-019-0378-z},

doi = {10.1186/s13321-019-0378-z},

year  = {2019},

date = {2019-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:31313429b,

title = {NFDI4Chem: Shaping a Digital and Cultural Change in Chemistry.},

author = {Herres-Pawlis S and Koepler O and Steinbeck C},

doi = {10.1002/anie.201907260},

year  = {2019},

date = {2019-01-01},

journal = {Angewandte Chemie (International ed. in English)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pupier:2018jo,

title = {NMReDATA, a standard to report the NMR assignment and parameters of organic compounds},

author = {Marion Pupier and Jean Marc Nuzillard and Julien Wist and Nils E Schlörer and Stefan Kuhn and Mate Erdelyi and Christoph Steinbeck and Antony J Williams and Craig Butts and Tim D W Claridge and Bozhana Mikhova and Wolfgang Robien and Hesam Dashti and Hamid R Eghbalnia and Christophe Far{`e}s and Christian Adam and Kessler Pavel and Fabrice Moriaud and Mikhail Elyashberg and Dimitris Argyropoulos and Manuel Pérez and Patrick Giraudeau and Roberto R Gil and Paul Trevorrow and Damien Jeannerat},

url = {https://onlinelibrary.wiley.com/doi/full/10.1002/mrc.4737},

doi = {10.1002/mrc.4737},

year  = {2018},

date = {2018-01-01},

journal = {Magnetic Resonance in Chemistry},

publisher = {Wiley-Blackwell},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ritter:2018bd,

title = {In vivo and in vitro identification of Z-BOX C – a new bilirubin oxidation end product},

author = {Marcel Ritter and Sandesh Neupane and Raphael A Seidel and Christoph Steinbeck and Georg Pohnert},

url = {http://pubs.rsc.org/en/content/articlehtml/2018/ob/c8ob00164b},

doi = {10.1039/C8OB00164B},

year  = {2018},

date = {2018-01-01},

journal = {Organic & Biomolecular Chemistry},

volume = {6},

pages = {967},

publisher = {The Royal Society of Chemistry},

abstract = {A new bilirubin oxidation end product (BOX) was isolated and characterized. The formation of the so-called Z-BOX C proceeds from bilirubin via propentdyopents as intermediates. This BOX was detected in pathological human bile samples using liquid chromatography/mass spectrometry and has potential relevance for liver dysfunction and cerebral vasospasms.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Peters:2018cv,

title = {Current Challenges in Plant Eco-Metabolomics},

author = {Kristian Peters and Anja Worrich and Alexander Weinhold and Oliver Alka and Gerd Balcke and Claudia Birkemeyer and Helge Bruelheide and Onno Calf and Sophie Dietz and Kai Dührkop and Emmanuel Gaquerel and Uwe Heinig and Marlen Kücklich and Mirka Macel and Caroline Müller and Yvonne Poeschl and Georg Pohnert and Christian Ristok and Victor Rodr{'i}guez and Christoph Ruttkies and Meredith Schuman and Rabea Schweiger and Nir Shahaf and Christoph Steinbeck and Maria Tortosa and Hendrik Treutler and Nico Ueberschaar and Pablo Velasco and Brigitte Weiß and Anja Widdig and Steffen Neumann and Nicole Dam},

url = {http://www.mdpi.com/1422-0067/19/5/1385/htm},

doi = {10.3390/ijms19051385},

year  = {2018},

date = {2018-01-01},

journal = {International Journal of Molecular Sciences},

volume = {19},

number = {5},

pages = {1385},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {The relatively new research discipline of Eco-Metabolomics is the application of metabolomics techniques to ecology with the aim to characterise biochemical interactions of organisms across different spatial and temporal scales. Metabolomics is an untargeted biochemical approach to measure many thousands of metabolites in different species, including plants and animals. Changes in metabolite concentrations can provide mechanistic evidence for biochemical processes that are relevant at ecological scales. These include physiological, phenotypic and morphological responses of plants and communities to environmental changes and also interactions with other organisms. Traditionally, research in biochemistry and ecology comes from two different directions and is performed at distinct spatiotemporal scales. Biochemical studies most often focus on intrinsic processes in individuals at physiological and cellular scales. Generally, they take a bottom-up approach scaling up cellular processes from spatiotemporally fine to coarser scales. Ecological studies usually focus on extrinsic processes acting upon organisms at population and community scales and typically study top-down and bottom-up processes in combination. Eco-Metabolomics is a transdisciplinary research discipline that links biochemistry and ecology and connects the distinct spatiotemporal scales. In this review, we focus on approaches to study chemical and biochemical interactions of plants at various ecological levels, mainly plant-organismal interactions, and discuss related examples from other domains. We present recent developments and highlight advancements in Eco-Metabolomics over the last decade from various angles. We further address the five key challenges: (1) complex experimental designs and large variation of metabolite profiles; (2) feature extraction; (3) metabolite identification; (4) statistical analyses; and (5) bioinformatics software tools and workflows. The presented solutions to these challenges will advance connecting the distinct spatiotemporal scales and bridging biochemistry and ecology.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Guo:2018ge,

