@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}

}

@article{Foster:2013bc,

title = {LipidHome: a database of theoretical lipids optimized for high throughput mass spectrometry lipidomics.},

author = {Foster, Joseph M and Moreno, Pablo and Fabregat, Antonio and Hermjakob, Henning and Steinbeck, Christoph and Apweiler, Rolf and Wakelam, Michael J O and Vizca{'i}no, Juan Antonio},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=23667450&retmode=ref&cmd=prlinks},

doi = {10.1371/journal.pone.0061951},

year  = {2013},

date = {2013-01-01},

journal = {PLoS ONE},

volume = {8},

number = {5},

pages = {e61951},

abstract = {Protein sequence databases are the pillar upon which modern proteomics is supported, representing a stable reference space of predicted and validated proteins. One example of such resources is UniProt, enriched with both expertly curated and automatic annotations. Taken largely for granted, similar mature resources such as UniProt are not available yet in some other "omics" fields, lipidomics being one of them. While having a seasoned community of wet lab scientists, lipidomics lies significantly behind proteomics in the adoption of data standards and other core bioinformatics concepts. This work aims to reduce the gap by developing an equivalent resource to UniProt called 'LipidHome', providing theoretically generated lipid molecules and useful metadata. Using the 'FASTLipid' Java library, a database was populated with theoretical lipids, generated from a set of community agreed upon chemical bounds. In parallel, a web application was developed to present the information and provide computational access via a web service. Designed specifically to accommodate high throughput mass spectrometry based approaches, lipids are organised into a hierarchy that reflects the variety in the structural resolution of lipid identifications. Additionally, cross-references to other lipid related resources and papers that cite specific lipids were used to annotate lipid records. The web application encompasses a browser for viewing lipid records and a 'tools' section where an MS1 search engine is currently implemented. LipidHome can be accessed at http://www.ebi.ac.uk/apweiler-srv/lipidhome.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DeMatos:2013jp,

title = {The Enzyme Portal: A case study in applying user-centred design methods in bioinformatics},

author = {De Matos, Paula and Cham, Jennifer A and Cao, Hong and Alcantara, Rafael and Rowland, Francis and Lopez, Rodrigo and Steinbeck, Christoph},

url = {http://www.biomedcentral.com/1471-2105/14/103},

doi = {10.1186/1471-2105-14-103},

year  = {2013},

date = {2013-01-01},

journal = {BMC Bioinformatics},

volume = {14},

number = {1},

pages = {103},

publisher = {BioMed Central Ltd},

abstract = {User-centred design (UCD) is a type of user interface design in which the needs and desires of users are taken into account at each stage of the design process for a service or product; often for software applications and websites. Its goal is to facilitate the design of software that is both useful and easy to use. To achieve this, you must characterise users' requirements, design suitable interactions to meet their needs, and test your designs using prototypes and real life scenarios.For bioinformatics, there is little practical information available regarding how to carry out UCD in practice. To address this we describe a complete, multi-stage UCD process used for creating a new bioinformatics resource for integrating enzyme information, called the Enzyme Portal (http://www.ebi.ac.uk/enzymeportal). This freely-available service mines and displays data about proteins with enzymatic activity from public repositories via a single search, and includes biochemical reactions, biological pathways, small molecule chemistry, disease information, 3D protein structures and relevant scientific literature.We employed several UCD techniques, including: persona development, interviews, 'canvas sort' card sorting, user workflows, usability testing and others. Our hope is that this case study will motivate the reader to apply similar UCD approaches to their own software design for bioinformatics. Indeed, we found the benefits included more effective decision-making for design ideas and technologies; enhanced team-working and communication; cost effectiveness; and ultimately a service that more closely meets the needs of our target audience.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Markley:2012jf,

