locations.bib

%% Saved with string encoding Unicode (UTF-8) 

@article{10.7717/peerj.933,
 title = {{GFVO}: the Genomic Feature and Variation Ontology},
 author = {Baran, Joachim and Durgahee, Bibi Sehnaaz Begum and Eilbeck, Karen and Antezana, Erick and Hoehndorf, Robert and Dumontier, Michel},
 year = {2015},
 month = {5},
 volume = {3},
 pages = {e933},
 journal = {PeerJ},
 issn = {2167-8359},
 url = {https://dx.doi.org/10.7717/peerj.933},
 doi = {10.7717/peerj.933}
}

@article{GVF,
	Author = {Martin G. Reese and Barry Moore and Colin Batchelor and Fidel Salas and Fiona Cunningham and Gabor T. Marth and Lincoln Stein and Paul Flicek and Mark Yandell and Karen Eilbeck},
	Title = {A standard variation file format for human genome sequences},
	Year = {2010},
	Journal = {Genome Biology},
	Volume = {11},
	Number = {R88},
	Doi = {10.1186/gb-2010-11-8-r88},
	Url = {http://dx.doi.org/10.1186/gb-2010-11-8-r88}}

@article{JBrowse,
	Author = {Mitchell E. Skinner and Andrew V. Uzilov and Lincoln D. Stein and Christopher J. Mungall and Ian H. Holmes},
	Title = {{JBrowse}: A next-generation genome browser},
	Year = {2009},
	Journal = {Genome Research},
	Volume = {19},
	Pages = {1630-1638},
	Doi = {10.1101/gr.094607.109},
	Url = {http://dx.doi.org/10.1101/gr.094607.109}}

@article{InterMine,
	author = {Richard N. Smith and Jelena Aleksic and Daniela Butano and Adrian Carr and Sergio Contrino and Fengyuan Hu and Mike Lyne and Rachel Lyne and Alex Kalderimis and Kim Rutherford and Radek Stepan and Julie Sullivan and Matthew Wakeling and Xavier Watkins and Gos Micklem},
	title = {{InterMine}: a flexible data warehouse system for the integration and analysis of heterogeneous biological data},
	journal = {Bioinformatics},
	year = {2012},
	volume = {28},
	number = {23},
	pages = {3163-3165},
	url = {http://dx.doi.org/10.1093/bioinformatics/bts577},
	doi = {10.1093/bioinformatics/bts577}}


@article{UniCarbKB,
	Author = {Campbell, M. P. and Peterson, R. and Mariethoz, J. and Gasteiger, E. and Akune, Y. and Aoki-Kinoshita, K. F. and Lisacek, F. and Packer, N. H.},
	Date-Added = {2013-10-22 15:12:45 +0000},
	Date-Modified = {2013-10-22 15:13:27 +0000},
	Journal = {Underconsideration for NAR Databases},
	Title = {UniCarbKB: Building a Knowledge Platform for Glycoproteomics},
	Year = {2014},
	url = {http://dx.doi.org/10.1093/nar/gkt1128},
	doi = {10.1093/nar/gkt1128}}

@article{doi:10.1021/ci100150d,
	Author = {Toukach, Philip V.},
	Date-Added = {2013-10-22 14:40:19 +0000},
	Date-Modified = {2013-10-22 14:40:19 +0000},
	Doi = {10.1021/ci100150d},
	Eprint = {http://pubs.acs.org/doi/pdf/10.1021/ci100150d},
	Journal = {Journal of Chemical Information and Modeling},
	Number = {1},
	Pages = {159-170},
	Title = {Bacterial Carbohydrate Structure Database 3: Principles and Realization},
	Url = {http://dx.doi.org/10.1021/ci100150d},
	Volume = {51},
	Year = {2011},
	Bdsk-Url-1 = {http://pubs.acs.org/doi/abs/10.1021/ci100150d},
	Bdsk-Url-2 = {http://dx.doi.org/10.1021/ci100150d}}