title = {Expanding the Rubterolone Family - Intrinsic Reactivity and Directed Diversification of PKS-derived Pyrans},

author = {Huijuan Guo and Rene Benndorf and Stefanie König and Daniel Leichnitz and Christiane Weigel and Gundela Peschel and Patrick Berthel and Marcel Kaiser and Christoph Steinbeck and Oliver Werz and Michael Poulsen and Christine Beemelmanns},

url = {https://onlinelibrary.wiley.com/doi/full/10.1002/chem.201802066},

doi = {10.1002/chem.201802066},

year  = {2018},

date = {2018-01-01},

journal = {Chemistry – A European Journal},

publisher = {Wiley-Blackwell},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{McAlpine:2018ee,

title = {The value of universally available raw NMR data for transparency, reproducibility, and integrity in natural product research},

author = {James B McAlpine and Shao-Nong Chen and Andrei Kutateladze and John B MacMillan and Giovanni Appendino and Andersson Barison and Mehdi A Beniddir and Maique W Biavatti and Stefan Bluml and Asmaa Boufridi and Mark S Butler and Robert J Capon and Young H Choi and David Coppage and Phillip Crews and Michael T Crimmins and Marie Csete and Pradeep Dewapriya and Joseph M Egan and Mary J Garson and Grégory Genta-Jouve and William H Gerwick and Harald Gross and Mary Kay Harper and Precilia Hermanto and James M Hook and Luke Hunter and Damien Jeannerat and Nai-Yun Ji and Tyler A Johnson and David G I Kingston and Hiroyuki Koshino and Hsiau-Wei Lee and Guy Lewin and Jie Li and Roger G Linington and Miaomiao Liu and Kerry L McPhail and Tadeusz F Molinski and Bradley S Moore and Joo-Won Nam and Ram P Neupane and Matthias Niemitz and Jean Marc Nuzillard and Nicholas H Oberlies and Fernanda M M Ocampos and Guohui Pan and Ronald J Quinn and Sai D Reddy and Jean-Hugues Renault and José Rivera-Chávez and Wolfgang Robien and Carla M Saunders and Thomas J Schmidt and Christoph Seger and Ben Shen and Christoph Steinbeck and Hermann Stuppner and Sonja Sturm and Orazio Taglialatela-Scafati and Dean J Tantillo and Robert Verpoorte and Bin-Gui Wang and Craig M Williams and Philip G Williams and Julien Wist and Jian-Min Yue and Chen Zhang and Zhengren Xu and Charlotte Simmler and David C Lankin and Jonathan Bisson and Guido F Pauli},

url = {https://pubs.rsc.org/en/content/articlehtml/2018/np/c7np00064b},

doi = {10.1039/C7NP00064B},

year  = {2018},

date = {2018-01-01},

journal = {Natural Product Reports},

volume = {33},

pages = {1028},

publisher = {The Royal Society of Chemistry},

abstract = {Covering: up to 2018With contributions from the global natural product (NP) research community, and continuing the Raw Data Initiative, this review collects a comprehensive demonstration of the immense scientific value of disseminating raw nuclear magnetic resonance (NMR) data, independently of, and in parallel with, classical publishing outlets. A comprehensive compilation of historic to present-day cases as well as contemporary and future applications show that addressing the urgent need for a repository of publicly accessible raw NMR data has the potential to transform natural products (NPs) and associated fields of chemical and biomedical research. The call for advancing open sharing mechanisms for raw data is intended to enhance the transparency of experimental protocols, augment the reproducibility of reported outcomes, including biological studies, become a regular component of responsible research, and thereby enrich the integrity of NP research and related fields.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Peters:2018dt,

title = {PhenoMeNal: Processing and analysis of Metabolomics data in the Cloud},

author = {Kristian Peters and James Bradbury and Sven Bergmann and Marco Capuccini and Marta Cascante and Pedro de Atauri and Tim Ebbels and Carles Foguet and Robert Glen and Alejandra González-Beltrán and Evangelos Handakas and Thomas Hankemeier and Stephanie Herman and Kenneth Haug and Petr Holub and Massimiliano Izzo and Daniel Jacob and David Johnson and Fabien Jourdan and Namrata Kale and Ibrahim Karaman and Bita Khalili and Payam Emami Khoonsari and Kim Kultima and Samuel Lampa and Anders Larsson and Pablo Moreno and Steffen Neumann and Jon Ander Novella and Claire O'Donovan and Jake TM Pearce and Alina Peluso and Luca Pireddu and Marco Enrico Piras and Michelle AC Reed and Philippe Rocca-Serra and Pierrick Roger and Antonio Rosato and Rico Rueedi and Christoph Ruttkies and Noureddin Sadawi and Reza Salek and Susanna-Assunta Sansone and Vitaly Selivanov and Ola Spjuth and Daniel Schober and Etienne A Thévenot and Mattia Tomasoni and Merlijn van Rijswijk and Michael van Vliet and Mark Viant and Ralf Weber and Gianluigi Zanetti and Christoph Steinbeck},