title = {In support of the BMRB.},

author = {Markley, John L and Akutsu, Hideo and Asakura, Tetsuo and Baldus, Marc and Boelens, Rolf and Bonvin, Alexandre and Kaptein, Robert and Bax, Ad and Bezsonova, Irina and Gryk, Michael R and Hoch, Jeffrey C and Korzhnev, Dmitry M and Maciejewski, Mark W and Case, Dave and Chazin, Walter J and Cross, Timothy A and Dames, Sonja and Kessler, Horst and Lange, Oliver and Madl, Tobias and Reif, Bernd and Sattler, Michael and Eliezer, David and Fersht, Alan and Forman-Kay, Julie and Kay, Lewis E and Fraser, James and Gross, John and Kortemme, Tanja and Sali, Andrej and Fujiwara, Toshimichi and Gardner, Kevin and Luo, Xuelian and Rizo-Rey, Jose and Rosen, Michael and Gil, Roberto R and Ho, Chien and Rule, Gordon and Gronenborn, Angela M and Ishima, Rieko and Klein-Seetharaman, Judith and Tang, Pei and van der Wel, Patrick and Xu, Yan and Grzesiek, Stephan and Hiller, Sebastian and Seelig, Joachim and Laue, Ernest D and Mott, Helen and Nietlispach, Daniel and Barsukov, Igor and Lian, Lu-Yun and Middleton, David and Blumenschein, Tharin and Moore, Geoffrey and Campbell, Iain and Schnell, Jason and Vakonakis, Ioannis John and Watts, Anthony and Conte, Maria R and Mason, James and Pfuhl, Mark and Sanderson, Mark R and Craven, Jeremy and Williamson, Michael and Dominguez, Cyril and Roberts, Gordon and G{ü}nther, Ulrich and Overduin, Michael and Werner, Joern and Williamson, Philip and Blindauer, Claudia and Crump, Matthew and Driscoll, Paul and Frenkiel, Tom and Golovanov, Alexander and Matthews, Steve and Parkinson, John and Uhrin, Dusan and Williams, Mark and Neuhaus, David and Oschkinat, Hartmut and Ramos, Andres and Shaw, David E and Steinbeck, Christoph and Vendruscolo, Michele and Vuister, Geerten W and Walters, Kylie J and Weinstein, Harel and W{ü}thrich, Kurt and Yokoyama, Shigeyuki},

url = {http://www.nature.com/doifinder/10.1038/nsmb.2371},

doi = {10.1038/nsmb.2371},

year  = {2012},

date = {2012-09-01},

journal = {Nature structural & molecular biology},

volume = {19},

number = {9},

pages = {854--860},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2012metabolights,

title = {MetaboLights: towards a new COSMOS of metabolomics data management},

author = {Steinbeck, Christoph and Conesa, Pablo and Haug, Kenneth and Mahendraker, Tejasvi and Williams, Mark and Maguire, Eamonn and Rocca-Serra, Philippe and Sansone, Susanna-Assunta and Salek, Reza M and Griffin, Julian L},

url = {http://www.springerlink.com/index/10.1007/s11306-012-0462-0},

doi = {10.1007/s11306-012-0462-0},

year  = {2012},

date = {2012-09-01},

journal = {Metabolomics},

volume = {8},

number = {5},

pages = {757--760},

abstract = {Exciting funding initiatives are emerging in Europe and the US for metabolomics data production, storage, dissemination and analysis. This is based on a rich ecosystem of resources around the world, which has been build during the past ten years, including but not limited to resources such as MassBank in Japan and the Human Metabolome Database in Canada. Now, the European Bioinformatics Institute has launched MetaboLights, a database for metabolomics experiments and the associated metadata (http://www.ebi.ac.uk/metabolights). It is the first comprehensive, cross-species, cross-platform metabolomics database maintained by one of the major open access data providers in molecular biology. In October, the European COSMOS consortium will start its work on Metabolomics data standardization, publication and dissemination workflows. The NIH in the US is establishing 6-8 metabolomics services cores as well as a national metabolomics repository. This communication reports about MetaboLights as a new resource for Metabolomics research, summarises the related developments and outlines how they may consolidate the knowledge management in this third large omics field next to proteomics and genomics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pavelin2012bioinformatics,

title = {Bioinformatics Meets User-Centred Design: A Perspective},

author = {Pavelin, Katrina and Cham, Jennifer A and De Matos, Paula and Brooksbank, Cath and Cameron, Graham and Steinbeck, Christoph},

url = {http://dx.plos.org/10.1371/journal.pcbi.1002554.pdf},

doi = {10.1371/journal.pcbi.1002554},

year  = {2012},

date = {2012-07-01},

journal = {PLoS Computational Biology},

volume = {8},

number = {7},

pages = {e1002554},

publisher = {Public Library of Science},

abstract = {Designers have a saying that "the joy of an early release lasts but a short time. The bitterness of an unusable system lasts for years." It is indeed disappointing to discover that your data resources are not being used to their full potential. Not only have you invested your time, effort, and research grant on the project, but you may face costly redesigns if you want to improve the system later. This scenario would be less likely if the product was designed to provide users with exactly what they need, so that it is fit for purpose before its launch. We work at EMBL-European Bioinformatics Institute (EMBL-EBI), and we consult extensively with life science researchers to find out what they need from biological data resources. We have found that although users believe that the bioinformatics community is providing accurate and valuable data, they often find the interfaces to these resources tricky to use and navigate. We believe that if you can find out what your users want even before you create the first mock-up of a system, the final product will provide a better user experience. This would encourage more people to use the resource and they would have greater access to the data, which could ultimately lead to more scientific discoveries. In this paper, we explore the need for a user-centred design (UCD) strategy when designing bioinformatics resources and illustrate this with examples from our work at EMBL-EBI. Our aim is to introduce the reader to how selected UCD techniques may be successfully applied to software design for bioinformatics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sansone2012toward,