@article{RINGS,
	Abstract = {In the bioinformatics field, many computer algorithmic and data mining technologies have been developed for gene prediction, protein--protein interaction analysis, sequence analysis, and protein folding predictions, to name a few. This kind of research has branched off from the genomics field, creating the transcriptomics, proteomics, metabolomics, and glycomics research areas in the postgenomic age. In the glycomics field, given the complexity of glycan structures with their branches of monosaccharides in various conformations, new data mining and algorithmic methods have been developed in an attempt to gain a better understanding of glycans. However, these methods have not all been implemented as tools such that the glycobiology community may utilize them in their research. Thus, we have developed RINGS (Resource for INformatics of Glycomes at Soka) as a freely available Web resource for glycobiologists to analyze their data using the latest data mining and algorithmic techniques. It provides a number of tools including a 2D glycan drawing and querying interface called DrawRINGS, a Glycan Pathway Predictor (GPP) tool for dynamically computing the N-glycan biosynthesis pathway from a given glycan structure, and data mining tools Glycan Miner Tool and Profile PSTMM. These tools and other utilities provided by RINGS will be described. The URL for RINGS is http://rings.t.soka.ac.jp/.},
	Author = {Yukie Akune and Masae Hosoda and Sakiko Kaiya and Daisuke Shinmachi and Kiyoko F. Aoki-Kinoshita},
	Date-Added = {2013-10-22 14:38:58 +0000},
	Date-Modified = {2013-10-22 14:40:10 +0000},
	Journal = {OMICS: A Journal of Integrative Biology},
	Month = {August},
	Number = {4},
	Pages = {475-486},
	Title = {The {RINGS} Resource for Glycome Informatics Analysis and Data Mining on the Web},
	Volume = {14},
	Year = {2010},
	Url = {http://dx.doi.org/10.1089/omi.2009.0129},
	Doi = {10.1089/omi.2009.0129}}

@article{BioHack2011and2012,
	Author = {Toshiaki Katayama and Mark D. Wilkinson and Kiyoko F. Aoki-Kinoshita and Shuichi Kawashima and Yasunori Yamamoto and Atsuko Yamaguchi and Shinobu Okamoto and Shin Kawano and Jin-Dong Kim and Yue Wang and Hongyan Wu and Yoshinobu Kano and Hiromasa Ono and Hidemasa Bono and Simon Kocbek and Jan Aerts and Yukie Akune and Erick Antezana and Kazuharu Arakawa and Bruno Aranda and Joachim Baran and Jerven Bolleman and Raoul J. P. Bonnal and Pier Luigi Buttigieg and Matthew P. Campbell and Yi-an Chen and Hirokazu Chiba and Peter J. A. Cock and Kevin B. Cohen and Alexandru Constantin and Geraint Duck and Michel Dumontier and Takatomo Fujisawa and Toyofumi Fujiwara and Naohisa Goto and Robert Hoehndorf and Yoshinobu Igarashi and Hidetoshi Itaya and Maori Ito and Wataru Iwasaki and Mat\'{u}\v{s} Kala\v{s} and Takeo Katoda and Taehong Kim and Anna Kokubu and Yusuke Komiyama and Masaaki Kotera and Camille Laibe and Hilmar Lapp and Thomas L\"{u}tteke and M Scott Marshall and Takaaki Mori and Hiroshi Mori and Mizuki Morita and Katsuhiko Murakami and Mitsuteru Nakao and Hisashi Narimatsu and Hiroyo Nishide and Yosuke Nishimura and Johan Nystrom-Persson and Soichi Ogishima and Yasunobu Okamura and Shujiro Okuda and Kazuki Oshita and Nicki H Packer and Pjotr Prins and Rene Ranzinger and Philippe Rocca-Serra and Susanna Sansone and Hiromichi Sawaki and Sung-Ho Shin and Andrea Splendiani and Francesco Strozzi and Shu Tadaka and Philip Toukach and Ikuo Uchiyama and Masahito Umezaki and Rutger Vos and Patricia L Whetzel and Issaku Yamada and Chisato Yamasaki and Riu Yamashita and William S York and Christian M. Zmasek and Shoko Kawamoto and Toshihisa Takagi},
	Title = {BioHackathon series in 2011 and 2012: penetration of ontology and {Linked Data} in life science domains},
	Journal = {Journal of Biomedical Semantics},
        Year =  2014,
        Volume =  5,
        Pages = 5,
        Doi = {10.1186/2041-1480-5-5},
        Abstract = {The application of semantic technologies to the integration of biological data and the interoperability of bioinformatics analysis and visualization tools has been the common theme of a series of annual BioHackathons hosted in Japan for the past five years. Here we provide a review of the activities and outcomes from the BioHackathons held in 2011 in Kyoto and 2012 in Toyama. In order to efficiently implement semantic technologies in the life sciences, participants formed various sub-groups and worked on the following topics: Resource Description Framework (RDF) models for specific domains, text mining of the literature, ontology development, essential metadata for biological databases, platforms to enable efficient Semantic Web technology development and interoperability, and the development of applications for Semantic Web data. In this review, we briefly introduce the themes covered by these sub-groups. The observations made, conclusions drawn, and software development projects that emerged from these activities are discussed.}
}

