% This file was created with JabRef 2.5.
% Encoding: UTF8

@ARTICLE{Allen1979,
  author = {Allen, F. H. and Bellard, S. and Brice, M. D. and Cartwright, B.
	A. and Doubleday, A. and Higgs, H. and Hummelink, T. and Hummelink-Peters,
	B. G. and Kennard, O. and Motherwell, W. D. S. and Rodgers, J. R.
	and Watson, D. G.},
  title = {{The Cambridge Crystallographic Data Centre: computer-based search,
	retrieval, analysis and display of information}},
  journal = {Acta Crystallographica Section B},
  year = {1979},
  volume = {35},
  pages = {2331--2339},
  number = {10},
  month = {Oct},
  doi = {10.1107/S0567740879009249},
  url = {http://dx.doi.org/10.1107/S0567740879009249}
}

@ARTICLE{Berman2002,
  author = {Berman, Helen M. and Battistuz, Tammy and Bhat, T. N. and Bluhm,
	Wolfgang F. and Bourne, Philip E. and Burkhardt, Kyle and Feng, Zukang
	and Gilliland, Gary L. and Iype, Lisa and Jain, Shri and Fagan, Phoebe
	and Marvin, Jessica and Padilla, David and Ravichandran, Veerasamy
	and Schneider, Bohdan and Thanki, Narmada and Weissig, Helge and
	Westbrook, John D. and Zardecki, Christine},
  title = {{The Protein Data Bank}},
  journal = {Acta Crystallographica Section D},
  year = {2002},
  volume = {58},
  pages = {899--907},
  number = {6 Part 1},
  month = {Jun},
  doi = {10.1107/S0907444902003451},
  url = {http://dx.doi.org/10.1107/S0907444902003451}
}

@ARTICLE{Berman1992,
  author = {H. M. Berman and W. K. Olson and D. L. Beveridge and J. Westbrook
	and A. Gelbin and T. Demeny and S.-H. Hsieh and A. R. Srinivasan
	and B. Schneider},
  title = {The Nucleic Acid Database: A Comprehensive Relational Database of
	Three-Dimensional Structures of Nucleic Acids},
  journal = {Biophys. J.},
  year = {1992},
  volume = {63},
  pages = {751-759},
  owner = {saulius},
  timestamp = {2011.07.31}
}

@ARTICLE{Bernstein1977,
  author = {F. C. Bernstein and T. F. Koetzle and G. J. Williams and E. F. Meyer
	and M. D. Brice and J. R. Rodgers and O. Kennard and T. Shimanouchi
	and M. Tasumi},
  title = {The Protein Data Bank: a computer-based archival file for macromolecular
	structures.},
  journal = {J. Mol. Biol.},
  year = {1977},
  volume = {112},
  pages = {535--542},
  number = {3},
  month = {May},
  keywords = {Computers; Great Britain; Information Systems; Japan; Protein Conformation;
	Proteins; United States},
  owner = {bricehoffmann},
  pmid = {875032},
  timestamp = {2009.02.13}
}

@BOOK{Collins-Sussman2008,
  title = {Version Control with Subversion},
  publisher = {O'Reilly Media},
  year = {2008},
  author = {Collins-Sussman, Ben and Fitzpatrick, Brian W and Pilato, C Michael},
  url = {\href{http://svnbook.red-bean.com/} {http://svnbook.red-bean.com/}}
}

@PHDTHESIS{Day2008,
  author = {Nicholas Elliot Day},
  title = {Automated Analysis and Validation of Open Chemical Data},
  school = {University of Cambridge},
  year = {2008},
  month = {nov},
  abstract = {Methods to automatically extract Open Data from the chemical literature,
	validate it, and use it to validate theory are examined.
	
	Chemical identifiers which assist the automatic location of chemical
	struc- tures using commercial Web search engines are investigated.
	The IUPAC International Chemical Idenfitifer (InChI) gives almost
	100% recall and pre- cision, though is shown to be too long for present
	search engines. A com- bination of InChI and InChIKey, a shorter,
	fixed-length hash of the InChI string, is concluded to be the best
	current method of identifying structures.
	
	The proportion of published, Open Crystallographic Information Files
	(CIFs) that are valid with respect to the specification is shown
	to be im- proving, and is around 99% in 2007. The error rate in the
	conversion of valid CIFs to Chemical Markup Language (CML) is less
	than 0.2%. The machine generation of connection tables from CIFs
	requires many heuristics, and in some cases it is impossible to deduce
	the exact connection table.
	