url = {http://biorxiv.org/lookup/doi/10.1101/409151},

doi = {10.1101/409151},

year  = {2018},

date = {2018-01-01},

journal = {bioRxiv},

pages = {409151},

publisher = {Cold Spring Harbor Laboratory},

abstract = {<p>Background: Metabolomics is the comprehensive study of a multitude of small molecules to gain insight into an organism9s metabolism. The research field is dynamic and expanding with applications across biomedical, biotechnological and many other applied biological domains. Its computationally-intensive nature has driven requirements for open data formats, data repositories and data analysis tools. However, the rapid progress has resulted in a mosaic of independent, and sometimes incompatible, analysis methods that are difficult to connect into a useful and complete data analysis solution. Findings: The PhenoMeNal (Phenome and Metabolome aNalysis) e-infrastructure provides a complete, workflow-oriented, interoperable metabolomics data analysis solution for a modern infrastructure-as-a-service (IaaS) cloud platform. PhenoMeNal seamlessly integrates a wide array of existing open source tools which are tested and packaged as Docker containers through the project9s continuous integration process and deployed based on a kubernetes orchestration framework. It also provides a number of standardized, automated and published analysis workflows in the user interfaces Galaxy, Jupyter, Luigi and Pachyderm. Conclusions: PhenoMeNal constitutes a keystone solution in cloud infrastructures available for metabolomics. It provides scientists with a ready-to-use, workflow-driven, reproducible and shareable data analysis platform harmonizing the software installation and configuration through user-friendly web interfaces. The deployed cloud environments can be dynamically scaled to enable large-scale analyses which are interfaced through standard data formats, versioned, and have been tested for reproducibility and interoperability. The flexible implementation of PhenoMeNal allows easy adaptation of the infrastructure to other application areas and 9omics research domains.</p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:30535405,

title = {PhenoMeNal: Processing and analysis of Metabolomics data in the Cloud.},

author = {Peters K and Bradbury J and Bergmann S and Capuccini M and Cascante M and Atauri de P and Ebbels TMD and Foguet C and Glen R and Gonzalez-Beltran A and Günther UL and Handakas E and Steinbeck C},

doi = {10.1093/gigascience/giy149},

year  = {2018},

date = {2018-01-01},

journal = {GigaScience},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Spicer:2017cr,

title = {A decade after the metabolomics standards initiative it's time for a revision},

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

url = {http://www.nature.com/articles/sdata2017138},

doi = {10.1038/sdata.2017.138},

year  = {2017},

date = {2017-09-01},

journal = {Scientific Data},

volume = {4},

pages = {sdata2017138},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{vanRijswijk:2017jk,

title = {The future of metabolomics in ELIXIR},

author = {Merlijn van Rijswijk and Charlie Beirnaert and Christophe Caron and Marta Cascante and Victoria Dominguez and Warwick B Dunn and Timothy M D Ebbels and Franck Giacomoni and Alejandra González-Beltrán and Thomas Hankemeier and Kenneth Haug and Jose L Izquierdo-Garcia and Rafael C Jiménez and Fabien Jourdan and Namrata Kale and Maria I Klapa and Oliver Kohlbacher and Kairi Koort and Kim Kultima and Gildas Le Corguillé and Nicholas K Moschonas and Steffen Neumann and Claire O'Donovan and Martin Reczko and Philippe Rocca-Serra and Antonio Rosato and Reza M Salek and Susanna-Assunta Sansone and Venkata Satagopam and Daniel Schober and Ruth Shimmo and Rachel A Spicer and Ola Spjuth and Etienne A Thévenot and Mark R Viant and Ralf J M Weber and Egon L Willighagen and Gianluigi Zanetti and Christoph Steinbeck},

url = {https://f1000research.com/articles/6-1649/v1},

doi = {10.12688/f1000research.12342.1},

year  = {2017},

date = {2017-09-01},

journal = {F1000Research},

volume = {6},

pages = {1649},

abstract = {Read the latest article version by Merlijn van Rijswijk, Charlie Beirnaert, Christophe Caron, Marta Cascante, Victoria Dominguez, Warwick B. Dunn, Timothy M. D. Ebbels, Franck Giacomoni, Alejandra Gonzalez-Beltran, Thomas Hankemeier, Kenneth Haug, Jose L. Izquierdo-Garcia, Rafael C. Jimenez, Fabien Jourdan, Namrata Kale, Maria I. Klapa, Oliver Kohlbacher, Kairi Koort, Kim Kultima, Gildas Le Corguillé, Nicholas K. Moschonas, Steffen Neumann, Claire OtextquoterightDonovan, Martin Reczko, Philippe Rocca-Serra, Antonio Rosato, Reza M. Salek, Susanna-Assunta Sansone, Venkata Satagopam, Daniel Schober, Ruth Shimmo, Rachel A. Spicer, Ola Spjuth, Etienne A. Thévenot, Mark R. Viant, Ralf J. M. Weber, Egon L. Willighagen, Gianluigi Zanetti, Christoph Steinbeck, at F1000Research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Spicer:2017jc,

