datacite-mapping 0.1.15 → 0.1.16

data/spec/data/dash1-datacite-xml/dataone-ark+=c5146=r3mw2v-mrt-datacite.xml

@@ -0,0 +1,33 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Lake, Sherry</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>BSEL Shelflist</title>
+  </titles>
+  <publisher>DataONE</publisher>
+  <publicationYear>2014</publicationYear>
+  <subjects>
+    <subject>Library</subject>
+    <subject>Engineering</subject>
+  </subjects>
+  <contributors>
+    <contributor contributorType="DataManager">
+      <contributorName>Lake, Sherry</contributorName>
+    </contributor>
+  </contributors>
+  <relatedIdentifiers/>
+  <resourceType resourceTypeGeneral="Dataset">Dataset</resourceType>
+  <sizes>
+    <size>77194</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="http://creativecommons.org/publicdomain/zero/1.0/">Creative Commons Public Domain Dedication (CC0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">Shelflist for the Brown Science and Engineering Library Weeding Project</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/dataone-ark+=c5146=r3np4v-mrt-datacite.xml

@@ -0,0 +1,40 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Kosenkov, Alexandr</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>IDEA Data API Specification</title>
+  </titles>
+  <publisher>DataONE</publisher>
+  <publicationYear>2016</publicationYear>
+  <subjects>
+    <subject>IDEA</subject>
+    <subject>Moorea</subject>
+  </subjects>
+  <contributors>
+    <contributor contributorType="DataManager">
+      <contributorName>Kosenkov, Alex</contributorName>
+    </contributor>
+    <contributor contributorType="Funder">
+      <contributorName>Alexandr Kosenkov</contributorName>
+    </contributor>
+  </contributors>
+  <relatedIdentifiers>
+    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">mooreaidea.org</relatedIdentifier>
+  </relatedIdentifiers>
+  <resourceType resourceTypeGeneral="Text">Text</resourceType>
+  <sizes>
+    <size>716</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="http://creativecommons.org/publicdomain/zero/1.0/">Creative Commons Public Domain Dedication (CC0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">The specification of IDEA Data API.</description>
+    <description descriptionType="Methods">Typing</description>
+    <description descriptionType="Other">0</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/dataone-ark+=c5146=r3pp45-mrt-datacite.xml

@@ -0,0 +1,47 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Sun, Wu</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Maseyk, Kadmiel</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Lett, Céline</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Seibt, Ulli</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>Data from Sun, W., Maseyk, K., Lett, C. and Seibt, U. (2016). Litter dominates surface fluxes of carbonyl sulfide (COS) in a Californian oak woodland</title>
+  </titles>
+  <publisher>DataONE</publisher>
+  <publicationYear>2016</publicationYear>
+  <subjects>
+    <subject>carbonyl sulfide (COS)</subject>
+    <subject>soil COS flux</subject>
+    <subject>litter COS flux</subject>
+    <subject>drying-rewetting effects</subject>
+    <subject>mediterranean ecosystem</subject>
+    <subject>COS diffusion-reaction model</subject>
+  </subjects>
+  <contributors>
+    <contributor contributorType="DataManager">
+      <contributorName>SUN, WU</contributorName>
+    </contributor>
+    <contributor contributorType="Funder">
+      <contributorName>European Research Council (ERC); UC Institute for the Study of Ecological and Evolutionary Climate Impacts (ISEECI); China Scholarship Council (CSC)</contributorName>
+    </contributor>
+  </contributors>
+  <relatedIdentifiers/>
+  <resourceType resourceTypeGeneral="Dataset">Dataset</resourceType>
+  <sizes>
+    <size>2024713</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="http://creativecommons.org/publicdomain/zero/1.0/">Creative Commons Public Domain Dedication (CC0)</rights>
+  </rightsList>
+  <descriptions/>
+</resource>

data/spec/data/dash1-datacite-xml/dataone-ark+=c5146=r3rp4s-mrt-datacite.xml

@@ -0,0 +1,34 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Chow, Edmond</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>Hitachi S4800</title>
+  </titles>
+  <publisher>DataONE</publisher>
+  <publicationYear>2014</publicationYear>
+  <subjects>
+    <subject>SEM </subject>
+    <subject>Hitachi S4800</subject>
+  </subjects>
+  <contributors>
+    <contributor contributorType="DataManager">
+      <contributorName>Chow, Edmond</contributorName>
+    </contributor>
+  </contributors>
+  <relatedIdentifiers/>
+  <resourceType resourceTypeGeneral="Image">Image</resourceType>
+  <sizes>
+    <size>1428290</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="http://creativecommons.org/publicdomain/zero/1.0/">Creative Commons Public Domain Dedication (CC0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract"/>
+    <description descriptionType="Methods"/>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/dataone-ark+=c5146=r3tg63-mrt-datacite.xml

