minid.bib

@IEEEtranBSTCTL{IEEEexample:BSTcontrol,
  CTLuse_forced_etal       = "yes",
  CTLmax_names_forced_etal = "3",
  CTLnames_show_etal       = "1"
}

@inproceedings{folk2011overview,
  title={An overview of the HDF5 technology suite and its applications},
  author={Folk, Mike and Heber, Gerd and Koziol, Quincey and Pourmal, Elena and Robinson, Dana},
  booktitle={EDBT/ICDT 2011 Workshop on Array Databases},
  pages={36--47},
  year={2011},
  organization={ACM}
}

@article{madduri2014experiences,
  title={Experiences building {Globus Genomics}: A next-generation sequencing analysis service using {Galaxy, Globus, and Amazon Web Services}},
  author={Madduri, Ravi K and Sulakhe, Dinanath and Lacinski, Lukasz and Liu, Bo and Rodriguez, Alex and Chard, Kyle and Dave, Utpal J and Foster, Ian T},
  journal={Concurrency and Computation: Practice and Experience},
  volume={26},
  number={13},
  pages={2266--2279},
  year={2014},
  publisher={Wiley Online Library}
}

@article{Deutsch2016,
  author = {Deutsch, EW and Sun, Z and Campbell, DS and Binz, PA and Farrah, T and Shteynberg, D and Mendoza, L and Omenn, GS and Moritz, RL},
  title = {Tiered Human Integrated Sequence Search Databases for Shotgun Proteomics},
  year = 2016, 
  journal = {Journal of Proteome Research},
  note = {submitted}
  }

@article{laibe2007miriam,
  title={{MIRIAM} Resources: tools to generate and resolve robust cross-references in Systems Biology},
  author={Laibe, Camille and Le Nov{\`e}re, Nicolas},
  journal={BMC Systems Biology},
  volume={1},
  number={1},
  pages={1},
  year={2007},
  publisher={BioMed Central}
}

@article{juty2012identifiers,
  title={Identifiers.org and {MIRIAM Registry}: Community resources to provide persistent identification},
  author={Juty, Nick and Le Nov{\`e}re, Nicolas and Laibe, Camille},
  journal={Nucleic acids research},
  volume={40},
  number={D1},
  pages={D580--D586},
  year={2012},
  publisher={Oxford Univ Press}
}

@article{deutsch2015state,
  title={State of the human proteome in 2014/2015 as viewed through {PeptideAtlas}: Enhancing accuracy and coverage through the {AtlasProphet}},
  author={Deutsch, Eric W and Sun, Zhi and Campbell, David and Kusebauch, Ulrike and Chu, Caroline S and Mendoza, Luis and Shteynberg, David and Omenn, Gilbert S and Moritz, Robert L},
  journal={Journal of Proteome Research},
  volume={14},
  number={9},
  pages={3461--3473},
  year={2015},
  publisher={ACS Publications}
}

@article{keller2005uniform,
  title={A uniform proteomics {MS/MS} analysis platform utilizing open {XML} file formats},
  author={Keller, Andrew and Eng, Jimmy and Zhang, Ning and Li, Xiao-jun and Aebersold, Ruedi},
  journal={Molecular Systems Biology},
  volume={1},
  number={1},
  year={2005},
  publisher={EMBO Press}
}

@article{deutsch2015trans,
  title={{Trans-Proteomic Pipeline}, a standardized data processing pipeline for large-scale reproducible proteomics informatics},
  author={Deutsch, Eric W and Mendoza, Luis and Shteynberg, David and Slagel, Joseph and Sun, Zhi and Moritz, Robert L},
  journal={PROTEOMICS-Clinical Applications},
  volume={9},
  number={7-8},
  pages={745--754},
  year={2015},
  publisher={Wiley Online Library}
}

@article{deutsch2015development,
  title={Development of data representation standards by the human proteome organization proteomics standards initiative},
  author={Deutsch, Eric W and Albar, Juan Pablo and Binz, Pierre-Alain and Eisenacher, Martin and Jones, Andrew R and Mayer, Gerhard and Omenn, Gilbert S and Orchard, Sandra and Vizca{\'\i}no, Juan Antonio and Hermjakob, Henning},
  journal={Journal of the American Medical Informatics Association},
  volume={22},
  number={3},
  pages={495--506},
  year={2015},
  publisher={The Oxford University Press}
}