title = {Toward interoperable bioscience data},

author = {Sansone, Susanna-Assunta and Rocca-Serra, Philippe and Field, Dawn and Maguire, Eamonn and Taylor, Chris and Hofmann, Oliver and Fang, Hong and Neumann, Steffen and Tong, Weida and Amaral-Zettler, Linda and Begley, Kimberly and Booth, Tim and Bougueleret, Lydie and Burns, Gully and Chapman, Brad and Clark, Tim and Coleman, Lee-Ann and Copeland, Jay and Das, Sudeshna and de Daruvar, Antoine and De Matos, Paula and Dix, Ian and Edmunds, Scott and Evelo, Chris T and Forster, Mark J and Gaudet, Pascale and Gilbert, Jack and Goble, Carole and Griffin, Julian L and Jacob, Daniel and Kleinjans, Jos and Harland, Lee and Haug, Kenneth and Hermjakob, Henning and Sui, Shannan J Ho and Laederach, Alain and Liang, Shaoguang and Marshall, Stephen and McGrath, Annette and Merrill, Emily and Reilly, Dorothy and Roux, Magali and Shamu, Caroline E and Shang, Catherine A and Steinbeck, Christoph and Trefethen, Anne and Williams-Jones, Bryn and Wolstencroft, Katherine and Xenarios, Ioannis and Hide, Winston},

url = {http://www.nature.com/doifinder/10.1038/ng.1054},

doi = {10.1038/ng.1054},

year  = {2012},

date = {2012-01-01},

journal = {Nat Genet},

volume = {44},

number = {2},

pages = {121--126},

publisher = {Nature Publishing Group},

abstract = {To make full use of research data, the bioscience community needs to adopt technologies and reward mechanisms that support interoperability and promote the growth of an open 'data commoning' culture. Here we describe the prerequisites for data commoning and present an established and growing ecosystem of solutions using the shared 'Investigation-Study-Assay' framework to support that vision.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{chepelev2012self,

title = {Self-organizing ontology of biochemically relevant small molecules.},

author = {Chepelev, Leonid L and Hastings, Janna and Ennis, Marcus and Steinbeck, Christoph and Dumontier, Michel},

url = {http://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-13-3},

doi = {10.1186/1471-2105-13-3},

year  = {2012},

date = {2012-01-01},

journal = {BMC Bioinformatics},

volume = {13},

number = {1},

pages = {3},

abstract = {BACKGROUND:The advent of high-throughput experimentation in biochemistry has led to the generation of vast amounts of chemical data, necessitating the development of novel analysis, characterization, and cataloguing techniques and tools. Recently, a movement to publically release such data has advanced biochemical structure-activity relationship research, while providing new challenges, the biggest being the curation, annotation, and classification of this information to facilitate useful biochemical pattern analysis. Unfortunately, the human resources currently employed by the organizations supporting these efforts (e.g. ChEBI) are expanding linearly, while new useful scientific information is being released in a seemingly exponential fashion. Compounding this, currently existing chemical classification and annotation systems are not amenable to automated classification, formal and transparent chemical class definition axiomatization, facile class redefinition, or novel class integration, thus further limiting chemical ontology growth by necessitating human involvement in curation. Clearly, there is a need for the automation of this process, especially for novel chemical entities of biological interest. 

 

RESULTS:To address this, we present a formal framework based on Semantic Web technologies for the automatic design of chemical ontology which can be used for automated classification of novel entities. We demonstrate the automatic self-assembly of a structure-based chemical ontology based on 60 MeSH and 40 ChEBI chemical classes. This ontology is then used to classify 200 compounds with an accuracy of 92.7%. We extend these structure-based classes with molecular feature information and demonstrate the utility of our framework for classification of functionally relevant chemicals. Finally, we discuss an iterative approach that we envision for future biochemical ontology development. 