	CrystalEye, a fully-automated system for the reformulation of the
	frag- mented crystallographic Web into a structured XML-based repository
	is de- scribed. Published, Open CIFs can be located and aggregated
	programmat- ically with almost 100% recall. It is shown that, by
	converting CIF data to CML, software can be created to use the latest
	Web standards and tech- nologies to enhance the ability of Web users
	to browse, find, keep updated, download and reuse the latest published
	crystallography.
	
	A workflow for the high-throughput calculation of solid-state geometry
	using a semi-empirical method is described. A wide-range of organic
	and inorganic systems provided by CrystalEye are used to test both
	the data and the method. Several errors in the method are discovered,
	many of which can be attributed to the parameterization process.
	
	An Open NMR experiment to perform high-throughput prediction of 13
	C chemical shifts using a GIAO protocol is described. The data and
	analysis were provided on publicly-available webpages to enable crowdsourcing,
	which assisted in discovering an error rate of 6.1% in the starting
	data. The protocol was refined during the work and shown to have
	an average unsigned error of 2.24ppm for 13 C nuclei of small, rigid
	molecules; comparable to the errors observed elsewhere for general
	structures using HOSE and Neural Network methods.},
  file = {2008_Day_phdthesis.pdf:by-author/D/Day/2008_Day_phdthesis.pdf:PDF},
  keywords = {data management, xray-crystallography, crystallography, NMR},
  owner = {saulius},
  timestamp = {2013.09.19},
  url = {https://www.repository.cam.ac.uk/bitstream/handle/1810/238467/ned24-thesis-corrected-1_A1b.pdf?sequence=1}
}

@ARTICLE{Downs2003,
  author = {Downs, RT and Hall-Wallace, M},
  title = {The American Mineralogist crystal structure database},
  journal = {American Mineralogist},
  year = {2003},
  volume = {88},
  pages = {247-250}
}

@ARTICLE{Grazulis2009,
  author = {Gra{\v{z}}ulis, Saulius and Chateigner, Daniel and Downs, Robert
	T. and Yokochi, A. F. T. and Quir{\'{o}}s, Miguel and Lutterotti,
	Luca and Manakova, Elena and Butkus, Justas and Moeck, Peter and
	Le Bail, Armel},
  title = {{Crystallography Open Database {--} an open-access collection of
	crystal structures}},
  journal = {Journal of Applied Crystallography},
  year = {2009},
  volume = {42},
  pages = {726--729},
  number = {4},
  month = {Aug},
  doi = {10.1107/S0021889809016690},
  url = {http://dx.doi.org/10.1107/S0021889809016690}
}

@ARTICLE{Grazulis2012,
  author = {Gražulis, Saulius and Daškevič, Adriana and Merkys, Andrius and Chateigner,
	Daniel and Lutterotti, Luca and Quirós, Miguel and Serebryanaya,
	Nadezhda R. and Moeck, Peter and Downs, Robert T. and Le Bail, Armel},
  title = {{C}rystallography {O}pen {D}atabase ({COD}): an open-access collection
	of crystal structures and platform for world-wide collaboration},
  journal = {Nucleic Acids Research},
  year = {2012},
  volume = {40},
  pages = {D420-D427},
  number = {D1},
  month = {Jan},
  abstract = {Using an open-access distribution model, the Crystallography Open
	Database (COD, http://www.crystallography.net) collects all known
	‘small molecule / small to medium sized unit cell’ crystal structures
	and makes them available freely on the Internet. As of today, the
	COD has aggregated ∼150 000 structures, offering basic search capabilities
	and the possibility to download the whole database, or parts thereof
	using a variety of standard open communication protocols. A newly
	developed website provides capabilities for all registered users
	to deposit published and so far unpublished structures as personal
	communications or pre-publication depositions. Such a setup enables
	extension of the COD database by many users simultaneously. This
	increases the possibilities for growth of the COD database, and is
	the first step towards establishing a world wide Internet-based collaborative
	platform dedicated to the collection and curation of structural knowledge.},
  doi = {10.1093/nar/gkr900},
  file = {:by-author/G/Gražulis/2012_Gražulis_D420.pdf:PDF},
  owner = {saulius},
  timestamp = {2011.12.29},
  url = {http://nar.oxfordjournals.org/content/40/D1/D420.abstract}
}

@ARTICLE{Grosse-Kunstleve2002,
  author = {Grosse-Kunstleve, Ralf W. and Sauter, Nicholas K. and Moriarty, Nigel
	W. and Adams, Paul D.},
  title = {{The {\it Computational Crystallography Toolbox}: crystallographic
	algorithms in a reusable software framework}},
  journal = {Journal of Applied Crystallography},
  year = {2002},
  volume = {35},
  pages = {126--136},
  number = {1},
  month = {Feb},
  doi = {10.1107/S0021889801017824},
  url = {http://dx.doi.org/10.1107/S0021889801017824}
}