@article{martens2011mzml,
  title={mz{ML}--a community standard for mass spectrometry data},
  author={Martens, Lennart and Chambers, Matthew and Sturm, Marc and Kessner, Darren and Levander, Fredrik and Shofstahl, Jim and Tang, Wilfred H and R{\"o}mpp, Andreas and Neumann, Steffen and Pizarro, Angel D and others},
  journal={Molecular \& Cellular Proteomics},
  volume={10},
  number={1},
  pages={R110--000133},
  year={2011},
  publisher={ASBMB}
}

@article{vizcaino2014proteomexchange,
  title={Proteome{X}change provides globally coordinated proteomics data submission and dissemination},
  author={Vizca{\'\i}no, Juan A and Deutsch, Eric W and Wang, Rui and Csordas, Attila and Reisinger, Florian and Rios, Daniel and Dianes, Jose A and Sun, Zhi and Farrah, Terry and Bandeira, Nuno and others},
  journal={Nature Biotechnology},
  volume={32},
  number={3},
  pages={223--226},
  year={2014},
  publisher={Nature Publishing Group}
}

@inproceedings{bechhofer2010research,
  title={{Research Objects}: Towards exchange and reuse of digital knowledge},
  author={Bechhofer, Sean and De Roure, David and Gamble, Matthew and Goble, Carole and Buchan, Iain},
  booktitle={Workshop on The Future of the Web for Collaborative Science},
  note={Available from Nature Precedings \url{http://dx.doi.org/10.1038/npre.2010.4626.1}},
  year={2010}
}

@inproceedings{chard2015globus,
  title={Globus data publication as a service: Lowering barriers to reproducible science},
  author={Chard, Kyle and Pruyne, Jim and Blaiszik, Ben and Ananthakrishnan, Rachana and Tuecke, Steven and Foster, Ian},
  booktitle={11th International Conference on e-Science},
  pages={401--410},
  year={2015},
  organization={IEEE}
}

@misc{ROBagItProfile,
  author={Soiland-Reyes, Stian},
  organization = {researchobject.org},
  title = {Research {O}bject {BagIt} archive},
  note={\url{https://w3id.org/ro/bagit}. Visited July 1, 2016}
}

@misc{BagItProfile,
  author={Mark Jordan AND Nick Ruest AND Meghan Currie AND Krista Godfrey AND William Wueppelmann AND Dan Chudnov},
  title = {BagIt Profiles Specification 1.0.1},
  year = {2015},
  month = {08},
  day = {06},
  note={\url{https://github.com/ruebot/bagit-profiles}. Visited July 20, 2016}
}



@article{Ison2013EDAM,
  title = {{EDAM}: an ontology of bioinformatics operations, types of data and identifiers, topics and formats},
  author = {Jon Ison AND Mat\'{u}\u{s} Kala\u{s} AND Inge Jonassen AND Dan Bolser AND Mahmut Uludag AND Hamish McWilliam AND James Malone
  AND Rodrigo Lopez AND Steve Pettifer AND Peter Rice},
  journal={Bioinformatics},
  volume = {29},
  number = {10},
  year = {2013},
  pages = {1325--1332},
  publisher = {Oxford Journals},
  doi = {10.1093/bioinformatics/btt113}
}

@misc{ROBundle,
  author={Soiland-Reyes, Stian AND Gamble, Matthew AND Haines, Robert},
  title = {Research {O}bject {Bundle} 1.0},
  organization = {researchobject.org},
  howpublished = {Specification},
  year={2014},
  month = {November},
  day = {05},
  note={\url{https://w3id.org/bundle/2014-11-05/}}
}

@inproceedings{Page2014AudioRO,
 author={Kevin R. Page AND Raul Palma AND Piotr Ho\l{}ubowicz AND Graham Klyne AND Stian Soiland-Reyes AND Daniel Garijo AND Khalid Belhajjame AND Rudolf Mayer},
 title={{Research Objects} for Audio Processing: Capturing Semantics for Reproducibility},
 booktitle={53rd International Conference: Semantic Audio},
 year={2014},
 month={January},
 day={27},
 isbn={978-0-937803-96-7},
 note={\url{http://www.aes.org/e-lib/browse.cfm?elib=17116}}
}