 

CONCLUSIONS:We conclude that the proposed methodology can ease the burden of chemical data annotators and dramatically increase their productivity. We anticipate that the use of formal logic in our proposed framework will make chemical classification criteria more transparent to humans and machines alike and will thus facilitate predictive and integrative bioactivity model development.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2012structure,

title = {Structure-based classification and ontology in chemistry.},

author = {Hastings, Janna and Magka, Despoina and Batchelor, Colin and Duan, Lian and Stevens, Robert and Ennis, Marcus and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=22480202&retmode=ref&cmd=prlinks},

doi = {10.1186/1758-2946-4-8},

year  = {2012},

date = {2012-01-01},

journal = {Journal of cheminformatics},

volume = {4},

number = {1},

pages = {8},

abstract = {BACKGROUND:Recent years have seen an explosion in the availability of data in the chemistry domain. With this information explosion, however, retrieving relevant results from the available information, and organising those results, become even harder problems. Computational processing is essential to filter and organise the available resources so as to better facilitate the work of scientists. Ontologies encode expert domain knowledge in a hierarchically organised machine-processable format. One such ontology for the chemical domain is ChEBI. ChEBI provides a classification of chemicals based on their structural features and a role or activity-based classification. An example of a structure-based class is 'pentacyclic compound' (compounds containing five-ring structures), while an example of a role-based class is 'analgesic', since many different chemicals can act as analgesics without sharing structural features. Structure-based classification in chemistry exploits elegant regularities and symmetries in the underlying chemical domain. As yet, there has been neither a systematic analysis of the types of structural classification in use in chemistry nor a comparison to the capabilities of available technologies. RESULTS:We analyze the different categories of structural classes in chemistry, presenting a list of patterns for features found in class definitions. We compare these patterns of class definition to tools which allow for automation of hierarchy construction within cheminformatics and within logic-based ontology technology, going into detail in the latter case with respect to the expressive capabilities of the Web Ontology Language and recent extensions for modelling structured objects. Finally we discuss the relationships and interactions between cheminformatics approaches and logic-based approaches. CONCLUSION:Systems that perform intelligent reasoning tasks on chemistry data require a diverse set of underlying computational utilities including algorithmic, statistical and logic-based tools. For the task of automatic structure-based classification of chemical entities, essential to managing the vast swathes of chemical data being brought online, systems which are capable of hybrid reasoning combining several different approaches are crucial. We provide a thorough review of the available tools and methodologies, and identify areas of open research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{alcantara2012rhea,

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

author = {Alcantara, Rafael and Axelsen, Kristian B and Morgat, Anne and Belda, Eugeni and Coudert, Elisabeth and Bridge, Alan and Cao, Hong and De Matos, Paula and Ennis, Marcus and Turner, Steve and Owen, Gareth and Bougueleret, Lydie and Xenarios, Ioannis and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=22135291&retmode=ref&cmd=prlinks},

doi = {10.1093/nar/gkr1126},

year  = {2012},

date = {2012-01-01},

journal = {Nucleic Acids Research},

volume = {40},

number = {Database issue},

pages = {D754--60},

abstract = {Rhea (http://www.ebi.ac.uk/rhea) is a comprehensive resource of expert-curated biochemical reactions. Rhea provides a non-redundant set of chemical transformations for use in a broad spectrum of applications, including metabolic network reconstruction and pathway inference. Rhea includes enzyme-catalyzed reactions (covering the IUBMB Enzyme Nomenclature list), transport reactions and spontaneously occurring reactions. Rhea reactions are described using chemical species from the Chemical Entities of Biological Interest ontology (ChEBI) and are stoichiometrically balanced for mass and charge. They are extensively manually curated with links to source literature and other public resources on metabolism including enzyme and pathway databases. This cross-referencing facilitates the mapping and reconciliation of common reactions and compounds between distinct resources, which is a common first step in the reconstruction of genome scale metabolic networks and models.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Jayaseelan:2012ig,

title = {Natural product-likeness score revisited: an open-source, open-data implementation.},

author = {Jayaseelan, Kalai Vanii and Moreno, Pablo and Truszkowski, Andreas and Ertl, Peter and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=22607271&retmode=ref&cmd=prlinks},

doi = {10.1186/1471-2105-13-106},

year  = {2012},

date = {2012-01-01},

journal = {BMC Bioinformatics},

volume = {13},

number = {1},

pages = {106},

abstract = {BACKGROUND:Natural product-likeness of a molecule, i.e. similarity of this molecule to the structure space covered by natural products, is a useful criterion in screening compound libraries and in designing new lead compounds. A closed source implementation of a natural product-likeness score, that finds its application in virtual screening, library design and compound selection, has been previously reported by one of us. In this note, we report an open-source and open-data re-implementation of this scoring system, illustrate its efficiency in ranking small molecules for natural product likeness and discuss its potential applications. RESULTS:The Natural-Product-Likeness scoring system is implemented as Taverna 2.2 workflows, and is available under Creative Commons Attribution-Share Alike 3.0 Unported License at http://www.myexperiment.org/packs/183.html. It is also available for download as executable standalone java package from http://sourceforge.net/projects/np-likeness/under Academic Free License. CONCLUSIONS:Our open-source, open-data Natural-Product-Likeness scoring system can be used as a filter for metabolites in Computer Assisted Structure Elucidation or to select natural-product-like molecules from molecular libraries for the use as leads in drug discovery.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2012ft,