@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Batista, Andre</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>Rain Gauge Rainfall Collection Data obtained at 620 Sao Bento Street, Guarulhos, Sao Paulo, Brazil, Zip Code 07070-000, from Aug. 24, 2015 to Nov, 24, 2015</title>
+  </titles>
+  <publisher>DataONE</publisher>
+  <publicationYear>2015</publicationYear>
+  <subjects>
+    <subject>Environmental Informatics</subject>
+    <subject>Rain Gauge</subject>
+  </subjects>
+  <contributors>
+    <contributor contributorType="DataManager">
+      <contributorName>Filipe, André</contributorName>
+    </contributor>
+  </contributors>
+  <relatedIdentifiers/>
+  <resourceType resourceTypeGeneral="Dataset">Dataset</resourceType>
+  <sizes>
+    <size>25735</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="http://creativecommons.org/publicdomain/zero/1.0/">Creative Commons Public Domain Dedication (CC0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">The dataset shows the amount of rainfall collected in a rain gauge outside my house in Guarulhos, Sao Paulo, Brazil, from Aug. 24,2015 to Nov. 24, 2015. Data were gathered in order to test the following hypothesis: In Guarulhos-SP (Brazil), between the months of August and November (08/24/2015-11/24/2015), we will have a slightly fall in the amount of rain in comparison with 2014 and 2013 (not together) over the same period. Since Brazil has been in an intensive drought over the last two years, I suppose that we will not have large amounts of rain.</description>
+    <description descriptionType="Methods">- Rainfall data was record at 9:00 AM (UTC-3) every day.
+- Rainfall data was recorded in millimeters and it was converted into inches
+- Rain gauge was cleaned after recording</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/ucb-ark+=b6078=d1159q-mrt-datacite.xml

@@ -0,0 +1,53 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Bruhn, Daniel</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Lowe, John</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Mortensen, David</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Yu, Dominic</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>Sino-Tibetan Etymological Dictionary and Thesaurus Database Software</title>
+  </titles>
+  <publisher>UC Berkeley</publisher>
+  <publicationYear>2015</publicationYear>
+  <subjects>
+    <subject>historical linguistics</subject>
+    <subject>sino-tibetan</subject>
+    <subject>tibeto-burman</subject>
+    <subject>lexicography</subject>
+    <subject>database</subject>
+    <subject>mysql</subject>
+    <subject>perl</subject>
+    <subject>php</subject>
+    <subject>latex</subject>
+    <subject>svn</subject>
+  </subjects>
+  <contributors>
+    <contributor contributorType="Funder">
+      <contributorName>National Science Foundation. Division of Behavioral and Cognitive Sciences</contributorName>
+    </contributor>
+  </contributors>
+  <relatedIdentifiers>
+    <relatedIdentifier relatedIdentifierType="URL" relationType="Documents">stedt.berkeley.edu</relatedIdentifier>
+  </relatedIdentifiers>
+  <resourceType resourceTypeGeneral="Software">Software</resourceType>
+  <sizes>
+    <size>477531112</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International (CC-BY 4.0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">several software suites which support access to the STEDT database.  These are written in PERL and PHP, and present different capabilities and dimensions of this linguistic data.  This object is a compressed archive of the svn code repository for the project as of January 5, 2015. The active repository is now on GitHub at https://github.com/stedt-project/sss.</description>
+    <description descriptionType="Other">BCS-1028192</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/ucb-ark+=b6078=d17g6j-mrt-datacite.xml