@article{encode2004encode,
  title={The {ENCODE} ({ENCyclopedia of DNA elements}) project},
  author={{ENCODE Project Consortium} and others},
  journal={Science},
  volume={306},
  number={5696},
  pages={636--640},
  year={2004},
  publisher={American Association for the Advancement of Science}
}

@article{vasilevsky2013reproducibility,
  title=
  {On the reproducibility of science: Unique identification of research resources in the biomedical literature},
  author={Vasilevsky, Nicole A and Brush, Matthew H and Paddock, Holly and Ponting, Laura and Tripathy, Shreejoy J and LaRocca, Gregory M and Haendel, Melissa A},
  journal={PeerJ},
  volume={1},
  pages={e148},
  year={2013},
  publisher={PeerJ Inc.}
}

@article{begley2012drug,
  title={Drug development: Raise standards for preclinical cancer research},
  author={Begley, C Glenn and Ellis, Lee M},
  journal={Nature},
  volume={483},
  number={7391},
  pages={531--533},
  year={2012},
  publisher={Nature Publishing Group}
}

@online{hdf5,
    author = {{The HDF Group}},
    title = "{{Hierarchical Data Format}, version 5}",
    year = {1997--2016},
    note = {\url{http://www.hdfgroup.org/HDF5/}}
}

@article{zhao2005notation,
  title={A notation and system for expressing and executing cleanly typed workflows on messy scientific data},
  author={Zhao, Yong and Dobson, Jed and Foster, Ian and Moreau, Luc and Wilde, Michael},
  journal={ACM SIGMOD Record},
  volume={34},
  number={3},
  pages={37--43},
  year={2005},
  publisher={ACM}
}

@article{read2015sizing,
  title={Sizing the Problem of Improving Discovery and Access to {NIH}-Funded Data: A Preliminary Study},
  author={Read, Kevin B and Sheehan, Jerry R and Huerta, Michael F and Knecht, Lou S and Mork, James G and Humphreys, Betsy L and others},
  journal={{PloS} {ONE}},
  volume={10},
  number={7},
  pages={e0132735},
  year={2015},
  publisher={Public Library of Science}
}

@techreport{powell2011data,
  title={{Data Format Description Language (DFDL)} v1.0 Specification},
  author={Beckerle, Michael J and Hanson, Stephen M},
  year={2014},
  number = {GFD-P-R.207},
  institution={Open Grid Forum}
}

@inproceedings{brase2009datacite,
  title={Data{C}ite--{A} global registration agency for research data},
  author={Brase, Jan},
  booktitle={4th International Conference on Cooperation and Promotion of Information Resources in Science and Technology},
  pages={257--261},
  year={2009},
  organization={IEEE}
}

@article{bourne2015nih,
  title={The {NIH Big Data to Knowledge (BD2K)} initiative},
  author={Bourne, Philip E and Bonazzi, Vivien and Dunn, Michelle and Green, Eric D and Guyer, Mark and Komatsoulis, George and Larkin, Jennie and Russell, Beth},
  journal={Journal of the American Medical Informatics Association},
  volume={22},
  number={6},
  pages={1114--1114},
  year={2015},
  publisher={The Oxford University Press}
}

