March 12, 2020 Dataset Open Access

Faessler, Erik; Modersohn, Luise; Lohr, Christina; Hahn, Udo

DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.3698568">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3698568</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3698568"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-1193-5103">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-1193-5103</dct:identifier>
        <foaf:name>Faessler, Erik</foaf:name>
        <foaf:givenName>Erik</foaf:givenName>
        <foaf:familyName>Faessler</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Jena University Language &amp; Information Engineering (JULIE) Lab,Friedrich-Schiller-Universität Jena, Jena, Germany</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Modersohn, Luise</foaf:name>
        <foaf:givenName>Luise</foaf:givenName>
        <foaf:familyName>Modersohn</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Jena University Language &amp; Information Engineering (JULIE) Lab,Friedrich-Schiller-Universität Jena, Jena, Germany</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Lohr, Christina</foaf:name>
        <foaf:givenName>Christina</foaf:givenName>
        <foaf:familyName>Lohr</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Jena University Language &amp; Information Engineering (JULIE) Lab,Friedrich-Schiller-Universität Jena, Jena, Germany</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Hahn, Udo</foaf:name>
        <foaf:givenName>Udo</foaf:givenName>
        <foaf:familyName>Hahn</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Jena University Language &amp; Information Engineering (JULIE) Lab,Friedrich-Schiller-Universität Jena, Jena, Germany</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>ProGene - A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2020</dct:issued>
    <dcat:keyword>Genes and proteins</dcat:keyword>
    <dcat:keyword>text corpus</dcat:keyword>
    <dcat:keyword>annotation</dcat:keyword>
    <dcat:keyword>biomedical corpus</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-03-12</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3698568"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3698568</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3698567"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/julie-lab"/>
    <owl:versionInfo>1.1</owl:versionInfo>
    <dct:description>&lt;p&gt;The Pro(tein)/Gene corpus was developed at the JULIE Lab Jena under supervision of Prof. Udo Hahn.&lt;/p&gt; &lt;p&gt;The goals of the annotation project were&lt;/p&gt; &lt;ul&gt; &lt;li&gt;to construct a consistent and (as far as possible) subdomain-independent/-comprehensive protein-annotated corpus&lt;/li&gt; &lt;li&gt;to differentiate between protein families and groups, protein complexes, protein molecules, protein variants (e.g. alleles) and elliptic enumerations of proteins.&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;The corpus has the following annotation levels / entity types:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;protein&lt;/li&gt; &lt;li&gt;protein_familiy_or_group&lt;/li&gt; &lt;li&gt;protein_complex&lt;/li&gt; &lt;li&gt;protein_variant&lt;/li&gt; &lt;li&gt;protein_enum&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;For definitions of the annotation levels, please refer to the Proteins-guidelines-final.doc file that is found in the download package.&lt;/p&gt; &lt;p&gt;To achieve a large coverage of biological subdomains, document from multiple other protein / gene corpora were reannotated. For further coverage, new document sets were created. All documents are abstracts from PubMed/MEDLINE. The corpus is made up of the union of all the documents in the different subcorpora.&lt;br&gt; All document are delivered as MMAX2 (http://mmax2.net/) annotation projects.&lt;/p&gt;</dct:description>
    <dct:description>{"references": ["Faessler et al. (2020). PROGENE\u2014A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus, LREC 2020"]}</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3698568"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3698568"/>
        <dcat:byteSize>24926113383</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3698568/files/progene.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>