@@ -0,0 +1,50 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Swanson-Hysell, Nicholas</creatorName>
+      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://www.orcid.org">0000-0003-3215-4648</nameIdentifier>
+    </creator>
+    <creator>
+      <creatorName>Burgess, Seth</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Maloof, Adam</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Bowring, Samuel</creatorName>
+      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://www.orcid.org">0000-0001-9722-469X</nameIdentifier>
+    </creator>
+  </creators>
+  <titles>
+    <title>Magmatic activity and plate motion during the latent stage of Midcontinent Rift development</title>
+  </titles>
+  <publisher>UC Berkeley</publisher>
+  <publicationYear>2015</publicationYear>
+  <subjects>
+    <subject>Midcontinent Rift</subject>
+    <subject>Large Igneous Province</subject>
+    <subject>U-Pb geochronology</subject>
+    <subject>paleomagnetism</subject>
+    <subject>Mamainse Point</subject>
+    <subject>geology</subject>
+    <subject>Mesoproterozoic</subject>
+  </subjects>
+  <relatedIdentifiers>
+    <relatedIdentifier relatedIdentifierType="URL" relationType="IsDocumentedBy">http://escholarship.org/uc/item/989179cs</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsDocumentedBy">10.1130/G35271.1</relatedIdentifier>
+  </relatedIdentifiers>
+  <resourceType resourceTypeGeneral="Collection">Collection</resourceType>
+  <rightsList>
+    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International (CC-BY 4.0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">The Keweenawan Midcontinent Rift of North America records significant continental rifting between ca. 1110 and 1085 Ma, and preserves the most detailed paleomagnetic record of plate motion of any continent in Precambrian time. U/Pb dates from extrusive and intrusive rocks of the western Lake Superior Basin suggest a latent stage of reduced magmatic activity from ca. 1106 to 1100 Ma that places constraints on the dynamics of rift development and the record of plate motion. However, it has remained unclear whether this stage is a feature of the entire &gt;2500-km-long rift. The succession of picritic and basaltic lava flows at Mamainse Point in the eastern Lake Superior Basin may be the most continuous and best exposed record of rift-related volcanism and magnetic reversals, but its age and duration relative to the latent stage has been uncertain due to a lack of radioisotopic dates. We present a weighted mean 206Pb/238U date of 1100.36 ± 0.25 Ma on zircon crystals isolated from a newly discovered tuff within the upper reversed polarity portion of the stratigraphy below the Great Conglomerate. This date indicates that eruptive activity at Mamainse Point continued during the interval of diminished magmatic activity in the western Lake Superior Basin. This result strengthens the chronostratigraphic framework of rift development while explaining the preservation of additional geomagnetic reversals at Mamainse Point and the record of progressively decreasing paleomagnetic inclination that is indicative of rapid paleogeographic change.</description>
+    <description descriptionType="Methods">The Data folder contains three files:
+      MP_Pmag_Summary.xlsx: This excel spreadsheet has all of the site mean data used in the study. There are four sheets within the spreadsheet (1) the latex formatted text that was used to generated the table in the GSA data repository; (2) an interactive worksheet where Fisher means can be calculated from the flow means; (3) a sheet with preliminary formatting for the MagIC database and (4) data in the format that was exported for the Mamainse_Point_data.csv file.
+      Mamainse_Point_data.csv: This csv file contains the flow (i.e. site) mean paleomagnetic data as well as the locations of the flows stratigraphically and geographically (lat, long is in WGS84). These data are imported and analyzed in the IPython notebook.
+      NSVGsubset_VGP.txt, SCV_VGP.txt, SI_upperthird_VGP.txt: Text files used for comparitive analysis in the IPython notebook. See paper text for more details.
+      The Code folder contains an IPython notebook that contains statistical data analysis and plotting associated with paleomagnetic data in the the manuscript. In addition to the IPython notebook, the folder contains the pmag.py, pmagplotlib.py, and pmagpyrc.py libraries of PmagPy version 2.206 as well as a library IPmag.py that modifies some of the interactive programs of PmagPy for use in the IPython environment in addition to providing some new functions. This folder also contains a PDF version of notebook to be viewed outside of the IPython generated using nbconvert. Note that the IPython notebook can also be viewed online without an IPython installation at this link where it is rendered better than in the PDF output:
+      http://nbviewer.ipython.org/github/Swanson-Hysell/2014_Swanson-Hysell-et-al_Mamainse/blob/master/Code/Mamainse_Data_Analysis.ipynb</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/ucb-ark+=b6078=d1c88g-mrt-datacite.xml

