@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}

}

@article{Tudose:2013iea,

title = {OntoQuery: easy-to-use web-based OWL querying.},

author = {Tudose, Ilinca and Hastings, Janna and Muthukrishnan, Venkatesh and Owen, Gareth and Turner, Steve and Dekker, Adriano and Kale, Namrata and Ennis, Marcus and Steinbeck, Christoph},

url = {http://bioinformatics.oxfordjournals.org/cgi/doi/10.1093/bioinformatics/btt514},

doi = {10.1093/bioinformatics/btt514},

year  = {2013},

date = {2013-11-01},

journal = {Bioinformatics},

volume = {29},

number = {22},

pages = {2955--2957},

publisher = {Oxford University Press},

abstract = {SUMMARY:The Web Ontology Language (OWL) provides a sophisticated language for building complex domain ontologies and is widely used in bio-ontologies such as the Gene Ontology. The Prot'eg'e-OWL ontology editing tool provides a query facility that allows composition and execution of queries with the human-readable Manchester OWL syntax, with syntax checking and entity label lookup. No equivalent query facility such as the Prot'eg'e Description Logics (DL) query yet exists in web form. However, many users interact with bio-ontologies such as chemical entities of biological interest and the Gene Ontology using their online Web sites, within which DL-based querying functionality is not available. To address this gap, we introduce the OntoQuery web-based query utility. 

 

AVAILABILITY AND IMPLEMENTATION: The source code for this implementation together with instructions for installation is available at http://github.com/IlincaTudose/OntoQuery. OntoQuery software is fully compatible with all OWL-based ontologies and is available for download (CC-0 license). The ChEBI installation, ChEBI OntoQuery, is available at http://www.ebi.ac.uk/chebi/tools/ontoquery. 

 CONTACT:hastings@ebi.ac.uk.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{KNIMECDKWorkflow:2013fk,

title = {KNIME-CDK: Workflow-driven cheminformatics},

author = {Beisken, Stephan and Meinl, Thorsten and Wiswedel, Bernd and de Figueiredo, Luis F and Berthold, Michael and Steinbeck, Christoph},

url = {http://www.biomedcentral.com/1471-2105/14/257},

doi = {10.1186/1471-2105-14-257},

year  = {2013},

date = {2013-08-01},

journal = {BMC Bioinformatics},

volume = {14},

number = {1},

pages = {257},

publisher = {BioMed Central Ltd},

abstract = {Cheminformaticians have to routinely process and analyse libraries of small molecules. Among other things, that includes the standardization of molecules, calculation of various descriptors, visualisation of molecular structures, and downstream analysis. For this purpose, scientific workflow platforms such as the Konstanz Information Miner can be used if provided with the right plug-in. A workflow-based cheminformatics tool provides the advantage of ease-of-use and interoperability between complementary cheminformatics packages within the same framework, hence facilitating the analysis process.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Salek:2013gv,

title = {The role of reporting standards for metabolite annotation and identification in metabolomic studies},

author = {Salek, Reza M and Steinbeck, Christoph and Viant, Mark R and Goodacre, Royston and Dunn, Warwick B},

url = {http://www.gigasciencejournal.com/content/2/1/13},

doi = {10.1186/2047-217X-2-13},

year  = {2013},

date = {2013-01-01},

journal = {GigaScience},

volume = {2},

number = {1},

pages = {13},

publisher = {BioMed Central Ltd},

abstract = {The application of reporting standards in metabolomics allow data from different laboratories to be shared, integrated and interpreted. Although minimum reporting standards related to metabolite identification were published in 2007, it is clear that significant efforts are required to ensure their continuous update and appropriate use by the metabolomics community. These include their use in metabolomics data submission (e.g., MetaboLights) and as a requirement for publication in peer-reviewed journals (e.g., Metabolomics). The Data Standards and Metabolite Identification Task Groups of the international Metabolomics Society are actively working to develop and promote these standards and educate the community on their use.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{haug2012metabolights,

title = {MetaboLights--an open-access general-purpose repository for metabolomics studies and associated meta-data.},

author = {Haug, Kenneth and Salek, Reza M and Conesa, Pablo and Hastings, Janna and De Matos, Paula and Rijnbeek, Mark and Mahendraker, Tejasvi and Williams, Mark and Neumann, Steffen and Rocca-Serra, Philippe and Maguire, Eamonn and Gonz{'a}lez-Beltr{'a}n, Alejandra and Sansone, Susanna-Assunta and Griffin, Julian L and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=23109552&retmode=ref&cmd=prlinks},