@article{BioHack2010,
	Author = {Toshiaki Katayama and Mark D. Wilkinson and Gos Micklem and Shuichi Kawashima and Atsuko Yamaguchi and Mitsuteru Nakao and Yasunori Yamamoto and Shinobu Okamoto and Kenta Oouchida and Hong-Woo Chun and Jan Aerts and Hammad Afzal and Erick Antezana and Kazuharu Arakawa and Bruno Aranda and Francois Belleau and Jerven Bolleman and Raoul J. P. Bonnal and Brad Chapman and Peter J. A. Cock and Tore Eriksson and Paul M. K. Gordon and Naohisa Goto and Kazuhiro Hayashi and Heiko Horn and Ryosuke Ishiwata and Eli Kaminuma and Arek Kasprzyk and Hideya Kawaji and Nobuhiro Kido and Young Joo Kim and Akira R. Kinjo and Fumikazu Konishi and Kyung-Hoon Kwon and Alberto Labarga and Anna-Lena Lamprecht and Yu Lin and Pierre Lindenbaum and Luke McCarthy and Hideyuki Morita and Katsuhiko Murakami and Koji Nagao and Kozo Nishida and Kunihiro Nishimura and Tatsuya Nishizawa and Soichi Ogishima and Keiichiro Ono and Kazuki Oshita and Keun-Joon Park and Pjotr Prins and Taro L. Saito and Matthias Samwald and Venkata P. Satagopam and Yasumasa Shigemoto and Richard Smith and Andrea Splendiani and Hideaki Sugawara and James Taylor and Rutger A. Vos and David Withers and Chisato Yamasaki and Christian M. Zmasek and Shoko Kawamoto and Kosaku Okubo and Kiyoshi Asai and Toshihisa Takagi},
	Doi = {10.1186/2041-1480-4-6},
	Journal = {Journal of Biomedical Semantics},
	Pages = 6,
	Title = {The {3rd} {DBCLS} {BioHackathon}: improving life science data integration with {Semantic Web} technologies},
	Url = {http://dx.doi.org/10.1186/2041-1480-4-6},
	Volume = 4,
	Year = 2013,
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/2041-1480-4-6}}

@article{BioHack2009,
    author = {Toshiaki Katayama and Mark D. Wilkinson and Rutger Vos and Takeshi Kawashima and Shuichi Kawashima and Mitsuteru Nakao and Yasunori Yamamoto and Hong-Woo Chun and Atsuko Yamaguchi and Shin Kawano and Jan Aerts and Kiyoko F Aoki-Kinoshita and Kazuharu Arakawa and Bruno Aranda and Raoul JP Bonnal and Jos\'{e} M Fern\'{a}ndez and Takatomo Fujisawa and Paul MK Gordon and Naohisa Goto and Syed Haider and Todd Harris and Takashi Hatakeyama and Isaac Ho and Masumi Itoh and Arek Kasprzyk and Nobuhiro Kido and Young-Joo Kim and Akira R Kinjo and Fumikazu Konishi and Yulia Kovarskaya and Greg von Kuster and Alberto Labarga and Vachiranee Limviphuvadh and Luke McCarthy and Yasukazu Nakamura and Yunsun Nam and Kozo Nishida and Kunihiro Nishimura and Tatsuya Nishizawa and Soichi Ogishima and Tom Oinn and Shinobu Okamoto and Shujiro Okuda and Keiichiro Ono and Kazuki Oshita and Keun-Joon Park and Nicholas Putnam and Martin Senger and Jessica Severin and Yasumasa Shigemoto and Hideaki Sugawara and James Taylor and Oswaldo Trelles and Chisato Yamasaki and Riu Yamashita and Noriyuki Satoh and Toshihisa Takagi},
    title = {The 2nd {DBCLS} {BioHackathon}: interoperable bioinformatics {Web services} for integrated applications},
    journal = {Journal of Biomedical Semantics},
    year = 2011,
    volume = 2,
    pages = 6,
    doi = {10.1186/2041-1480-2-4},
    url = {http://dx.doi.org/10.1186/2041-1480-2-4}
}