@@ -0,0 +1,47 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>Swanson-Hysell, Nicholas</creatorName>
+      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://www.orcid.org">0000-0003-3215-4648</nameIdentifier>
+    </creator>
+    <creator>
+      <creatorName>Vaughn, Angus</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Mustain, Monica</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Asp, Kristofer</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>Confirmation of progressive plate motion during the Midcontinent Rift’s early magmatic stage from the Osler Volcanic Group, Ontario, Canada</title>
+  </titles>
+  <publisher>UC Berkeley</publisher>
+  <publicationYear>2015</publicationYear>
+  <subjects>
+    <subject>paleomagnetism</subject>
+    <subject>Midcontinent Rift</subject>
+    <subject>paleogeography</subject>
+    <subject>geomagnetic field</subject>
+  </subjects>
+  <relatedIdentifiers>
+    <relatedIdentifier relatedIdentifierType="URL" relationType="IsDocumentedBy">http://escholarship.org/uc/item/9qx4j3zq</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsDocumentedBy">10.1002/2013GC005180</relatedIdentifier>
+  </relatedIdentifiers>
+  <resourceType resourceTypeGeneral="Collection">Collection</resourceType>
+  <rightsList>
+    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International (CC-BY 4.0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">As the supercontinent Rodinia was assembling ca. 1.1 billion years ago, there was extensive magmatism on at least five Proterozoic continents including the development of the North American Midcontinent Rift. New paleomagnetic data from 84 lava flows of the Osler Volcanic Group of the Midcontinent Rift reveal that there was a significant and progressive decrease in inclination between the initiation of extrusive volcanism in the region (ca. 1110 Ma) and ca. 1105 ± 2 Ma (during the “early stage” of rift development). Paleomagnetic poles can be calculated for the lower portion of the reversed Osler Volcanic Group (40.9°N, 218.6°E, A95 = 4.8°, N = 30) and the upper portion of the reversed Osler Volcanic Group (42.5°N, 201.6°E, A95 = 3.7°, N = 59; this pole can be assigned the age of ca. 1105 ± 2 Ma). This result is a positive test of the hypothesis that there was significant plate motion during the early stage of rift development. In addition to being a time of widespread volcanism on Laurentia and other continents, this interval of the late Mesoproterozoic was characterized by rapid paleogeographic change.</description>
+    <description descriptionType="Methods">The 2014_Osler_data folder contains these files:
+      Simpson_Island_alldata.xlsx: This excel spreadsheet has all of the specimen level data and details the flow mean calculations.
+      SimpsonIsland_OslerData.csv: This csv file contains the flow (i.e. site) mean paleomagnetic data as well as the locations of the flows stratigraphically and geographically (lat, long is in WGS84).
+      Halls1974_data.csv: This csv file contains data from the Halls (1974) study of the Osler Volcanics.
+      Tauxe2009a_data.csv: This csv file contains data from the Tauxe and Kodama (2009) study of the North Shore Volcanic Group.
+      The 2014_Osler_Manuscript folder contains the manuscript and figure files. The source .tex file and individual figure files are in the folder along with the compiled .pdf file.
+      The 2014_Osler_Code folder contains an IPython notebook with all of the statistical data analysis and plotting for the manuscript. In addition to the IPython notebook, the folder contains the pmag.py, and pmagplotlib.py libraries of PmagPy version 2.206 as well as a newly developed library IPmag.py that modifies some of the interactive programs of PmagPy for use in the IPython environment in addition to providing new functions. This folder also contains a PDF version of notebook to be viewed outside of the IPython that is the supporting online material to the G^3 manuscript. Note that the IPython notebook can also be viewed online as rendered html without an IPython installation at this link: http://nbviewer.ipython.org/urls/raw.github.com/Swanson-Hysell/2014_Swanson-Hysell-et-al_Osler/master/2014_Osler_Code/2014_Osler_Data_Analysis.ipynb</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/ucb-ark+=b6078=d1cc74-mrt-datacite.xml