title = {Accessing and using chemical property databases.},

author = {Hastings, Janna and Josephs, Zara and Steinbeck, Christoph},

url = {http://link.springer.com/10.1007/978-1-62703-050-2_9},

doi = {10.1007/978-1-62703-050-2_9},

isbn = {978-1-62703-049-6},

year  = {2012},

date = {2012-01-01},

journal = {Methods in molecular biology (Clifton, N.J.)},

volume = {929},

number = {Chapter 9},

pages = {193--219},

publisher = {Humana Press},

address = {Totowa, NJ},

abstract = {Chemical compounds participate in all the processes of life. Understanding the complex interactions of small molecules such as metabolites and drugs and the biological macromolecules that consume and produce them is key to gaining a wider understanding in a systemic context. Chemical property databases collect information on the biological effects and physicochemical properties of chemical entities. Accessing and using such databases is key to understanding the chemistry of toxic molecules. In this chapter, we present methods to search, understand, download, and manipulate the wealth of information available in public chemical property databases, with particular focus on the database of Chemical Entities of Biological Interest (ChEBI).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{de2012database,

title = {A database for chemical proteomics: ChEBI.},

author = {De Matos, Paula and Adams, Nico and Hastings, Janna and Moreno, Pablo and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=22065232&retmode=ref&cmd=prlinks},

doi = {10.1007/978-1-61779-364-6_19},

isbn = {978-1-61779-363-9},

year  = {2012},

date = {2012-01-01},

journal = {Methods in molecular biology (Clifton, N.J.)},

volume = {803},

number = {Chapter 19},

pages = {273--296},

publisher = {Humana Press},

address = {Totowa, NJ},

abstract = {Chemical proteomics is concerned with the identification of protein targets interacting with small molecules. Hence, the availability of a high quality and free resource storing small molecules is essential for the future development of the field. The Chemical Entities of Biological Interest (ChEBI) database is one such database. The scope of ChEBI includes any constitutionally or isotopically distinct atom, molecule, ion, ion pair, radical, radical ion, complex, conformer, etc., identifiable as a separately distinguishable entity. These entities in question are either products of nature or synthetic products used to intervene in the processes of living organisms. In addition, ChEBI contains a chemical ontology which relates the small molecules with each other thereby making it easier for users to discover data. The ontology also describes the biological roles that the small molecules are active in. The ChEBI database also provides a central reference point in which to access a variety of bioinformatics data points such as pathways and their biochemical reactions; expression data; protein sequence and structures.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{orchard2011minimum,

title = {Minimum information about a bioactive entity (MIABE)},

author = {Orchard, Sandra and Al-Lazikani, Bissan and Bryant, Steve and Clark, Dominic and Calder, Elizabeth and Dix, Ian and Engkvist, Ola and Forster, Mark and Gaulton, Anna and Gilson, Michael and Glen, Robert and Grigorov, Martin and Hammond-Kosack, Kim and Harland, Lee and Hopkins, Andrew and Larminie, Christopher and Lynch, Nick and Mann, Romeena K and Murray-Rust, Peter and Lo Piparo, Elena and Southan, Christopher and Steinbeck, Christoph and Wishart, David and Hermjakob, Henning and Overington, John and Thornton, Janet},

url = {http://www.nature.com/doifinder/10.1038/nrd3503},

doi = {10.1038/nrd3503},

year  = {2011},

date = {2011-01-01},

journal = {Nature Reviews Drug Discovery},

volume = {10},

number = {9},

pages = {661--669},

publisher = {Nature Publishing Group},

abstract = {Bioactive molecules such as drugs, pesticides and food additives are produced in large numbers by many commercial and academic groups around the world. Enormous quantities of data are generated on the biological properties and quality of these molecules. Access to such data - both on licensed and commercially available compounds, and also on those that fail during development - is crucial for understanding how improved molecules could be developed. For example, computational analysis of aggregated data on molecules that are investigated in drug discovery programmes has led to a greater understanding of the properties of successful drugs. However, the information required to perform these analyses is rarely published, and when it is made available it is often missing crucial data or is in a format that is inappropriate for efficient data-mining. Here, we propose a solution: the definition of reporting guidelines for bioactive entities - the Minimum Information About a Bioactive Entity (MIABE) - which has been developed by representatives of pharmaceutical companies, data resource providers and academic groups.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2011hx,