@article{Wilkinson2016,
  doi = {10.1038/sdata.2016.18},
  url-not-used = {http://dx.doi.org/10.1038/sdata.2016.18},
  year  = {2016},
  month = {mar},
  publisher = {Nature Publishing Group},
  volume = {3},
  pages = {160018},
  author = {Mark D. Wilkinson and Michel Dumontier and IJsbrand Jan Aalbersberg and Gabrielle Appleton and Myles Axton and Arie Baak and Niklas Blomberg and Jan-Willem Boiten and Luiz Bonino da Silva Santos and Philip E. Bourne and Jildau Bouwman and Anthony J. Brookes and Tim Clark and Merc{\`{e}} Crosas and Ingrid Dillo and Olivier Dumon and Scott Edmunds and Chris T. Evelo and Richard Finkers and Alejandra Gonzalez-Beltran and Alasdair J.G. Gray and Paul Groth and Carole Goble and Jeffrey S. Grethe and Jaap Heringa and Peter A.C 't Hoen and Rob Hooft and Tobias Kuhn and Ruben Kok and Joost Kok and Scott J. Lusher and Maryann E. Martone and Albert Mons and Abel L. Packer and Bengt Persson and Philippe Rocca-Serra and Marco Roos and Rene van Schaik and Susanna-Assunta Sansone and Erik Schultes and Thierry Sengstag and Ted Slater and George Strawn and Morris A. Swertz and Mark Thompson and Johan van der Lei and Erik van Mulligen and Jan Velterop and Andra Waagmeester and Peter Wittenburg and Katherine Wolstencroft and Jun Zhao and Barend Mons},
  title = {The {FAIR} Guiding Principles for scientific data management and stewardship},
  journal = {Scientific Data}
}

@incollection{Tabata2005,
   author = {Tabata, Koichi and Okada, Takeshi and Nagamori, Mitsuharu and Sakaguchi, Tetsuo and Sugimoto, Shigeo},
   title = {A collaboration model between archival systems to enhance the reliability of preservation by an enclose-and-deposit method},
   booktitle = {5th International Web Archiving Workshop},
   address = {Vienna, Austria},
   year = {2005}
}

@techreport{Kunze2015,
   author = {Kunze, J. and Littman, J. and Madden, L. and Summers, E. and Boyko, A. and Vargas, B.},
   title = {The {BagIt} File Packaging Format ({V}0.97)},
   institution = {Internet Engineering Task Force, Internet Draft (work in progress), draft-kunze-bagit-14.txt},
   year = {2017}
}

@misc{rfc4151,
  author="T. Kindberg and S. Hawke",
  title="{The 'tag' URI Scheme}",
  series="Request for Comments",
  number="4151",
  howpublished="RFC 4151 (Informational)",
  publisher="IETF",
  organization="Internet Engineering Task Force",
  year=2005,
  month=oct,
    url="http://www.ietf.org/rfc/rfc4151.txt",
}

@article{Toga2015,
  author = {Toga, Arthur W. and Foster, Ian and Kesselman, Carl and Madduri, Ravi and Chard, Kyle and Deutsch, Eric W. and Price, Nathan D. and Glusman, Gustavo and Heavner, Benjamin D. and Dinov, Ivo D.},
   title = {Big biomedical data as the key resource for discovery science},
   journal = {Journal of the American Medical Informatics Association},
  volume={22},
  number={6},
  pages={1126--1131},
   year = {2015}
}

@article{hettne2014structuring,
  title={Structuring research methods and data with the {Research Object} model: Genomics workflows as a case study},
  author={Hettne, Kristina M and Dharuri, Harish and Zhao, Jun and Wolstencroft, Katherine and Belhajjame, Khalid and Soiland-Reyes, Stian and Mina, Eleni and Thompson, Mark and Cruickshank, Don and Verdes-Montenegro, Lourdes and Julian Garrido and David de Roure and Oscar Corcho and Graham Klyne and Reinout van Schouwen and Peter A C 't Hoen and Sean Bechhofer and Carole Goble and Marco Roos},
  journal={J Biomed Semant},
  volume={5},
  number="41",
  year={2014},
  doi="10.1186/2041-1480-5-41"
}


@article{Belhajjame2015SuiteOntologies,
title = "Using a suite of ontologies for preserving workflow-centric {Research Objects}",
journal = "Web Semantics: Science, Services and Agents on the World Wide Web ",
volume = "32",
number = "",
pages = "16 - 42",
year = "2015",
note = "",
issn = "1570-8268",
doi = "10.1016/j.websem.2015.01.003",
url = {http://dx.doi.org/10.1016/j.websem.2015.01.003},
author = "Khalid Belhajjame and Jun Zhao and Daniel Garijo and Matthew Gamble and Kristina Hettne and Raul Palma and Eleni Mina and Oscar Corcho and Jos\'{e} Manuel G\'{o}mez-P\'{e}rez and Sean Bechhofer and Graham Klyne and Carole Goble",
}