@@ -0,0 +1,71 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI">10.6078/D1CC74</identifier>
+  <creators>
+    <creator>
+      <creatorName>Srouji, John</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Xu, Anting</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Park, Annsea</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Kirsch, Jack</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Brenner, Steven</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>The Evolution of Function within the Nudix Superfamily</title>
+  </titles>
+  <publisher>UC Berkeley</publisher>
+  <publicationYear>2015</publicationYear>
+  <subjects>
+    <subject>hydrolase</subject>
+    <subject>homoplasy</subject>
+    <subject>Nudix</subject>
+    <subject>sequence alignment</subject>
+    <subject>structural alignment</subject>
+  </subjects>
+  <relatedIdentifiers>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d17p4v</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d13w2x</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1059d</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1vc7g</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1qp46</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1kw28</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1g59r</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1bc7t</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d16p4j</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1301k</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1z593</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1tg6t</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/d1pp4w</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1K01X</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1F59F</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D19G65</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D15P47</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D12018</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1X59S</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1SG6H</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1NP4K</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1J01M</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1D594</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D18G6V</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D14S3K</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1101Z</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasPart">10.6078/D1W884</relatedIdentifier>
+  </relatedIdentifiers>
+  <resourceType resourceTypeGeneral="Collection">Data and software</resourceType>
+  <sizes>
+    <size>292902042</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International (CC-BY 4.0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">The Nudix superfamily encompasses over 80,000 protein domains from all three domains of life. These proteins fall into four general functional classes: isopentenyl diphosphate isomerases (IDIs), adenine/guanine mismatch-specific adenine glycosylases (A/G-specific adenine glycosylases), pyrophosphohydrolases, and non-enzymatic activities such as protein/protein interaction and transcriptional regulation. The largest group, pyrophosphohydrolases, encompasses more than 100 distinct hydrolase specificities. To understand the evolution of this vast number of activities, we assembled and analyzed experimental and structural data for 205 Nudix proteins collected from the literature. We corrected erroneous functions or provided more appropriate descriptions for 53 annotations described in the Gene Ontology Annotation database in this family, and propose 275 new experimentally-based annotations. We manually constructed structure-guided sequence alignment of 78 Nudix proteins. Using the structural alignment as a seed, we then made an alignment of 347 “select” Nudix domains, curated from structurally determined, functionally characterized, or phylogenetically important Nudix domains. Based on our review of Nudix pyrophosphohydrolase structures and specificities, we further analyzed a loop region downstream of the Nudix hydrolase motif previously shown to contact the substrate molecule and possess known functional motifs. This loop region provides a potential structural basis for the functional radiation and evolution of substrate specificity within the hydrolase family. Finally, phylogenetic analyses of the 347 select protein domains and of the complete Nudix clan revealed general monophyly with regard to function and a few instances of probable homoplasy.</description>
+  </descriptions>
+</resource>