title = {IOS Press Ebooks - Modularization Requirements in Bio-Ontologies: A Case Study of ChEbi},

author = {Hastings, J and Batchelor, C R and Steinbeck, C and Schulz, S},

url = {http://ebooks.iospress.nl/publication/6516},

doi = {10.3233/978-1-60750-799-4-63},

year  = {2011},

date = {2011-01-01},

journal = {WoMO},

abstract = {Abstract Bio-ontologies such as the Gene Ontology and ChEBI are characterized by large sizes and relatively low expressivity. However, ongoing efforts aim to increase the formalisation of these ontologies by adding full definitions (equivalent classes). This increase in complexity results in a decrease of performance for standard reasoning tasks. In this paper, we explore the contribution which modularization can play in the evolution of ...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Griffin:2011es,

title = {A Metadata description of the data in "A metabolomic comparison of urinary changes in type 2 diabetes in mouse, rat, and human.".},

author = {Griffin, Julian L and Atherton, Helen J and Steinbeck, Chris and Salek, Reza M},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=21801423&retmode=ref&cmd=prlinks},

doi = {10.1186/1756-0500-4-272},

year  = {2011},

date = {2011-01-01},

journal = {BMC Research Notes},

volume = {4},

number = {1},

pages = {272},

abstract = {BACKGROUND:Metabolomics is a rapidly developing functional genomic tool that has a wide range of applications in diverse fields in biology and medicine. However, unlike transcriptomics and proteomics there is currently no central repository for the depositing of data despite efforts by the Metabolomics Standard Initiative (MSI) to develop a standardised description of a metabolomic experiment. FINDINGS:In this manuscript we describe how the MSI description has been applied to a published dataset involving the identification of cross-species metabolic biomarkers associated with type II diabetes. The study describes sample collection of urine from mice, rats and human volunteers, and the subsequent acquisition of data by high resolution 1H NMR spectroscopy. The metadata is described to demonstrate how the MSI descriptions could be applied in a manuscript and the spectra have also been made available for the mouse and rat studies to allow others to process the data. CONCLUSIONS:The intention of this manuscript is to stimulate discussion as to whether the MSI description is sufficient to describe the metadata associated with metabolomic experiments and encourage others to make their data available to other researchers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2011s,

title = {Whattextquoterights in an textquoteleftis abouttextquoterightlink? Chemical diagrams and the IAO},

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

url = {http://www.google.de/search?client=safari&rls=10_7_4&q=Whats+in+an+is+aboutlink+Chemical+diagrams+and+the+IAO&ie=UTF-8&oe=UTF-8&redir_esc=&ei=Mvm5ULHuCKyL4gSDi4CoCg},

year  = {2011},

date = {2011-01-01},

journal = {Proceedings of the International Conference on Biomedical Ontology (ICBO2011), Buffalo, USA},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{o2011open,

title = {Open Data, Open Source and Open Standards in chemistry: The Blue Obelisk five years on.},

author = {O'Boyle, Noel M and Guha, Rajarshi and Willighagen, Egon L and Adams, Samuel E and Alvarsson, Jonathan and Bradley, Jean-Claude and Filippov, Igor V and Hanson, Robert M and Hanwell, Marcus D and Hutchison, Geoffrey R and James, Craig A and Jeliazkova, Nina and Lang, Andrew Sid and Langner, Karol M and Lonie, David C and Lowe, Daniel M and Pansanel, Jerome and Pavlov, Dmitry and Spjuth, Ola and Steinbeck, Christoph and Tenderholt, Adam L and Theisen, Kevin J and Murray-Rust, Peter},

url = {http://www.jcheminf.com/content/3/1/37},

doi = {10.1186/1758-2946-3-37},

year  = {2011},

date = {2011-01-01},

journal = {Journal of cheminformatics},

volume = {3},

number = {1},

pages = {37},

abstract = {BACKGROUND:The Blue Obelisk movement was established in 2005 as a response to the lack of Open Data, Open Standards and Open Source (ODOSOS) in chemistry. It aims to make it easier to carry out chemistry research by promoting interoperability between chemistry software, encouraging cooperation between Open Source developers, and developing community resources and Open Standards. RESULTS:This contribution looks back on the work carried out by the Blue Obelisk in the past 5 years and surveys progress and remaining challenges in the areas of Open Data, Open Standards, and Open Source in chemistry. CONCLUSIONS:We show that the Blue Obelisk has been very successful in bringing together researchers and developers with common interests in ODOSOS, leading to development of many useful resources freely available to the chemistry community.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{truszkowski2011new,