@article{BioHack2008,
    author = {Toshiaki Katayama and Kazuharu Arakawa and Mitsuteru Nakao and Keiichiro Ono and Kiyoko F Aoki-Kinoshita and Yasunori Yamamoto and Atsuko Yamaguchi and Shuichi Kawashima and Hong-Woo Chun and Jan Aerts and Bruno Aranda and Lord Hendrix Barboza and Raoul JP Bonnal and Richard Bruskiewich and Jan C Bryne and Jos\'{e} M Fern\'{a}ndez and Akira Funahashi and Paul MK Gordon and Naohisa Goto and Andreas Groscurth and Alex Gutteridge and Richard Holland and Yoshinobu Kano and Edward A Kawas and Arnaud Kerhornou and Eri Kibukawa and Akira R Kinjo and Michael Kuhn and Hilmar Lapp and Heikki Lehvaslaiho and Hiroyuki Nakamura and Yasukazu Nakamura and Tatsuya Nishizawa and Chikashi Nobata and Tamotsu Noguchi and Thomas M Oinn and Shinobu Okamoto and Stuart Owen and Evangelos Pafilis and Matthew Pocock and Pjotr Prins and Ren\'{e} Ranzinger and Florian Reisinger and Lukasz Salwinski and Mark Schreiber and Martin Senger and Yasumasa Shigemoto and Daron M Standley and Hideaki Sugawara and Toshiyuki Tashiro and Oswaldo Trelles and Rutger A Vos and Mark D Wilkinson and William York and Christian M Zmasek and Kiyoshi Asai and Toshihisa Takagi},
    title = {The {DBCLS} {BioHackathon}: standardization and interoperability for bioinformatics web services and workflows},
    journal = {Journal of Biomedical Semantics},
    year = 2010,
    volume = 1,
    pages = 8,
    doi = {10.1186/2041-1480-1-8},
    url = {http://dx.doi.org/10.1186/2041-1480-1-8}
}

@article{SequenceOntology2005,
	Author = {K. Eilbeck and S. E. Lewis and C. J. Mungall and M. Yandell and L. Stein and R. Durbin and M. Ashburner},
	Doi = {10.1186/gb-2005-6-5-r44},
	Journal = {Genome Biology},
	Number = 5,
	Pages = {R44},
	Title = {The {Sequence} {Ontology}: A tool for the unification of genome annotations.},
	Url = {http://dx.doi.org/10.1186/gb-2005-6-5-r44},
	Volume = 6,
	Year = 2005,
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/gb-2005-6-5-r44}}

@article{BioJava2012,
	Author = {A. Prli\'{c} and A. Yates and S. E. Bliven and P. W. Rose and J. Jacobsen and P. V. Troshin and M. Chapman and J. Gao and C. H. Koh and S. Foisy and R. Holland and G. Rimsa and M. L. Heuer and H. Brandst\"{a}tter-M\"{u}ller and P. E. Bourne and S. Willis},
	Doi = {10.1093/bioinformatics/bts494},
	Journal = {Bioinformatics},
	Number = 20,
	Pages = {2693-2695},
	Title = {{BioJava}: an open-source framework for bioinformatics in 2012},
	Url = {http://dx.doi.org/10.1093/bioinformatics/bts494},
	Volume = 28,
	Year = 2012,
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/bts494}}

@article{BioRuby2010,
	Author = {N. Goto and P. Prins and M. Nakao and R. Bonnal and J. Aerts and T. Katayama},
	Doi = {10.1093/bioinformatics/btq475},
	Journal = {Bioinformatics},
	Number = 20,
	Pages = {2617-2619},
	Title = {{BioRuby}: bioinformatics software for the {Ruby} programming language.},
	Url = {http://dx.doi.org/10.1093/bioinformatics/btq475},
	Volume = 26,
	Year = 2010,
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/btq475}}

@article{BioPerl2002,
	Author = {Jason E Stajich and David Block and Kris Boulez and Steven E Brenner and Stephen A Chervitz and Chris Dagdigian and Georg Fuellen and James G R Gilbert and Ian Korf and Hilmar Lapp and Heikki Lehv{\"a}slaiho and Chad Matsalla and Chris J Mungall and Brian I Osborne and Matthew R Pocock and Peter Schattner and Martin Senger and Lincoln D Stein and Elia Stupka and Mark D Wilkinson and Ewan Birney},
	Doi = {10.1101/gr.361602},
	Journal = {Genome Research},
	Number = {10},
	Pages = {1611-1618},
	Pmid = {12368254},
	Title = {The {Bioperl} toolkit: Perl modules for the life sciences},
	Url = {http://dx.doi.org/10.1101/gr.361602},
	Volume = {12},
	Year = {2002},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.361602}}

@article{Biopython2009,
	Author = {Cock, Peter J A and Antao, Tiago and Chang, Jeffrey T and Chapman, Brad A and Cox, Cymon J and Dalke, Andrew and Friedberg, Iddo and Hamelryck, Thomas and Kauff, Frank and Wilczynski, Bartek and de Hoon, Michiel J. L.},
	Doi = {10.1093/bioinformatics/btp163},
	Journal = {Bioinformatics},
	Number = {11},
	Pages = {1422-1423},
	Title = {{Biopython}: freely available {Python} tools for computational molecular biology and bioinformatics},
	Url = {http://dx.doi.org/10.1093/bioinformatics/btp163},
	Volume = {25},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/btp163}}