@ARTICLE{Hall1991,
  author = {Hall, S. R. and Allen, F. H. and Brown, I. D.},
  title = {{The crystallographic information file (CIF): a new standard archive
	file for crystallography}},
  journal = {Acta Crystallographica Section A},
  year = {1991},
  volume = {47},
  pages = {655--685},
  number = {6},
  month = {Nov},
  doi = {10.1107/S010876739101067X},
  url = {http://dx.doi.org/10.1107/S010876739101067X}
}

@ARTICLE{Kabekkodu2002,
  author = {Kabekkodu, SN and Faber, J and Fawcett, T},
  title = {New Powder Diffraction File (PDF-4) in relational database format:
	advantages and data-mining capabilities},
  journal = {Acta Crystallographica, Section B},
  year = {2002},
  volume = {58},
  pages = {333-7}
}

@ARTICLE{Kaduk2002,
  author = {Kaduk, James A},
  title = {Use of the Inorganic Crystal Structure Database as a problem solving
	tool},
  journal = {Acta Crystallogr B},
  year = {2002},
  volume = {58},
  pages = {370-9},
  number = {Pt 3 Pt 1},
  month = {Jun},
  abstract = {The information in the Inorganic Crystal Structure Database (ICSD)
	can be used to determine the structures of new compounds by analogy;
	this database is thus a useful tool for practical problem solving.
	A model for the structure of (NH(4))Fe(CO(3))(OH)(2) [Cmcm, a = 6.6154
	(6), b = 12.0639 (10), c = 6.0263 (5) A, Z = 4] was found by searching
	the ICSD for compounds with C-centered orthorhombic cells and containing
	C, H, N and O. [Al(H(2)O)(6)](2)[Al(H(2)O)(5)(SO(4))](2)-(H(3)O)(2)(SO(4))(5)
	[P1;, a = 12.5881 (5), b = 13.0726 (5), c = 7.3354 (2) A, alpha =
	108.162 (2), beta = 70.536 (2), gamma = 112.658 (2) degrees, Z =
	1] is isostructural to a Cr compound of the same stoichiometry, which
	was located by searching on the formula type ANX = A4B7X52. Suitable
	models for MgCl(2)(H(2)O)(4) [P2(1)/c, a = 5.9001 (9), b = 7.2709
	(7), c = 8.4199 (7) A, beta = 111.007 (15) degrees, Z = 2], MgCl(2)(H(2)O)(2)
	[C2/m, a = 7.3886 (29), b = 8.5498 (24), c = 3.6488 (17) A, beta
	= 98.96 (3) degrees, Z = 2], and MgCl(2)(H(2)O) [Pnma, a = 8.899
	(7), b = 3.6339 (20), c = 11.398 (8) A, Z = 4] were located by combining
	searches on chemistry and formula type. Quantum-chemical calculations
	were performed on all five structures to locate the H-atom positions
	and to obtain quantitative understanding of the hydrogen bonding
	important in all the structures.},
  address = {BP Chemicals, PO Box 3011, MC F-9, Naperville, IL 60566, USA. kadukja@bp.com},
  bibliography-url = {http://view.ncbi.nlm.nih.gov/pubmed/12037358},
  isbn = {0108-7681}
}

@INCOLLECTION{Downs2006,
  author = {Rajan, H. and Uchida, H. and Bryan, D.L. and Swaminathan, R. and
	Downs, R.T. and Hall-Wallace, M},
  title = {Building the American Mineralogist Crystal Structure Database: A
	recipe for construction of a small Internet database},
  booktitle = {Geoinformatics: Data to Knowledge},
  year = {2006},
  editor = {Sinha, A.K.},
  volume = {397},
  pages = {73-80},
  journal = {Geological Society of America Special Paper}
}

@ARTICLE{Todorov2008,
  author = {Todorov, Georgi and Bernstein, Herbert J.},
  title = {{{\it VCIF2}: extended CIF validation software}},
  journal = {Journal of Applied Crystallography},
  year = {2008},
  volume = {41},
  pages = {808--810},
  number = {4},
  month = {Aug},
  doi = {10.1107/S002188980801385X},
  url = {http://dx.doi.org/10.1107/S002188980801385X}
}