title = {New developments on the cheminformatics open workflow environment CDK-Taverna.},

author = {Truszkowski, Andreas and Jayaseelan, Kalai Vanii and Neumann, Stefan and Willighagen, Egon L and Zielesny, Achim and Steinbeck, Christoph},

url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=22166170&retmode=ref&cmd=prlinks},

doi = {10.1186/1758-2946-3-54},

year  = {2011},

date = {2011-01-01},

journal = {Journal of cheminformatics},

volume = {3},

number = {1},

pages = {54},

abstract = {BACKGROUND:The computational processing and analysis of small molecules is at heart of cheminformatics and structural bioinformatics and their application in e.g. metabolomics or drug discovery. Pipelining or workflow tools allow for the Legotexttrademark-like, graphical assembly of I/O modules and algorithms into a complex workflow which can be easily deployed, modified and tested without the hassle of implementing it into a monolithic application. The CDK-Taverna project aims at building a free open-source cheminformatics pipelining solution through combination of different open-source projects such as Taverna, the Chemistry Development Kit (CDK) or the Waikato Environment for Knowledge Analysis (WEKA). A first integrated version 1.0 of CDK-Taverna was recently released to the public. RESULTS:The CDK-Taverna project was migrated to the most up-to-date versions of its foundational software libraries with a complete re-engineering of its worker's architecture (version 2.0). 64-bit computing and multi-core usage by paralleled threads are now supported to allow for fast in-memory processing and analysis of large sets of molecules. Earlier deficiencies like workarounds for iterative data reading are removed. The combinatorial chemistry related reaction enumeration features are considerably enhanced. Additional functionality for calculating a natural product likeness score for small molecules is implemented to identify possible drug candidates. Finally the data analysis capabilities are extended with new workers that provide access to the open-source WEKA library for clustering and machine learning as well as training and test set partitioning. The new features are outlined with usage scenarios. CONCLUSIONS:CDK-Taverna 2.0 as an open-source cheminformatics workflow solution matured to become a freely available and increasingly powerful tool for the biosciences. The combination of the new CDK-Taverna worker family with the already available workflows developed by a lively Taverna community and published on myexperiment.org enables molecular scientists to quickly calculate, process and analyse molecular data as typically found in e.g. today's systems biology scenarios.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2011chemical,

title = {The chemical information ontology: provenance and disambiguation for chemical data on the biological semantic web.},

author = {Hastings, Janna and Chepelev, Leonid and Willighagen, Egon and Adams, Nico and Steinbeck, Christoph and Dumontier, Michel},

url = {http://dx.plos.org/10.1371/journal.pone.0025513.pdf},

doi = {10.1371/journal.pone.0025513},

year  = {2011},

date = {2011-01-01},

journal = {PLoS ONE},

volume = {6},

number = {10},

pages = {e25513},

abstract = {Cheminformatics is the application of informatics techniques to solve chemical problems in silico. There are many areas in biology where cheminformatics plays an important role in computational research, including metabolism, proteomics, and systems biology. One critical aspect in the application of cheminformatics in these fields is the accurate exchange of data, which is increasingly accomplished through the use of ontologies. Ontologies are formal representations of objects and their properties using a logic-based ontology language. Many such ontologies are currently being developed to represent objects across all the domains of science. Ontologies enable the definition, classification, and support for querying objects in a particular domain, enabling intelligent computer applications to be built which support the work of scientists both within the domain of interest and across interrelated neighbouring domains. Modern chemical research relies on computational techniques to filter and organise data to maximise research productivity. The objects which are manipulated in these algorithms and procedures, as well as the algorithms and procedures themselves, enjoy a kind of virtual life within computers. We will call these information entities. Here, we describe our work in developing an ontology of chemical information entities, with a primary focus on data-driven research and the integration of calculated properties (descriptors) of chemical entities within a semantic web context. Our ontology distinguishes algorithmic, or procedural information from declarative, or factual information, and renders of particular importance the annotation of provenance to calculated data. The Chemical Information Ontology is being developed as an open collaborative project. More details, together with a downloadable OWL file, are available at http://code.google.com/p/semanticchemistry/ (license: CC-BY-SA).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{apweiler2010large,

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

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

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

doi = {10.1038/nchembio.460},

year  = {2010},

date = {2010-11-01},

journal = {Nature Chemical Biology},

volume = {6},

number = {11},

pages = {785--785},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hastings:2010uk,

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

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

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

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

year  = {2010},

date = {2010-07-01},

pages = {257--270},

publisher = {IOS Press},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{griffin2010so,

