Dataset Open Access

Cleaned and pre-processed MS/MS datset (build from all positive ionmode spectra in GNPS) - zip file

Huber, Florian; Ridder, Lars; Verhoeven, Stefan; Spaaks, Jurriaan H.; Diblen, Faruk; Rogers, Simon; van der Hooft, Justin J.J.


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.3978118">
    <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.3978118</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3978118"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-3535-9406">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-3535-9406</dct:identifier>
        <foaf:name>Huber, Florian</foaf:name>
        <foaf:givenName>Florian</foaf:givenName>
        <foaf:familyName>Huber</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Netherlands eScience Center</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>Ridder, Lars</foaf:name>
        <foaf:givenName>Lars</foaf:givenName>
        <foaf:familyName>Ridder</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Netherlands eScience Center</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>Verhoeven, Stefan</foaf:name>
        <foaf:givenName>Stefan</foaf:givenName>
        <foaf:familyName>Verhoeven</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Netherlands eScience Center</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>Spaaks, Jurriaan H.</foaf:name>
        <foaf:givenName>Jurriaan H.</foaf:givenName>
        <foaf:familyName>Spaaks</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Netherlands eScience Center</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>Diblen, Faruk</foaf:name>
        <foaf:givenName>Faruk</foaf:givenName>
        <foaf:familyName>Diblen</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Netherlands eScience Center</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>Rogers, Simon</foaf:name>
        <foaf:givenName>Simon</foaf:givenName>
        <foaf:familyName>Rogers</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Glascow</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>van der Hooft, Justin J.J.</foaf:name>
        <foaf:givenName>Justin J.J.</foaf:givenName>
        <foaf:familyName>van der Hooft</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Wageningen University</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Cleaned and pre-processed MS/MS datset (build from all positive ionmode spectra in GNPS) - zip file</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>mass spectrometry, MS/MS data</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-08-10</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3978118"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3978118</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isPartOf rdf:resource="https://doi.org/10.1371/journal.pcbi.1008724"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3978117"/>
    <dct:description>&lt;p&gt;Large MS/MS dataset build from data that was obtained from GNPS (accessed on 2020-05-11): &lt;a href="https://gnps-external.ucsd.edu/gnpslibrary/ALL_GNPS.json"&gt;https://gnps-external.ucsd.edu/gnpslibrary/ALL_GNPS.json&lt;/a&gt;&lt;/p&gt; &lt;p&gt;The data was cleaned and pre-processed using notebooks provided here: https://github.com/iomega/spec2vec_gnps_data_analysis/tree/master/notebooks&lt;/p&gt; &lt;ul&gt; &lt;li&gt;112,956 positive ionmode spectra&lt;/li&gt; &lt;li&gt;metadata was cleaned and corrected using matchms (https://github.com/matchms/matchms) and lookup routines using PubChem&lt;/li&gt; &lt;li&gt;92,954 of the spectra have Smiles and InchiKey (13717 unique InchiKey in first 14 characters)&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;Was used for the main article on Spec2Vec --&amp;gt; &lt;a href="https://doi.org/10.1371/journal.pcbi.1008724"&gt;https://doi.org/10.1371/journal.pcbi.1008724&lt;/a&gt;&lt;/p&gt;</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.3978118"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3978118">https://doi.org/10.5281/zenodo.3978118</dcat:accessURL>
        <dcat:byteSize>336575777</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3978118/files/gnps_positive_ionmode_cleaned_by_matchms_and_lookups.zip">https://zenodo.org/record/3978118/files/gnps_positive_ionmode_cleaned_by_matchms_and_lookups.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
159
23
views
downloads
All versions This version
Views 159159
Downloads 2323
Data volume 7.7 GB7.7 GB
Unique views 135135
Unique downloads 1919

Share

Cite as