title = {Navigating freely-available software tools for metabolomics analysis},

author = {Spicer, Rachel and Salek, Reza M and Moreno, Pablo and Cañueto, Daniel and Steinbeck, Christoph},

url = {https://link.springer.com/article/10.1007/s11306-017-1242-7},

doi = {10.1007/s11306-017-1242-7},

year  = {2017},

date = {2017-08-01},

journal = {Metabolomics},

volume = {13},

number = {9},

pages = {106},

publisher = {Springer US},

abstract = {The field of metabolomics has expanded greatly over the past two decades, both as an experimental science with applications in many areas, as well as in regards to data standards and bioinformatics so},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PerezRiverol:2017ek,

title = {Discovering and linking public omics data sets using the Omics Discovery Index},

author = {Pèrez-Riverol, Yasset and Bai, Mingze and da Veiga Leprevost, Felipe and Squizzato, Silvano and Park, Young Mi and Haug, Kenneth and Carroll, Adam J and Spalding, Dylan and Paschall, Justin and Wang, Mingxun and Del-Toro, Noemi and Ternent, Tobias and Zhang, Peng and Buso, Nicola and Bandeira, Nuno and Deutsch, Eric W and Campbell, David S and Beavis, Ronald C and Salek, Reza M and Sarkans, Ugis and Petryszak, Robert and Keays, Maria and Fahy, Eoin and Sud, Manish and Subramaniam, Shankar and Barbera, Ariana and Jim{'e}nez, Rafael C and Nesvizhskii, Alexey I and Sansone, Susanna-Assunta and Steinbeck, Christoph and Lopez, Rodrigo and Vizca{'i}no, Juan A and Ping, Peipei and Hermjakob, Henning},

url = {http://www.nature.com/doifinder/10.1038/nbt.3790},

doi = {10.1038/nbt.3790},

year  = {2017},

date = {2017-05-01},

journal = {Nature Biotechnology},

volume = {35},

number = {5},

pages = {406--409},

publisher = {Nature Research},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Haug:2017cb,

title = {Global open data management in metabolomics.},

author = {Haug, Kenneth and Salek, Reza M and Steinbeck, Christoph},

url = {http://linkinghub.elsevier.com/retrieve/pii/S1367593116302083},

doi = {10.1016/j.cbpa.2016.12.024},

year  = {2017},

date = {2017-02-01},

journal = {Current Opinion in Chemical Biology},

volume = {36},

pages = {58--63},

abstract = {Chemical Biology employs chemical synthesis, analytical chemistry and other tools to study biological systems. Recent advances in both molecular biology such as next generation sequencing (NGS) have led to unprecedented insights towards the evolution of organisms' biochemical repertoires. Because of the specific data sharing culture in Genomics, genomes from all kingdoms of life become readily available for further analysis by other researchers. While the genome expresses the potential of an organism to adapt to external influences, the Metabolome presents a molecular phenotype that allows us to asses the external influences under which an organism exists and develops in a dynamic way. Steady advancements in instrumentation towards high-throughput and highresolution methods have led to a revival of analytical chemistry methods for the measurement and analysis of the metabolome of organisms. This steady growth of metabolomics as a field is leading to a similar accumulation of big data across laboratories worldwide as can be observed in all of the other omics areas. This calls for the development of methods and technologies for handling and dealing with such large datasets, for efficiently distributing them and for enabling re-analysis. Here we describe the recently emerging ecosystem of global open-access databases and data exchange efforts between them, as well as the foundations and obstacles that enable or prevent the data sharing and reanalysis of this data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Larralde:2017di,

title = {mzML2ISA & nmrML2ISA: generating enriched ISA-Tab metadata files from metabolomics XML data.},

author = {Larralde, Martin and Lawson, Thomas N and Weber, Ralf J M and Moreno, Pablo and Haug, Kenneth and Rocca-Serra, Philippe and Viant, Mark R and Steinbeck, Christoph and Salek, Reza M},

url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btx169},

doi = {10.1093/bioinformatics/btx169},

year  = {2017},

date = {2017-01-01},

journal = {Bioinformatics},

abstract = {Summary:Submission to the MetaboLights repository for metabolomics data currently places the burden of reporting instrument and acquisition parameters in ISA-Tab format on users, who have to do it manually, a process that is time consuming and prone to user input error. Since the large majority of these parameters are embedded in instrument raw data files, an opportunity exists to capture this metadata more accurately. Here we report a set of Python packages that can automatically generate ISA-Tab metadata file stubs from raw XML metabolomics data files. The parsing packages are separated into mzML2ISA (encompassing mzML and imzML formats) and nmrML2ISA (nmrML format only). Overall, the use of mzML2ISA & nmrML2ISA reduces the time needed to capture metadata substantially (capturing 90% of metadata on assay and sample levels), is much less prone to user input errors, improves compliance with minimum information reporting guidelines and facilitates more finely grained data exploration and querying of datasets. 