doi = {10.1093/nar/gks1004},

year  = {2013},

date = {2013-01-01},

journal = {Nucleic Acids Research},

volume = {41},

number = {Database issue},

pages = {D781--6},

abstract = {MetaboLights (http://www.ebi.ac.uk/metabolights) is the first general-purpose, open-access repository for metabolomics studies, their raw experimental data and associated metadata, maintained by one of the major open-access data providers in molecular biology. Metabolomic profiling is an important tool for research into biological functioning and into the systemic perturbations caused by diseases, diet and the environment. The effectiveness of such methods depends on the availability of public open data across a broad range of experimental methods and conditions. The MetaboLights repository, powered by the open source ISA framework, is cross-species and cross-technique. It will cover metabolite structures and their reference spectra as well as their biological roles, locations, concentrations and raw data from metabolic experiments. Studies automatically receive a stable unique accession number that can be used as a publication reference (e.g. MTBLS1). At present, the repository includes 15 submitted studies, encompassing 93 protocols for 714 assays, and span over 8 different species including human, Caenorhabditis elegans, Mus musculus and Arabidopsis thaliana. Eight hundred twenty-seven of the metabolites identified in these studies have been mapped to ChEBI. These studies cover a variety of techniques, including NMR spectroscopy and mass spectrometry.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{alcantara2012ebi,

title = {The EBI enzyme portal.},

author = {Alcantara, Rafael and Onwubiko, Joseph and Cao, Hong and Matos, Paula de and Cham, Jennifer A and Jacobsen, Jules and Holliday, Gemma L and Fischer, Julia D and Rahman, Syed Asad and Jassal, Bijay and Goujon, Mikael and Rowland, Francis and Velankar, Sameer and Lopez, Rodrigo and Overington, John P and Kleywegt, Gerard J and Hermjakob, Henning and O'Donovan, Claire and Mart{'i}n, Mar{'i}a Jes{'u}s and Thornton, Janet M and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=23175605&retmode=ref&cmd=prlinks},

doi = {10.1093/nar/gks1112},

year  = {2013},

date = {2013-01-01},

journal = {Nucleic Acids Research},

volume = {41},

number = {Database issue},

pages = {D773--80},

abstract = {The availability of comprehensive information about enzymes plays an important role in answering questions relevant to interdisciplinary fields such as biochemistry, enzymology, biofuels, bioengineering and drug discovery. At the EMBL European Bioinformatics Institute, we have developed an enzyme portal (http://www.ebi.ac.uk/enzymeportal) to provide this wealth of information on enzymes from multiple in-house resources addressing particular data classes: protein sequence and structure, reactions, pathways and small molecules. The fact that these data reside in separate databases makes information discovery cumbersome. The main goal of the portal is to simplify this process for end users.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{May:2013kc,

title = {Metingear: a development environment for annotating genome-scale metabolic models.},

author = {May, John W and James, A Gordon and Steinbeck, Christoph},

url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btt342},

doi = {10.1093/bioinformatics/btt342},

year  = {2013},

date = {2013-01-01},

journal = {Bioinformatics},

volume = {29},

number = {17},

pages = {2213--2215},

abstract = {SUMMARY:Genome-scale metabolic models often lack annotations that would allow them to be used for further analysis. Previous efforts have focused on associating metabolites in the model with a cross reference, but this can be problematic if the reference is not freely available, multiple resources are used or the metabolite is added from a literature review. Associating each metabolite with chemical structure provides unambiguous identification of the components and a more detailed view of the metabolism. We have developed an open-source desktop application that simplifies the process of adding database cross references and chemical structures to genome-scale metabolic models. Annotated models can be exported to the Systems Biology Markup Language open interchange format. 

 

AVAILABILITY:Source code, binaries, documentation and tutorials are freely available at http://johnmay.github.com/metingear. The application is implemented in Java with bundles available for MS Windows and Macintosh OS X. 

 CONTACT:johnmay@ebi.ac.uk 

 

SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Salek:2013gja,

title = {Dissemination of metabolomics results: role of MetaboLights and COSMOS.},

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

url = {http://www.gigasciencejournal.com/content/2/1/8},

doi = {10.1186/2047-217X-2-8},

year  = {2013},

date = {2013-01-01},

journal = {GigaScience},

volume = {2},

number = {1},

pages = {8},

publisher = {BioMed Central},

abstract = {With ever-increasing amounts of metabolomics data produced each year, there is an even greater need to disseminate data and knowledge produced in a standard and reproducible way. To assist with this a general purpose, open source metabolomics repository, MetaboLights, was launched in 2012. To promote a community standard, initially culminated as metabolomics standards initiative (MSI), COordination of Standards in MetabOlomicS (COSMOS) was introduced. COSMOS aims to link life science e-infrastructures within the worldwide metabolomics community as well as develop and maintain open source exchange formats for raw and processed data, ensuring better flow of metabolomics information.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{RezaMSalek:2013bm,