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

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

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

doi = {10.1186/gm159},

year  = {2010},

date = {2010-01-01},

journal = {Genome medicine},

volume = {2},

number = {6},

pages = {38},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2010representing,

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

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

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

year  = {2010},

date = {2010-01-01},

journal = {CEUR Workshop Proceedings},

volume = {614},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kuhn2010cdk,

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

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

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

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

year  = {2010},

date = {2010-01-01},

journal = {BMC Bioinformatics},

volume = {11},

number = {1},

pages = {159},

publisher = {BioMed Central},

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

 

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

 

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{de2010chemical,

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

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

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

doi = {10.1093/nar/gkp886},

year  = {2010},

date = {2010-01-01},

journal = {Nucleic Acids Research},

volume = {38},

number = {Database issue},

pages = {D249--54},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hastings2010substance,

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

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

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

year  = {2010},

date = {2010-01-01},

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

pages = {9--10},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{batchelor2010ontological,

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

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

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

year  = {2010},

date = {2010-01-01},

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

pages = {271--284},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rijnbeek:2009jy,

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

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

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

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

year  = {2009},

date = {2009-01-01},

journal = {Journal of cheminformatics},

volume = {1},

number = {1},

pages = {17},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{spjuth2009bioclipse,

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

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

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

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

year  = {2009},

date = {2009-01-01},

journal = {BMC Bioinformatics},

volume = {10},

number = {1},

pages = {397},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Blinov:2008jf,

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

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

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

doi = {10.1021/ci700363r},

year  = {2008},

date = {2008-03-01},

journal = {Journal of Chemical Information and Modeling},

volume = {48},

number = {3},

pages = {550--555},

publisher = {American Chemical Society},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kuhn2008building,

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

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

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

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

year  = {2008},

date = {2008-01-01},

journal = {BMC Bioinformatics},

volume = {9},

number = {1},

pages = {400},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{blinov2008performance,

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

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

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

year  = {2008},

date = {2008-01-01},

journal = {Journal of Chemical Information and Modeling},

volume = {48},

number = {3},

pages = {550--555},

publisher = {ACS Publications},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kuhn2007chemical,

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

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

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

doi = {10.1021/ci600531a},

year  = {2007},

date = {2007-01-01},

journal = {Journal of Chemical Information and Modeling},

volume = {47},

number = {6},

pages = {2015--2034},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{spjuth2007bioclipse,

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

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

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

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

year  = {2007},

date = {2007-01-01},

journal = {BMC Bioinformatics},

volume = {8},

number = {1},

pages = {59},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{willighagen2007userscripts,

title = {Userscripts for the life sciences},

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

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

year  = {2007},

date = {2007-01-01},

journal = {BMC Bioinformatics},

volume = {8},

number = {1},

pages = {487},

publisher = {BioMed Central Ltd},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schenk:2007kha,

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

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

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

doi = {10.1002/anie.200702033},

year  = {2007},

date = {2007-01-01},

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

volume = {46},

number = {37},

pages = {7035--7038},

publisher = {WILEY-VCH Verlag},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2006recent,

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

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

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

doi = {10.2174/138161206777585274},

year  = {2006},

date = {2006-01-01},

journal = {Current pharmaceutical design},

volume = {12},

number = {17},

pages = {2111--2120},

publisher = {Bentham Science Publishers},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hoppe2006classification,

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

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

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

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

year  = {2006},

date = {2006-01-01},

journal = {Journal of Molecular Graphics & Modelling},

volume = {24},

number = {5},

pages = {328--340},

publisher = {Elsevier},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{guha2006blue,

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

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

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

doi = {10.1021/ci050400b},

year  = {2006},

date = {2006-01-01},

journal = {Journal of Chemical Information and Modeling},

volume = {46},

number = {3},

pages = {991--998},

publisher = {ACS Publications},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{NMRShiftDB2005,

title = {Eine offene NMR-Datenbank},

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

year  = {2005},

date = {2005-09-01},

journal = {Nachrichten Aus Der Chemie},

volume = {53},

pages = {1039--1040},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:2004do,

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

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

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

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

year  = {2004},

date = {2004-10-01},

journal = {Phytochemistry},

volume = {65},

number = {19},

pages = {2711--2717},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{steinbeck2004recent,

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

author = {Steinbeck, C},

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

year  = {2004},

date = {2004-01-01},

journal = {Natural Product Reports},

volume = {21},

number = {4},

pages = {512--518},

publisher = {Royal Society of Chemistry},

keywords = {},

pubstate = {published},

tppubtype = {article}

}