 

Availability and Implementation:mzML2ISA & nmrML2ISA are available under version 3 of the GNU General Public Licence at https://github.com/ISA-tools . Documentation is available from http://2isa.readthedocs.io/en/latest/ . 

 Contact:reza.salek@ebi.ac.uk or isatools@googlegroups.com. 

 

Supplementary information:Supplementary data are available at Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Willighagen:2017ge,

title = {The Chemistry Development Kit (CDK) v2.0: atom typing, depiction, molecular formulas, and substructure searching},

author = {Willighagen, Egon L and Mayfield, John W and Alvarsson, Jonathan and Berg, Arvid and Carlsson, Lars and Jeliazkova, Nina and Kuhn, Stefan and Pluskal, Tomás and Rojas-Chertó, Miquel and Spjuth, Ola and Torrance, Gilleain and Evelo, Chris T and Guha, Rajarshi and Steinbeck, Christoph},

url = {https://jcheminf.springeropen.com/articles/10.1186/s13321-017-0220-4},

doi = {10.1186/s13321-017-0220-4},

year  = {2017},

date = {2017-01-01},

journal = {Journal of cheminformatics},

volume = {9},

number = {1},

pages = {33},

publisher = {Springer International Publishing},

abstract = {The Chemistry Development Kit (CDK) is a widely used open source cheminformatics toolkit, providing data structures to represent chemical concepts along with methods to manipulate such structures and perform computations on them. The library implements a wide variety of cheminformatics algorithms ranging from chemical structure canonicalization to molecular descriptor calculations and pharmacophore perception. It is used in drug discovery, metabolomics, and toxicology. Over the last 10~years, the code base has grown significantly, however, resulting in many complex interdependencies among components and poor performance of many algorithms. We report improvements to the CDK v2.0 since the v1.2 release series, specifically addressing the increased functional complexity and poor performance. We first summarize the addition of new functionality, such atom typing and molecular formula handling, and improvement to existing functionality that has led to significantly better performance for substructure searching, molecular fingerprints, and rendering of molecules. Second, we outline how the CDK has evolved with respect to quality control and the approaches we have adopted to ensure stability, including a code review mechanism. This paper highlights our continued efforts to provide a community driven, open source cheminformatics library, and shows that such collaborative projects can thrive over extended periods of time, resulting in a high-quality and performant library. By taking advantage of community support and contributions, we show that an open source cheminformatics project can act as a peer reviewed publishing platform for scientific computing software.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Weber:2017fga,

title = {Computational tools and workflows in metabolomics: An international survey highlights the opportunity for harmonisation through Galaxy.},

author = {Weber, Ralf J M and Lawson, Thomas N and Salek, Reza M and Ebbels, Timothy M D and Glen, Robert C and Goodacre, Royston and Griffin, Julian L and Haug, Kenneth and Koulman, Albert and Moreno, Pablo and Ralser, Markus and Steinbeck, Christoph and Dunn, Warwick B and Viant, Mark R},

url = {http://link.springer.com/10.1007/s11306-016-1147-x},

doi = {10.1007/s11306-016-1147-x},

year  = {2017},

date = {2017-01-01},

journal = {Metabolomics},

volume = {13},

number = {2},

pages = {12},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Salek:2017ex,

title = {Automated Assembly of Species Metabolomes through Data Submission into a Public Repository},

author = {Reza M Salek and Pablo Conesa and Keeva Cochrane and Kenneth Haug and Mark Williams and Namrata Kale and Pablo Moreno and Kalai Jayaseelan and Jose Ramon Macias and Venkata Chandrasekhar Nainala and Robert D Hall and Laura K Reed and Mark R Viant and Claire O'Donovan and Christoph Steinbeck},

url = {https://academic.oup.com/gigascience/article-lookup/doi/10.1093/gigascience/gix062},

doi = {10.1093/gigascience/gix062},

year  = {2017},

date = {2017-01-01},

journal = {GigaScience},

abstract = {Following similar global efforts to exchange genomic and other biomedical data, global databases in metabolomics have now been established. MetaboLights, the first general purpose, publically available, cross-species, cross-application database in metabolomics, has become the fastest growing data repository at the European Bioinformatics Institute in terms of data volume. Here we present the automated assembly of species metabolomes in MetaboLights, a crucial reference for chemical biology, which is growing through user submissions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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{Beisken:2014fxa,