@article{UniProt2013,
	Abstract = {The mission of the Universal Protein Resource (UniProt) (http://www.uniprot.org) is to support biological research by providing a freely accessible, stable, comprehensive, fully classified, richly and accurately annotated protein sequence knowledgebase. It integrates, interprets and standardizes data from numerous resources to achieve the most comprehensive catalogue of protein sequences and functional annotation. UniProt comprises four major components, each optimized for different uses, the UniProt Archive, the UniProt Knowledgebase, the UniProt Reference Clusters and the UniProt Metagenomic and Environmental Sequence Database. UniProt is produced by the UniProt Consortium, which consists of groups from the European Bioinformatics Institute (EBI), the SIB Swiss Institute of Bioinformatics (SIB) and the Protein Information Resource (PIR). UniProt is updated and distributed every 4 weeks and can be accessed online for searches or downloads.},
	Author = {{The UniProt Consortium}},
	Doi = {10.1093/nar/gks1068},
	Eprint = {http://nar.oxfordjournals.org/content/41/D1/D43.full.pdf+html},
	Journal = {Nucleic Acids Research},
	Number = {D1},
	Pages = {D43-D47},
	Title = {Update on activities at the {Universal Protein Resource} ({UniProt}) in 2013},
	Url = {http://dx.doi.org/10.1093/nar/gks1068},
	Volume = {41},
	Year = {2013},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/content/41/D1/D43.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/nar/gks1068}}

@article{Genbank2013,
	Abstract = {GenBank (http://www.ncbi.nlm.nih.gov) is a comprehensive database that contains publicly available nucleotide sequences for almost 260 000 formally described species. These sequences are obtained primarily through submissions from individual laboratories and batch submissions from large-scale sequencing projects, including whole-genome shotgun (WGS) and environmental sampling projects. Most submissions are made using the web-based BankIt or standalone Sequin programs, and GenBank staff assigns accession numbers upon data receipt. Daily data exchange with the European Nucleotide Archive (ENA) and the DNA Data Bank of Japan (DDBJ) ensures worldwide coverage. GenBank is accessible through the NCBI Entrez retrieval system, which integrates data from the major DNA and protein sequence databases along with taxonomy, genome, mapping, protein structure and domain information, and the biomedical journal literature via PubMed. BLAST provides sequence similarity searches of GenBank and other sequence databases. Complete bimonthly releases and daily updates of the GenBank database are available by FTP. To access GenBank and its related retrieval and analysis services, begin at the NCBI home page: www.ncbi.nlm.nih.gov.},
	Author = {Benson, Dennis A. and Cavanaugh, Mark and Clark, Karen and Karsch-Mizrachi, Ilene and Lipman, David J. and Ostell, James and Sayers, Eric W.},
	Doi = {10.1093/nar/gks1195},
	Eprint = {http://nar.oxfordjournals.org/content/41/D1/D36.full.pdf+html},
	Journal = {Nucleic Acids Research},
	Number = {D1},
	Pages = {D36-D42},
	Title = {GenBank},
	Url = {http://dx.doi.org/10.1093/nar/gks1195},
	Volume = {41},
	Year = {2013},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/content/41/D1/D36.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/nar/gks1195}}

@article{DDBJ2013,
	Abstract = {The DNA data bank of Japan (DDBJ, http://www.ddbj.nig.ac.jp) maintains a primary nucleotide sequence database and provides analytical resources for biological information to researchers. This database content is exchanged with the US National Center for Biotechnology Information (NCBI) and the European Bioinformatics Institute (EBI) within the framework of the International Nucleotide Sequence Database Collaboration (INSDC). Resources provided by the DDBJ include traditional nucleotide sequence data released in the form of 27 316 452 entries or 16 876 791 557 base pairs (as of June 2012), and raw reads of new generation sequencers in the sequence read archive (SRA). A Japanese researcher published his own genome sequence via DDBJ-SRA on 31 July 2012. To cope with the ongoing genomic data deluge, in March 2012, our computer previous system was totally replaced by a commodity cluster-based system that boasts 122.5 TFlops of CPU capacity and 5 PB of storage space. During this upgrade, it was considered crucial to replace and refactor substantial portions of the DDBJ software systems as well. As a result of the replacement process, which took more than 2 years to perform, we have achieved significant improvements in system performance.},
	Author = {Ogasawara, Osamu and Mashima, Jun and Kodama, Yuichi and Kaminuma, Eli and Nakamura, Yasukazu and Okubo, Kousaku and Takagi, Toshihisa},
	Doi = {10.1093/nar/gks1152},
	Eprint = {http://nar.oxfordjournals.org/content/41/D1/D25.full.pdf+html},
	Journal = {Nucleic Acids Research},
	Number = {D1},
	Pages = {D25-D29},
	Title = {DDBJ new system and service refactoring},
	Url = {http://dx.doi.org/10.1093/nar/gks1152},
	Volume = {41},
	Year = {2013},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/content/41/D1/D25.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/nar/gks1152}}