@article{Goodman2014TenSimplerules,
    author = {Goodman, Alyssa AND Pepe, Alberto AND Blocker, Alexander W. AND Borgman, Christine L. AND Cranmer, Kyle AND Crosas, Merce AND Di Stefano, Rosanne AND Gil, Yolanda AND Groth, Paul AND Hedstrom, Margaret AND Hogg, David W. AND Kashyap, Vinay AND Mahabal, Ashish AND Siemiginowska, Aneta AND Slavkovic, Aleksandra},
    journal = {{PLoS} Comput Biol},
    publisher = {Public Library of Science},
    title = {Ten Simple Rules for the Care and Feeding of Scientific Data},
    year = {2014},
    month = {04},
    volume = {10},
    url-notused = {http://dx.doi.org/10.1371/journal.pcbi.1003542},
    pages = {1-5},
    abstract = {},
    number = {4},
    doi-notused = {10.1371/journal.pcbi.1003542}
}

@article{GonzalesBeltran2015Reproducibility,
    author = {Gonz\'{a}lez-Beltr\'{a}n, Alejandra AND Li, Peter AND Zhao, Jun AND Avila-Garcia, Maria Susana AND Roos, Marco AND Thompson, Mark AND van der Horst, Eelke AND Kaliyaperumal, Rajaram AND Luo, Ruibang AND Lee, Tin-Lap AND Lam, Tak-wah AND Edmunds, Scott C. AND Sansone, Susanna-Assunta AND Rocca-Serra, Philippe},
    journal = {{PLoS} {ONE}},
    publisher = {Public Library of Science},
    title = {From Peer-Reviewed to Peer-Reproduced in Scholarly Publishing: The Complementary Roles of Data Models and Workflows in Bioinformatics},
    year = {2015},
    month = {07},
    volume = {10},
    url-not-used = {http://dx.doi.org/10.1371/journal.pone.0127612},
    pages = {1-20},
    number = {7},
    doi = {10.1371/journal.pone.0127612}
}

@unpublished{McMurry2015,
  author       = {Julie McMurry and
                  Blomberg, Niklas and
                  Burdett, Tony and
                  Conte, Nathalie and
                  Dumontier, Michel and
                  Fellows, Donal K and
                  Gonzalez-Beltran, Alejandra and
                  Gormanns, Philipp and
                  Hastings, Janna and
                  Haendel, Melissa A and
                  Hermjakob, Henning and
                  Hériché, Jean-Karim and
                  Ison, Jon C and
                  Jimenez, Rafael C and
                  Jupp, Simon and
                  Juty, Nick and
                  Laibe, Camille and
                  Le Novère, Nicolas and
                  Malone, James and
                  Martin, Maria J and
                  McEntyre, Johanna R and
                  Morris, Chris and
                  Muilu, Juha and
                  Müller, Wolfgang and
                  Mungall, Christopher J and
                  Rocca-Serra, Philippe and
                  Sansone, Susanna-Assunta and
                  Sariyar, Murat and
                  Snoep, Jacky L and
                  Stanford, Natalie J and
                  Swainston, Neil and
                  Washington, Nicole and
                  Williams, Alan R and
                  Wolstencroft, Katherine and
                  Goble, Carole and
                  Parkinson, Helen},
  title        = {10 simple rules for design, provision, and reuse
                   of identifiers for web-based life science data},
  note         = {{Zenodo preprint}},
  publisher    = {Zenodo},
  month        = oct,
  year         = 2015,
  doi          = {10.5281/zenodo.31765},
  url          = {http://dx.doi.org/10.5281/zenodo.31765}
}

@inproceedings{pham2015ldv,
  title={{LDV}: Light-weight database virtualization},
  author={Pham, Quan and Malik, Tanu and Glavic, Boris and Foster, Ian},
  booktitle={31st International Conference on Data Engineering},
  pages={1179--1190},
  year={2015},
  organization={IEEE}
}

@article{foster11globus,
author = {Ian Foster},
title = {Globus {O}nline: Accelerating and Democratizing Science through Cloud-Based Services},
journal ={IEEE Internet Computing},
volume = {15},
number = {3},
issn = {1089-7801},
year = {2011},
pages = {70-73},
doi = {http://doi.ieeecomputersociety.org/10.1109/MIC.2011.64},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}