title = {Metabolic differences in ripening of Solanum lycopersicum textquoteleftAilsa Craigtextquoteright and three monogenic mutants},

author = {Beisken, Stephan and Earll, Mark and Baxter, Charles and Portwood, David and Ament, Zsuzsanna and Kende, Aniko and Hodgman, Charlie and Seymour, Graham and Smith, Rebecca and Fraser, Paul and Seymour, Mark and Salek, Reza M and Steinbeck, Christoph},

url = {http://www.nature.com/articles/sdata201429},

doi = {10.1038/sdata.2014.29},

year  = {2014},

date = {2014-09-01},

journal = {Scientific Data},

volume = {1},

pages = {140029},

publisher = {The Author(s) SN -},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Beisken:2014ie,

title = {MassCascade: Visual Programming for LC-MS Data Processing in Metabolomics.},

author = {Beisken, Stephan and Earll, Mark and Portwood, David and Seymour, Mark and Steinbeck, Christoph},

url = {http://onlinelibrary.wiley.com/doi/10.1002/minf.201400016/full},

doi = {10.1002/minf.201400016},

year  = {2014},

date = {2014-04-01},

journal = {Molecular Informatics},

volume = {33},

number = {4},

pages = {307--310},

publisher = {WILEY-VCH Verlag},

abstract = {Liquid chromatography coupled to mass spectrometry (LC-MS) is commonly applied to investigate the small molecule complement of organisms. Several software tools are typically joined in custom pipelines to semi-automatically process and analyse the resulting data. General workflow environments like the Konstanz Information Miner (KNIME) offer the potential of an all-in-one solution to process LC-MS data by allowing easy integration of different tools and scripts. We describe MassCascade and its workflow plug-in for processing LC-MS data. The Java library integrates frequently used algorithms in a modular fashion, thus enabling it to serve as back-end for graphical front-ends. The functions available in MassCascade have been encapsulated in a plug-in for the workflow environment KNIME, allowing combined use with e.g. statistical workflow nodes from other providers and making the tool intuitive to use without knowledge of programming. The design of the software guarantees a high level of modularity where processing functions can be quickly replaced or concatenated. MassCascade is an open-source library for LC-MS data processing in metabolomics. It embraces the concept of visual programming through its KNIME plug-in, simplifying the process of building complex workflows. The library was validated using open data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rueedi:2014ej,

title = {Genome-wide association study of metabolic traits reveals novel gene-metabolite-disease links.},

author = {Rueedi, Rico and Ledda, Mirko and Nicholls, Andrew W and Salek, Reza M and Marques-Vidal, Pedro and Morya, Edgard and Sameshima, Koichi and Montoliu, Ivan and Da Silva, Laeticia and Collino, Sebastiano and Martin, Fran{c c}ois-Pierre and Rezzi, Serge and Steinbeck, Christoph and Waterworth, Dawn M and Waeber, G{'e}rard and Vollenweider, Peter and Beckmann, Jacques S and Le Coutre, Johannes and Mooser, Vincent and Bergmann, Sven and Genick, Ulrich K and Kutalik, Zolt{'a}n},

url = {http://dx.plos.org/10.1371/journal.pgen.1004132},

doi = {10.1371/journal.pgen.1004132},

year  = {2014},

date = {2014-02-01},

journal = {PLoS Genetics},

volume = {10},

number = {2},

pages = {e1004132},

publisher = {Public Library of Science},

abstract = {Metabolic traits are molecular phenotypes that can drive clinical phenotypes and may predict disease progression. Here, we report results from a metabolome- and genome-wide association study on (1)H-NMR urine metabolic profiles. The study was conducted within an untargeted approach, employing a novel method for compound identification. From our discovery cohort of 835 Caucasian individuals who participated in the CoLaus study, we identified 139 suggestively significant (P<5texttimes10(-8)) and independent associations between single nucleotide polymorphisms (SNP) and metabolome features. Fifty-six of these associations replicated in the TasteSensomics cohort, comprising 601 individuals from S~ao Paulo of vastly diverse ethnic background. They correspond to eleven gene-metabolite associations, six of which had been previously identified in the urine metabolome and three in the serum metabolome. Our key novel findings are the associations of two SNPs with NMR spectral signatures pointing to fucose (rs492602, P = 6.9texttimes10(-44)) and lysine (rs8101881, P = 1.2texttimes10(-33)), respectively. Fine-mapping of the first locus pinpointed the FUT2 gene, which encodes a fucosyltransferase enzyme and has previously been associated with Crohn's disease. This implicates fucose as a potential prognostic disease marker, for which there is already published evidence from a mouse model. The second SNP lies within the SLC7A9 gene, rare mutations of which have been linked to severe kidney damage. The replication of previous associations and our new discoveries demonstrate the potential of untargeted metabolomics GWAS to robustly identify molecular disease markers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Truszkowski:2014gd,

title = {A molecular fragment cheminformatics roadmap for mesoscopic simulation.},