@article{ENA2013,
	Abstract = {The European Nucleotide Archive (ENA; http://www.ebi.ac.uk/ena/) collects, maintains and presents comprehensive nucleic acid sequence and related information as part of the permanent public scientific record. Here, we provide brief updates on ENA content developments and major service enhancements in 2012 and describe in more detail two important areas of development and policy that are driven by ongoing growth in sequencing technologies. First, we describe the ENA data warehouse, a resource for which we provide a programmatic entry point to integrated content across the breadth of ENA. Second, we detail our plans for the deployment of CRAM data compression technology in ENA.},
	Author = {Cochrane, Guy and Alako, Blaise and Amid, Clara and Bower, Lawrence and Cerde{\~n}o-T{\'a}rraga, Ana and Cleland, Iain and Gibson, Richard and Goodgame, Neil and Jang, Mikyung and Kay, Simon and Leinonen, Rasko and Lin, Xiu and Lopez, Rodrigo and McWilliam, Hamish and Oisel, Arnaud and Pakseresht, Nima and Pallreddy, Swapna and Park, Youngmi and Plaister, Sheila and Radhakrishnan, Rajesh and Rivi{\`e}re, Stephane and Rossello, Marc and Senf, Alexander and Silvester, Nicole and Smirnov, Dmitriy and ten Hoopen, Petra and Toribio, Ana and Vaughan, Daniel and Zalunin, Vadim},
	Doi = {10.1093/nar/gks1175},
	Eprint = {http://nar.oxfordjournals.org/content/41/D1/D30.full.pdf+html},
	Journal = {Nucleic Acids Research},
	Number = {D1},
	Pages = {D30-D35},
	Title = {Facing growth in the {European Nucleotide Archive}},
	Url = {http://dx.doi.org/10.1093/nar/gks1175},
	Volume = {41},
	Year = {2013},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/content/41/D1/D30.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/nar/gks1175}}

@article{Chado2007,
	Abstract = {Motivation: A few years ago, FlyBase undertook to design a new database schema to store Drosophila data. It would fully integrate genomic sequence and annotation data with bibliographic, genetic, phenotypic and molecular data from the literature representing a distillation of the first 100 years of research on this major animal model system. In developing this new integrated schema, FlyBase also made a commitment to ensure that its design was generic, extensible and available as open source, so that it could be employed as the core schema of any model organism data repository, thereby avoiding redundant software development and potentially increasing interoperability. Our question was whether we could create a relational database schema that would be successfully reused.Results: Chado is a relational database schema now being used to manage biological knowledge for a wide variety of organisms, from human to pathogens, especially the classes of information that directly or indirectly can be associated with genome sequences or the primary RNA and protein products encoded by a genome. Biological databases that conform to this schema can interoperate with one another, and with application software from the Generic Model Organism Database (GMOD) toolkit. Chado is distinctive because its design is driven by ontologies. The use of ontologies (or controlled vocabularies) is ubiquitous across the schema, as they are used as a means of typing entities. The Chado schema is partitioned into integrated subschemas (modules), each encapsulating a different biological domain, and each described using representations in appropriate ontologies. To illustrate this methodology, we describe here the Chado modules used for describing genomic sequences.Availability: GMOD is a collaboration of several model organism database groups, including FlyBase, to develop a set of open-source software for managing model organism data. The Chado schema is freely distributed under the terms of the Artistic License (http://www.opensource.org/licenses/artistic-license.php) from GMOD (www.gmod.org).Contact: cjm@fruitfly.org or emmert@morgan.harvard.edu.},
	Author = {Mungall, Christopher J. and Emmert, David B. and {The FlyBase Consortium}},
	Doi = {10.1093/bioinformatics/btm189},
	Eprint = {http://bioinformatics.oxfordjournals.org/content/23/13/i337.full.pdf+html},
	Journal = {Bioinformatics},
	Number = {13},
	Pages = {i337-i346},
	Title = {A {Chado} case study: an ontology-based modular schema for representing genome-associated biological information},
	Url = {http://dx.doi.org/10.1093/bioinformatics/btm189},
	Volume = {23},
	Year = {2007},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/content/23/13/i337.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/btm189}}