@ARTICLE{Wang2010,
  author = {Wang, Yanli and Bolton, Evan and Dracheva, Svetlana and Karapetyan,
	Karen and Shoemaker, Benjamin A. and Suzek, Tugba O. and Wang, Jiyao
	and Xiao, Jewen and Zhang, Jian and Bryant, Stephen H.},
  title = {An overview of the PubChem BioAssay resource},
  journal = {Nucleic Acids Research},
  year = {2010},
  volume = {38},
  pages = {D255-D266},
  number = {suppl 1},
  abstract = {The PubChem BioAssay database (http://pubchem.ncbi.nlm.nih.gov) is
	a public repository for biological activities of small molecules
	and small interfering RNAs (siRNAs) hosted by the US National Institutes
	of Health (NIH). It archives experimental descriptions of assays
	and biological test results and makes the information freely accessible
	to the public. A PubChem BioAssay data entry includes an assay description,
	a summary and detailed test results. Each assay record is linked
	to the molecular target, whenever possible, and is cross-referenced
	to other National Center for Biotechnology Information (NCBI) database
	records. ‘Related BioAssays’ are identified by examining the assay
	target relationship and activity profile of commonly tested compounds.
	A key goal of PubChem BioAssay is to make the biological activity
	information easily accessible through the NCBI information retrieval
	system-Entrez, and various web-based PubChem services. An integrated
	suite of data analysis tools are available to optimize the utility
	of the chemical structure and biological activity information within
	PubChem, enabling researchers to aggregate, compare and analyze biological
	test results contributed by multiple organizations. In this work,
	we describe the PubChem BioAssay database, including data model,
	bioassay deposition and utilities that PubChem provides for searching,
	downloading and analyzing the biological activity information contained
	therein.},
  doi = {10.1093/nar/gkp965},
  eprint = {http://nar.oxfordjournals.org/content/38/suppl_1/D255.full.pdf+html},
  url = {http://nar.oxfordjournals.org/content/38/suppl_1/D255.abstract}
}

@ARTICLE{White2002,
  author = {White, Peter S and Rodgers, John R and Le Page, Yvon},
  title = {CRYSTMET: a database of the structures and powder patterns of metals
	and intermetallics},
  journal = {Acta Crystallogr B},
  year = {2002},
  volume = {58},
  pages = {343-8},
  number = {Pt 3 Pt 1},
  month = {Jun},
  abstract = {CRYSTMET is a database of critically evaluated crystallographic data
	for metals (including alloys, intermetallics and minerals) and associated
	bibliographic, chemical and physical information. Also included are
	simulated powder diffraction patterns for all of the entries. The
	database currently contains almost 70,000 entries and covers the
	literature exhaustively from 1922 to the present. The database is
	available on CD-ROM with search/analysis software for use on personal
	computers. This software can be used with any database in the appropriate
	format; currently CRYSTMET and the ICSD databases are available.
	This paper describes the database content, the procedures used in
	its construction, the software made available to the user and a number
	of potential uses for the data.},
  address = {Department of Chemistry, CB 3290 Venable Hall, University of North
	Carolina at Chapel Hill, Chapel Hill, NC 27599-3290, USA. pwhite@pyrite.chem.unc.edu},
  bibliography-url = {http://view.ncbi.nlm.nih.gov/pubmed/12037354},
  isbn = {0108-7681}
}

@TECHREPORT{Zucker2006,
  author = {Lynne G. Zucker and Michael R. Darby and Jonathan Furner and Robert
	C. Liu and Hongyan Ma},
  title = {Minerva Unbound: Knowledge Stocks, Knowledge Flows and New Knowledge
	Production},
  institution = {National Bureau of Economic Research},
  year = {2006},
  type = {Working Paper},
  number = {12669},
  month = {November},
  abstract = {The rate of regional growth of new knowledge in the field of nanotechnology,
	as measured by counts of articles and patents in the open-access
	digital library NanoBank, is shown to be positively affected both
	by the size of existing regional stocks of recorded knowledge in
	all scientific fields, and the extent to which tacit knowledge in
	all fields flows between institutions of different organizational
	types. The level of federal funding has a large, robust impact on
	both publication and patenting. The data provide further support
	for the cumulative advantage model of knowledge production, and for
	ongoing efforts to institutionalize channels through which cross-organizational
	collaboration may be achieved.},
  series = {Working Paper Series},
  url = {http://www.nber.org/papers/w12669}
}

@ELECTRONIC{Perl2008,
  year = {2008},
  title = {Perl.org},
  note = {accessed \mbox{2011-10-20}},
  url = {http://www.perl.org/},
  abstract = {Perl.com includes resources on downloading and installing Perl, a
	six-part tutorial on learning Perl, Perl articles, and Perl weblogs
	to help new and experienced programmers refine their skills, solve
	problems, and contribute to the worldwide Perl community},
  key = {Perl},
  publisher = {O’Reilly Media}
}

@MISC{Rsync2008,
  title = {Rsync},
  year = {2008},
  note = {accessed \mbox{2008-09-01}},
  key = {Rsync},
  url = {\href{http://samba.anu.edu.au/rsync/} {http://samba.anu.edu.au/rsync/}}
}