author = {Truszkowski, Andreas and Daniel, Mirco and Kuhn, Hubert and Neumann, Stefan and Steinbeck, Christoph and Zielesny, Achim and Epple, Matthias},

url = {http://www.jcheminf.com/content/6/1/45},

doi = {10.1186/s13321-014-0045-3},

year  = {2014},

date = {2014-01-01},

journal = {Journal of cheminformatics},

volume = {6},

number = {1},

pages = {45},

publisher = {Springer International Publishing},

abstract = {BACKGROUND:Mesoscopic simulation studies the structure, dynamics and properties of large molecular ensembles with millions of atoms: Its basic interacting units (beads) are no longer the nuclei and electrons of quantum chemical ab-initio calculations or the atom types of molecular mechanics but molecular fragments, molecules or even larger molecular entities. For its simulation setup and output a mesoscopic simulation kernel software uses abstract matrix (array) representations for bead topology and connectivity. Therefore a pure kernel-based mesoscopic simulation task is a tedious, time-consuming and error-prone venture that limits its practical use and application. A consequent cheminformatics approach tackles these problems and provides solutions for a considerably enhanced accessibility. This study aims at outlining a complete cheminformatics roadmap that frames a mesoscopic Molecular Fragment Dynamics (MFD) simulation kernel to allow its efficient use and practical application. 

 

RESULTS:The molecular fragment cheminformatics roadmap consists of four consecutive building blocks: An adequate fragment structure representation (1), defined operations on these fragment structures (2), the description of compartments with defined compositions and structural alignments (3), and the graphical setup and analysis of a whole simulation box (4). The basis of the cheminformatics approach (i.e. building block 1) is a SMILES-like line notation (denoted fSMILES) with connected molecular fragments to represent a molecular structure. The fSMILES notation and the following concepts and methods for building blocks 2-4 are outlined with examples and practical usage scenarios. It is shown that the requirements of the roadmap may be partly covered by already existing open-source cheminformatics software. 

 

CONCLUSIONS:Mesoscopic simulation techniques like MFD may be considerably alleviated and broadened for practical use with a consequent cheminformatics layer that successfully tackles its setup subtleties and conceptual usage hurdles. Molecular Fragment Cheminformatics may be regarded as a crucial accelerator to propagate MFD and similar mesoscopic simulation techniques in the molecular sciences. Graphical abstractA molecular fragment cheminformatics roadmap for mesoscopic simulation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Jayaseelan:2014im,

title = {Building blocks for automated elucidation of metabolites: natural product-likeness for candidate ranking.},

author = {Jayaseelan, Kalai Vanii and Steinbeck, Christoph},

url = {http://www.biomedcentral.com/1471-2105/15/234},

doi = {10.1186/1471-2105-15-234},

year  = {2014},

date = {2014-01-01},

journal = {BMC Bioinformatics},

volume = {15},

number = {1},

pages = {234},

publisher = {BioMed Central Ltd},

abstract = {BACKGROUND:In metabolomics experiments, spectral fingerprints of metabolites with no known structural identityare detected routinely. Computer-assisted structure elucidation (CASE) has been used to determine thestructural identities of unknown compounds. It is generally accepted that a single 1D NMR spectrumor mass spectrum is usually not sufficient to establish the identity of a hitherto unknown compound.When a suite of spectra from 1D and 2D NMR experiments supplemented with a molecular formulaare available, the successful elucidation of the chemical structure for candidates with up to 30 heavyatoms has been reported previously by one of the authors. In high-throughput metabolomics, usually1D NMR or mass spectrometry experiments alone are conducted for rapid analysis of samples. Thismethod subsequently requires that the spectral patterns are analyzed automatically to quickly identifyknown and unknown structures. In this study, we investigated whether additional existing knowledge,such as the fact that the unknown compound is a natural product, can be used to improve the rankingof the correct structure in the result list after the structure elucidation process. 

 

RESULTS:To identify unknowns using as little spectroscopic information as possible, we implemented anevolutionary algorithm-based CASE mechanism to elucidate candidates in a fully automated fashion,with input of the molecular formula and 13C NMR spectrum of the isolated compound. Wealso tested how filters like natural product-likeness, a measure that calculates the similarity ofthe compounds to known natural product space, might enhance the performance and quality ofthe structure elucidation. The evolutionary algorithm is implemented within the SENECA packagefor CASE reported previously, and is available for free download under artistic license athttp://sourceforge.net/projects/seneca/. The natural product-likeness calculator is incorporated as aplugin within SENECA and is available as a GUI client and command-line executable. Significantimprovements in candidate ranking were demonstrated for 41 small test molecules when the CASEsystem was supplemented by a natural product-likeness filter. 