@article{NCL2007,
	Abstract = {Motivation: The exponential growth of sequence databases poses a major
	challenge to bioinformatics tools for querying alignment and annotation
	databases. There is a pressing need for methods for finding overlapping
	sequence intervals that are highly scalable to database size, query
	interval size, result size, and construction / updating of the interval
	database. Results: We have developed a new interval database representation,
	the Nested Containment List {(NCList),} whose query time is O(n +
	log N), where N is the database size and n is the size of the result
	set. In all cases tested this query algorithm is 5 -500 fold faster
	than other indexing methods tested in this study, such as {MySQL}
	mult-column indexing, {MySQL} binning, and {R-Tree} indexing. We
	provide performance comparisons both in simulated datasets and real-world
	genome alignment databases, across a wide range of data-base sizes
	and query interval widths. We also present an in-place {NCList} construction
	algorithm that yields database construction times that are approximately
	100-fold faster than other methods available. The {NCList} data structure
	appears to provide a useful foundation for highly scalable interval
	database applications. Availability: {NCList} data structure is part
	of Pygr, a bioinformatics graph database library, available at http://sourceforge.net/projects/pygr},
	Author = {Alexander V Alekseyenko and Christopher J Lee},
	Doi = {10.1093/bioinformatics/btl647},
	Journal = {Bioinformatics},
	Pages = {btl647},
	Title = {Nested Containment List {(NCList):} A new algorithm for accelerating interval query of genome alignment and interval databases},
	Url = {http://dx.doi.org/10.1093/bioinformatics/btl647},
	Year = {2007},
	Bdsk-Url-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/btl647v1},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/bioinformatics/btl647}}

@article{BOING,
	Author = {Martijn Devisscher and Tim {De Meyer} and Wim {Van Criekinge} and Peter Dawyndt},
	Journal = {EMBnet.journal},
	volume = {19},
	number = {B},
	Pages = {51-55},
	Title = {An ontology based query engine for querying biological sequences},
	Year = {2013},
	Url = {http://journal.embnet.org/index.php/embnetjournal/article/view/729}}

@article{Lutteke01052006,
	Abstract = {The development of glycan-related databases and bioinformatics applications is considerably lagging behind compared with the wealth of available data and software tools in genomics and proteomics. Because the encoding of glycan structures is more complex, most of the bioinformatics approaches cannot be applied to glycan structures. No standard procedures exist where glycan structures found in various species, organs, tissues or cells can be routinely deposited. In this article the concepts of the GLYCOSCIENCES.de portal are described. It is demonstrated how an efficient structure-based cross-linking of various glycan-related data originating from different resources can be accomplished using a single user interface. The structure oriented retrieval options{\~N}exact structure, substructure, motif, composition and sugar components{\~N}are discussed. The types of available data{\~N}references, composition, spatial structures, nuclear magnetic resonance (NMR) shifts (experimental and estimated), theoretically calculated fragments and Protein Database (PDB) entries{\~N}are exemplified for Man3. The free availability and unrestricted use of glycan-related data is an absolute prerequisite to efficiently share distributed resources. Additionally, there is an urgent need to agree to a generally accepted exchange format as well as to a common software interface. An open access repository for glyco-related experimental data will secure that the loss of primary data will be considerably reduced.},
	Author = {L{\"u}tteke, Thomas and Bohne-Lang, Andreas and Loss, Alexander and Goetz, Thomas and Frank, Martin and von der Lieth, Claus-W.},
	Doi = {10.1093/glycob/cwj049},
	Eprint = {http://glycob.oxfordjournals.org/content/16/5/71R.full.pdf+html},
	Journal = {Glycobiology},
	Number = {5},
	Pages = {71R-81R},
	Title = {GLYCOSCIENCES.de: an Internet portal to support glycomics and glycobiology research},
	Url = {http://dx.doi.org/10.1093/glycob/cwj049},
	Volume = {16},
	Year = {2006},
	Bdsk-Url-1 = {http://glycob.oxfordjournals.org/content/16/5/71R.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/glycob/cwj049}}