@article{song2010dnase,
  title={D{N}ase-seq: a high-resolution technique for mapping active gene regulatory elements across the genome from mammalian cells},
  author={Song, Lingyun and Crawford, Gregory E},
  journal={Cold Spring Harbor Protocols},
  volume={2010},
  number={2},
  pages={pdb--prot5384},
  year={2010},
  publisher={Cold Spring Harbor Laboratory Press}
}

@article{allen12saas,
 author = {Allen, Bryce and Bresnahan, John and Childers, Lisa and Foster, Ian and Kandaswamy, Gopi and Kettimuthu, Raj and Kordas, Jack and Link, Mike and Martin, Stuart and Pickett, Karl and Tuecke, Steven},
 title = {Software As a Service for Data Scientists},
 journal = {Commun. ACM},
 issue_date = {February 2012},
 volume = {55},
 number = {2},
 month = feb,
 year = {2012},
 issn = {0001-0782},
 pages = {81--88},
 numpages = {8},
 url = {http://doi.acm.org/10.1145/2076450.2076468},
 doi = {10.1145/2076450.2076468},
 acmid = {2076468},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

@TECHREPORT{handlesystem,
  author = {S. Sun and L. Lannom and B. Boesch},
  title = {Handle System Overview},
  institution = {Internet Engineering Task Force, Network Working Group},
  year = {2003},
  type = {{RFC}},
  number = {3650},
  month = {November},
  owner = {kyle},
  timestamp = {2014.12.06},
  url = {https://www.ietf.org/rfc/rfc3650.txt}
}

@Standard{oaiore,
  title =        {Open Archives Initiative Object Reuse and Exchange},
  organization = {Open Archives Initiative},
  author =       {C. Lagoze and H. Van de Sompel and P. Johnston and M. Nelson and R. Sanderson and S. Warner},
  howpublished = {\url{http://www.openarchives.org/ore/1.0/vocabulary}. Accessed August 1, 2016},
  month =        {October},
  year =         {2008}
}


@MISC{ezid,
  title = {{EZID}},
  howpublished = {\url{http://ezid.cdlib.org/}},
  note = {Web site. Accessed August 1, 2016},
}

@article{afgan16galaxy,
author = {Afgan, Enis and Baker, Dannon and van den Beek, Marius and Blankenberg, Daniel and Bouvier, Dave and Čech, Martin and Chilton, John and Clements, Dave and Coraor, Nate and Eberhard, Carl and Grüning, Björn and Guerler, Aysam and Hillman-Jackson, Jennifer and Von Kuster, Greg and Rasche, Eric and Soranzo, Nicola and Turaga, Nitesh and Taylor, James and Nekrutenko, Anton and Goecks, Jeremy}, 
title = {The {G}alaxy platform for accessible, reproducible and collaborative biomedical analyses: 2016 update},
volume = {44}, 
number = {W1}, 
pages = {W3-W10}, 
year = {2016}, 
doi = {10.1093/nar/gkw343}, 
abstract ={High-throughput data production technologies, particularly ‘next-generation’ DNA sequencing, have ushered in widespread and disruptive changes to biomedical research. Making sense of the large datasets produced by these technologies requires sophisticated statistical and computational methods, as well as substantial computational power. This has led to an acute crisis in life sciences, as researchers without informatics training attempt to perform computation-dependent analyses. Since 2005, the Galaxy project has worked to address this problem by providing a framework that makes advanced computational tools usable by non experts. Galaxy seeks to make data-intensive research more accessible, transparent and reproducible by providing a Web-based environment in which users can perform computational analyses and have all of the details automatically tracked for later inspection, publication, or reuse. In this report we highlight recently added features enabling biomedical analyses on a large scale.}, 
URL-notused = {http://nar.oxfordjournals.org/content/44/W1/W3.abstract}, 
eprint-notused = {http://nar.oxfordjournals.org/content/44/W1/W3.full.pdf+html}, 
journal = {Nucleic Acids Research} 
}