data/spec/data/dash1-datacite-xml/ucb-ark+=b6078=d1h019-mrt-datacite.xml

@@ -0,0 +1,38 @@
+<?xml version="1.0" encoding="utf-8"?><resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+  <identifier identifierType="DOI"/>
+  <creators>
+    <creator>
+      <creatorName>French, Courtney</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Wei, Gang</creatorName>
+    </creator>
+    <creator>
+      <creatorName>Brenner, Steven</creatorName>
+    </creator>
+  </creators>
+  <titles>
+    <title>Transcriptome Analysis Reveals Extensive Alternative Splicing-Coupled Nonsense-Mediated mRNA Decay in a Human Cell Line</title>
+  </titles>
+  <publisher>UC Berkeley</publisher>
+  <publicationYear>2015</publicationYear>
+  <subjects>
+    <subject>RNA-seq</subject>
+    <subject>Nonsense-mediated mRNA decay</subject>
+    <subject>Alternative splicing</subject>
+  </subjects>
+  <relatedIdentifiers/>
+  <resourceType resourceTypeGeneral="Collection">Collection</resourceType>
+  <sizes>
+    <size>240593770</size>
+  </sizes>
+  <rightsList>
+    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International (CC-BY 4.0)</rights>
+  </rightsList>
+  <descriptions>
+    <description descriptionType="Abstract">To further explore the regulatory potential of nonsense-mediated mRNA decay (NMD) in human cells, we globally surveyed the transcripts targeted by this pathway via RNA-Seq analysis of HeLa cells in which NMD had been inhibited. We first identified those transcripts with both a premature termination codon more than 50 nucleotides upstream of an exon-exon junction (50nt rule) and a significant increase in abundance upon NMD inhibition. Remarkably, at least 2,793 transcripts derived from 2,116 genes are physiological NMD targets (9.2% of expressed transcripts and &gt;20% of alternatively spliced genes). Our analysis identifies previously inferred unproductive isoforms and numerous previously uncharacterized ones. NMD-targeted transcripts were derived from genes involved in many functional categories, and are particularly enriched for RNA splicing genes and ultraconserved elements. By investigating the features of all transcripts impacted by NMD, we find that the 50nt rule is a strong predictor of NMD degradation while 3’ UTR length generally has only a small effect in human cells. Additionally, thousands more transcripts without a premature termination codon upstream of an exon-exon junction in the main coding sequence contain a uORF and display significantly increased abundance upon NMD inhibition indicating potentially widespread regulation through decay coupled with uORF translation. Our results support the hypothesis that alternative splicing coupled with NMD is a prevalent post-transcriptional  mechanism in human cells with broad potential for biological regulation.</description>
+    <description descriptionType="Methods">HeLa cells were inoculated on plates in Dulbecco’s MEM medium with 0.1 mM non-essential amino acids and 10% fetal bovine serum, incubated at 37°C and 5% CO2. Plates at 80% cell confluency were transfected with plasmids pSUPERpuro-hUpf1/II and pSUPERpuro-Scramble, whose functions were to knockdown UPF1 and act as a mock control, respectively. Transfections were performed using Lipofectamine™ LTX and PLUS™ Reagents (Invitrogen) according to the manufacturer’s protocol, and the following culture according to the published method (Paillusson et al., 2005). The whole cell lysates were prepared in 1% sodium dodecyl sulfate and incubated at 100 °C for 5 min, then centrifuged at 12,000 rpm for 10 min. Total RNA was extracted using the QIAGEN RNeasy® Mini kit according to the manufacturer’s manual. Directional and paired-end RNA-seq libraries were constructed according to the protocol published on the Illumina website (www.illumina.com), with a few changes: The adapters were prepared according to the reported methods (Vigneault et al., 2008). The PCR process to prepare the library was divided in two steps. In the first step, 3 cycles of PCR were performed (according to the protocol) to prepare the library template, and then the library was run on a 2% agarose gel, fragments of desired size were cut out and isolated by QIAquick® Gel Extraction Kit. A second round of PCR (12 cycles) was performed to enrich the library and then it was purified twice with Agencourt AMPure XP kit as suggested by the Illumina protocol. The libraries were then assayed by Agilent 2100 BioAnalyzer. These RNA-Seq libraries were prepared from cells with inhibited NMD and control cells for two biological replicates. One biological replicate was sequenced on an Illumina GAIIx machine and the other on HiSeq 2000. 
+
+Paired end reads for each library were aligned to the NCBI human RefSeq transcriptome (Pruitt et al., 2009) with Bowtie (Langmead et al., 2009) to determine the average insert size and standard deviation, required as a parameter by TopHat (Trapnell et al., 2009). The reads of each library were then aligned to the human genome (hg19 assembly, Feb. 2009; downloaded from UCSC genome browser (Fujita et al., 2011)) using TopHat v1.2.0 with default parameters plus the following: --coverage search, --allow indels, --microexon search, and --butterfly search. Cufflinks 1.0.1 (Roberts et al., 2011; Trapnell et al., 2010) was used to assemble each set of aligned reads into transcripts with the UCSC known transcript set (Fujita et al., 2011) as the reference guide, along with the following parameters: --frag-bias-correct, and --multi-read-correct. Cuffcompare (a sub-tool of Cufflinks) was used to merge the resulting sets of assembled transcripts. Each junction was assigned a Shannon entropy score based on offset of spliced reads across all four libraries. Transcripts with a junction that had an entropy score &lt;1 and was not present in the reference annotation were filtered out. Cuffdiff (a sub-tool of Cufflinks) was used to quantify and compare transcript abundance (measured by FPKM, Fragments Per Kilobase per Million reads) between the UPF1 knockdown and control samples. For each sample, the reads from two biological replicates were provided. The following parameters were used: --frag-bias-correct and --multi-read-correct. Only transcripts with FPKM&gt;1 in either the control or UPF1 knockdown sample were used for further analysis. A transcript was called significantly more abundant in the UPF1 knockdown sample if Cuffdiff called it significantly changing and the fold change was greater than 1.5x. Significantly decreased transcript abundances were determined in the same way. For each transcript, the coding sequence (CDS) was determined as described in the Supplementary Methods. A coding sequence was defined to terminate in a premature stop codon (PTC50nt) if it stops at least 50 nucleotides upstream of the last exon-exon junction (50nt rule in mammals (Nagy and Maquat, 1998)). NMD targets were defined as those transcripts with both a PTC50nt and significantly increased expression abundance in NMD inhibited (UPF1 knockdown) cells. The transcripts must also increase in each biological replicate when analyzed independently and come from a gene with a non-PTC50nt-containing isoform with FPKM&gt;0. To obtain a more reliable list of NMD-targeted transcripts, only those transcripts that adhered to either of the following criteria were kept: 1) No non-PTC50nt-containing isoform from the gene was more than 1.2-fold higher in the NMD inhibited sample, or 2) the PTC50nt-containing isoform increased at least 2x more than the sum of all non-PTC50nt-containing isoform FPKMs from the gene in NMD inhibited cells. </description>
+  </descriptions>
+</resource>