@article{Ranzinger01012011,
	Abstract = {GlycomeDB integrates the structural and taxonomic data of all major public carbohydrate databases, as well as carbohydrates contained in the Protein Data Bank, which renders the database currently the most comprehensive and unified resource for carbohydrate structures worldwide. GlycomeDB retains the links to the original databases and is updated at weekly intervals with the newest structures available from the source databases. The complete database can be downloaded freely or accessed through a Web-interface (www.glycome-db.org) that provides flexible and powerful search functionalities.},
	Author = {Ranzinger, Ren{\'e} and Herget, Stephan and von der Lieth, Claus-Wilhelm and Frank, Martin},
	Doi = {10.1093/nar/gkq1014},
	Eprint = {http://nar.oxfordjournals.org/content/39/suppl_1/D373.full.pdf+html},
	Journal = {Nucleic Acids Research},
	Number = {suppl 1},
	Pages = {D373-D376},
	Title = {{GlycomeDB} -- a unified database for carbohydrate structures},
	Url = {http://dx.doi.org/10.1093/nar/gkq1014},
	Volume = {39},
	Year = {2011},
	Bdsk-Url-1 = {http://nar.oxfordjournals.org/content/39/suppl_1/D373.abstract},
	Bdsk-Url-2 = {http://dx.doi.org/10.1093/nar/gkq1014}}
@article{Sanger1949,
	Author = {Fred Sanger},
	Title = {The terminal peptides of insulin},
	Year = {1949},
	Volume = {45(5)},
	Pages = {563-574},
	Journal = {Biochemical Journal}
}

@book{dayhoff1965atlas,
		Author = {Dayhoff, M.O. and Eck, R.V. and National Biomedical Research Foundation},
	Issn = {0572-435X},
	Lccn = {65029342},
	Publisher = {National Biomedical Research Foundation.},
	Title = {Atlas of Protein Sequence and Structure},
	Year = {1965}}
@techreport{RDFValidationReport,
Title= {RDF Validation Workshop Report, Practical Assurances for Quality RDF Data},
Institution={W3C},
Year={2013},
Author={Arnaud {Le Hors} and Harold Solbrig and {Eric Prud'hommeaux}},
Url = {http://www.w3.org/2012/12/rdf-val/report}
}

@techreport{TurtleFormatSpec,
Title= {RDF 1.1 Turtle - Terse RDF Triple Language},
Institution={W3C},
Year={2014},
Author={David Beckett and Tim Berners-Lee and Eric {Prud'hommeaux} and Gavin Carothers} ,
Url={http://www.w3.org/TR/turtle/}
}

@techreport{JSONLDFormatSpec,
Title= {JSON-LD 1.0 - A JSON-based Serialization for Linked Data},
Institution={W3C},
Year={2014},
Author={Manu Sporny and Gregg Kellogg and Markus Lanthaler},
Url={http://www.w3.org/TR/json-ld/}
}

@techreport{NCBI,
Title={Biological Sequence Data Model},
Subtitle={Locations on Biological Sequences},
Year={2013},
Institution={NCBI},
Author={Vakatov D, editor},
Url={http://www.ncbi.nlm.nih.gov/books/NBK7198/#ch_datamod.Locations_on_Biologi}
}

@article{24602174,
	Abstract = {The Semanticscience Integrated Ontology (SIO) is an ontology to facilitate biomedical knowledge discovery. SIO features a simple upper level comprised of essential types and relations for the rich description of arbitrary (real, hypothesized, virtual, fictional) objects, processes and their attributes. SIO specifies simple design patterns to describe and associate qualities, capabilities, functions, quantities, and informational entities including textual, geometrical, and mathematical entities, and provides specific extensions in the domains of chemistry, biology, biochemistry, and bioinformatics. SIO provides an ontological foundation for the Bio2RDF linked data for the life sciences project and is used for semantic integration and discovery for SADI-based semantic web services. SIO is freely available to all users under a creative commons by attribution license. See website for further information: http://sio.semanticscience.org webcite.},
	Author = {Dumontier, Michel and Baker, Christopher and Baran, Joachim and Callahan, Alison and Chepelev, Leonid and Cruz-Toledo, Jose and Del Rio, Nicholas and Duck, Geraint and Furlong, Laura and Keath, Nichealla and Klassen, Dana and McCusker, James and Queralt-Rosinach, Nuria and Samwald, Matthias and Villanueva-Rosales, Natalia and Wilkinson, Mark and Hoehndorf, Robert},
	Doi = {10.1186/2041-1480-5-14},
	Issn = {2041-1480},
	Journal = {Journal of Biomedical Semantics},
	Number = {1},
	Pages = {14},
	Pubmedid = {24602174},
	Title = {The Semanticscience Integrated Ontology (SIO) for biomedical research and knowledge discovery},
	Url = {http://www.jbiomedsem.com/content/5/1/14},
	Volume = {5},
	Year = {2014},
	Bdsk-Url-1 = {http://www.jbiomedsem.com/content/5/1/14},
	Bdsk-Url-2 = {http://dx.doi.org/10.1186/2041-1480-5-14}}