@article {toga15bdds,
	author = {Toga, Arthur W and Foster, Ian and Kesselman, Carl and Madduri, Ravi and Chard, Kyle and Deutsch, Eric W and Price, Nathan D and Glusman, Gustavo and Heavner, Benjamin D and Dinov, Ivo D and Ames, Joseph and Van Horn, John and Kramer, Roger and Hood, Leroy},
	title = {Big Biomedical data as the key resource for discovery science},
	year = {2015},
	volume = 22,
	number = 6,
	pages = {1126--31},
	doi = {10.1093/jamia/ocv077},
	publisher = {The Oxford University Press},
	abstract = {Modern biomedical data collection is generating exponentially more data in a multitude of formats. This flood of complex data poses significant opportunities to discover and understand the critical interplay among such diverse domains as genomics, proteomics, metabolomics, and phenomics, including imaging, biometrics, and clinical data. The Big Data for Discovery Science Center is taking an {\textquotedblleft}-ome to home{\textquotedblright} approach to discover linkages between these disparate data sources by mining existing databases of proteomic and genomic data, brain images, and clinical assessments. In support of this work, the authors developed new technological capabilities that make it easy for researchers to manage, aggregate, manipulate, integrate, and model large amounts of distributed data. Guided by biological domain expertise, the Center{\textquoteright}s computational resources and software will reveal relationships and patterns, aiding researchers in identifying biomarkers for the most confounding conditions and diseases, such as Parkinson{\textquoteright}s and Alzheimer{\textquoteright}s.},
	issn = {1067-5027},
	URL-notused = {http://jamia.oxfordjournals.org/content/early/2015/07/21/jamia.ocv077},
	eprint-notused = {http://jamia.oxfordjournals.org/content/early/2015/07/21/jamia.ocv077.full.pdf},
	journal = {Journal of the American Medical Informatics Association}
}


@article {Wimalaratne101279,
	author = {Wimalaratne, Sarala and Juty, Nick and Kunze, John and Jan{\'e}e, Greg and McMurry, Julie A and Beard, Niall and Jimenez, Rafael and Grethe, Jeffrey and Hermjakob, Henning and Clark, Tim},
	title = {Uniform Resolution of Compact Identifiers for Biomedical Data},
	year = {2018},
	doi = {10.1101/101279},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Compact identifiers have been widely used in biomedical informatics both formally and informally. They consist of two parts: 1) a unique prefix or namespace indicating the assigning authority and 2) a locally assigned database identifier sometimes called an accession number. The former is used to avoid global identifier collisions when integrating separately managed datasets that are run by different communities and consortia under a variety of autonomous data management systems and practices. This bi-partite identifier approach predates the invention of the Web, but can be leveraged to work more harmoniously with it. Identifiers.org and N2T.net are two meta-resolvers that take any given identifier from over 500 source databases and reliably redirect it to its original source on the Web. Identifiers.org is based at the European Molecular Biology Laboratory-European Bioinformatics Institute (EMBL-EBI) and serves the biomedical domain; whereas N2T.net (Name-to-Thing) is based at the California Digital Library (CDL), University of California Office of the President, and is domain-agnostic. Both resolvers, while derived from independently developed code bases, with different features and objectives, can now uniformly resolve compact identifiers using a set of common procedures and redirection rules. Here we report on significant further work by our teams toward a more unified approach to making compact identifiers available for long-term use in an ecosystem supporting formal citation of primary scholarly research data. This approach is intended to be robust beyond the operational and funding scope of any one organization, enabling long-term resolution of persistent archived data, whether it is cited in the literature, or is referenced in the web at large. We demonstrate that multiple resolvers with fundamentally different underlying code bases, organizational settings and international alignments, can readily support this approach. As part of this project we have deployed public, production-quality resolvers using a common registry of prefix-based redirection rules. We believe these products and our approach will be of significant help to publishers, authors and others implementing persistent, machine-resolvable citation of research data in compliance with emerging science policy recommendations and funder requirements.},
	URL = {https://www.biorxiv.org/content/early/2018/02/14/101279},
	eprint = {https://www.biorxiv.org/content/early/2018/02/14/101279.full.pdf},
	journal = {bioRxiv}
}