title = {The MetaboLights repository: curation challenges in metabolomics},

author = {Salek, R M and Haug, K and Conesa, P and Hastings, J K and Williams, M and Steinbeck, C and Sansone, S A and Mahendraker, T and Maguire, E and Gonzalez-Beltran, A and Rocca-Serra, P},

url = {/pmc/articles/PMC3638156/?report=abstract},

doi = {10.1093/database/bat029},

year  = {2013},

date = {2013-01-01},

journal = {Database: The Journal of Biological Databases and Curation},

volume = {2013},

number = {0},

pages = {bat029--bat029},

publisher = {Oxford University Press},

abstract = {Abstract MetaboLights is the first general-purpose open-access curated repository for metabolomic studies, their raw experimental data and associated metadata, maintained by one of the major open-access data providers in molecular biology. Increases in the ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hill:2013gi,

title = {Dovetailing biology and chemistry: integrating the Gene Ontology with the ChEBI chemical ontology.},

author = {Hill, David P and Adams, Nico and Bada, Mike and Batchelor, Colin and Berardini, Tanya Z and Dietze, Heiko and Drabkin, Harold J and Ennis, Marcus and Foulger, Rebecca E and Harris, Midori A and Hastings, Janna and Kale, Namrata S and De Matos, Paula and Mungall, Christopher J and Owen, Gareth and Roncaglia, Paola and Steinbeck, Christoph and Turner, Steve and Lomax, Jane},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=23895341&retmode=ref&cmd=prlinks},

doi = {10.1186/1471-2164-14-513},

year  = {2013},

date = {2013-01-01},

journal = {BMC Genomics},

volume = {14},

number = {1},

pages = {513},

abstract = {BACKGROUND:The Gene Ontology (GO) facilitates the description of the action of gene products in a biological context. Many GO terms refer to chemical entities that participate in biological processes. To facilitate accurate and consistent systems-wide biological representation, it is necessary to integrate the chemical view of these entities with the biological view of GO functions and processes. We describe a collaborative effort between the GO and the Chemical Entities of Biological Interest (ChEBI) ontology developers to ensure that the representation of chemicals in the GO is both internally consistent and in alignment with the chemical expertise captured in ChEBI. RESULTS:We have examined and integrated the ChEBI structural hierarchy into the GO resource through computationally-assisted manual curation of both GO and ChEBI. Our work has resulted in the creation of computable definitions of GO terms that contain fully defined semantic relationships to corresponding chemical terms in ChEBI. CONCLUSIONS:The set of logical definitions using both the GO and ChEBI has already been used to automate aspects of GO development and has the potential to allow the integration of data across the domains of biology and chemistry. These logical definitions are available as an extended version of the ontology from http://purl.obolibrary.org/obo/go/extensions/go-plus.owl.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2012jx,

title = {The ChEBI reference database and ontology for biologically relevant chemistry: enhancements for 2013.},

author = {Hastings, Janna and De Matos, Paula and Dekker, Adriano and Ennis, Marcus and Harsha, Bhavana and Kale, Namrata and Muthukrishnan, Venkatesh and Owen, Gareth and Turner, Steve and Williams, Mark and Steinbeck, Christoph},

url = {http://nar.oxfordjournals.org/lookup/doi/10.1093/nar/gks1146},

doi = {10.1093/nar/gks1146},

year  = {2013},

date = {2013-01-01},

journal = {Nucleic Acids Research},

volume = {41},

number = {Database issue},

pages = {D456--63},

publisher = {Oxford University Press},

abstract = {ChEBI (http://www.ebi.ac.uk/chebi) is a database and ontology of chemical entities of biological interest. Over the past few years, ChEBI has continued to grow steadily in content, and has added several new features. In addition to incorporating all user-requested compounds, our annotation efforts have emphasized immunology, natural products and metabolites in many species. All database entries are now 'is_a' classified within the ontology, meaning that all of the chemicals are available to semantic reasoning tools that harness the classification hierarchy. We have completely aligned the ontology with the Open Biomedical Ontologies (OBO) Foundry-recommended upper level Basic Formal Ontology. Furthermore, we have aligned our chemical classification with the classification of chemical-involving processes in the Gene Ontology (GO), and as a result of this effort, the majority of chemical-involving processes in GO are now defined in terms of the ChEBI entities that participate in them. This effort necessitated incorporating many additional biologically relevant compounds. We have incorporated additional data types including reference citations, and the species and component for metabolites. Finally, our website and web services have had several enhancements, most notably the provision of a dynamic new interactive graph-based ontology visualization.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}