 

CONCLUSIONS:In spectroscopically underdetermined structure elucidation problems, natural product-likeness cancontribute to a better ranking of the correct structure in the results list.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tipton:2014hp,

title = {Standards for Reporting Enzyme Data: The STRENDA Consortium: What it aims to do and why it should be helpful},

author = {Tipton, Keith F and Armstrong, Richard N and Bakker, Barbara M and Bairoch, Amos and Cornish-Bowden, Athel and Halling, Peter J and Hofmeyr, Jan-Hendrik and Leyh, Thomas S and Kettner, Carsten and Raushel, Frank M and Rohwer, Johann and Schomburg, Dietmar and Steinbeck, Christoph},

url = {http://linkinghub.elsevier.com/retrieve/pii/S2213020914000135},

doi = {10.1016/j.pisc.2014.02.012},

year  = {2014},

date = {2014-01-01},

journal = {Perspectives in Science},

volume = {1},

number = {1-6},

pages = {131--137},

abstract = {Abstract Data on enzyme activities and kinetics have often been reported with insufficient experimental detail to allow their repetition. This paper discusses the objectives and recommendations of the Standards for Reporting Enzyme Data ( STRENDA ) project to ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2014fa,

title = {Ten recommendations for software engineering in research.},

author = {Hastings, Janna and Haug, Kenneth and Steinbeck, Christoph},

url = {http://www.gigasciencejournal.com/content/3/1/31},

doi = {10.1186/2047-217X-3-31},

year  = {2014},

date = {2014-01-01},

journal = {GigaScience},

volume = {3},

number = {1},

pages = {31},

publisher = {BioMed Central},

abstract = {Research in the context of data-driven science requires a backbone of well-written software, but scientific researchers are typically not trained at length in software engineering, the principles for creating better software products. To address this gap, in particular for young researchers new to programming, we give ten recommendations to ensure the usability, sustainability and practicality of research software.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Efficientringperce:2014hg,

title = {Efficient ring perception for the Chemistry Development Kit.},

author = {May, John W and Steinbeck, Christoph},

url = {http://www.jcheminf.com/content/6/1/3/abstract},

doi = {10.1186/1758-2946-6-3},

year  = {2014},

date = {2014-01-01},

journal = {Journal of cheminformatics},

volume = {6},

number = {1},

pages = {3},

publisher = {Chemistry Central Ltd},

abstract = {BACKGROUND:The Chemistry Development Kit (CDK) is an open source Java library for manipulating and processing chemical information. A key aspect in handling chemical structures is the determination of the chemical rings. The rings of a structure are used areas including descriptors, stereochemistry, similarity, screening and atom typing. The CDK includes multiple algorithms for determining the rings of a structure on demand. Non-unique descriptions of rings were often used due to the slower performance of the unique alternatives. 

 

RESULTS:Efficient algorithms for handling chemical ring perception have been implemented and optimised in the CDK. The algorithms provide much faster computation of new and existing types of rings. Several optimisation and implementation considerations are discussed which improve real case usage. The performance is measured on several publicly available data sets and in several cases the new implementations were found to be more than an order of magnitude faster. 

 

CONCLUSIONS:Algorithmic improvements allow handling of much larger datasets in reasonable time. Faster computation allows more appropriate rings to be utilised in procedures such as aromaticity. Several areas that require ring perception have also seen a noticeable improvement. The time taken to compute the unique rings is now comparable allowing a correct usage throughout the toolkit. All source code is open source and freely available.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Venkata:2014cq,

title = {The potential utility of predicted one bond carbon-proton coupling constants in the structure elucidation of small organic molecules by NMR spectroscopy.},

author = {Venkata, Chandrasekhar and Forster, Mark J and Howe, Peter W A and Steinbeck, Christoph},

url = {http://dx.plos.org/10.1371/journal.pone.0111576},

doi = {10.1371/journal.pone.0111576},

year  = {2014},

date = {2014-01-01},

journal = {PLoS ONE},

volume = {9},

number = {11},

pages = {e111576},

publisher = {Public Library of Science},

abstract = {NMR spectroscopy is the most popular technique used for structure elucidation of small organic molecules in solution, but incorrect structures are regularly reported. One-bond proton-carbon J-couplings provide additional information about chemical structure because they are determined by different features of molecular structure than are proton and carbon chemical shifts. However, these couplings are not routinely used to validate proposed structures because few software tools exist to predict them. This study assesses the accuracy of Density Functional Theory for predicting them using 396 published experimental observations from a diverse range of small organic molecules. With the B3LYP functional and the TZVP basis set, Density Functional Theory calculations using the open-source software package NWChem can predict one-bond CH J-couplings with good accuracy for most classes of small organic molecule. The root-mean-square deviation after correction is 1.5 Hz for most sp3 CH pairs and 1.9 Hz for sp2 pairs; larger errors are observed for sp3 pairs with multiple electronegative substituents and for sp pairs. These results suggest that prediction of one-bond CH J-couplings by Density Functional Theory is sufficiently accurate for structure validation. This will be of particular use in strained ring systems and heterocycles which have characteristic couplings and which pose challenges for structure elucidation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}