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.


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3978118</identifier>
  <creators>
    <creator>
      <creatorName>Huber, Florian</creatorName>
      <givenName>Florian</givenName>
      <familyName>Huber</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-3535-9406</nameIdentifier>
      <affiliation>Netherlands eScience Center</affiliation>
    </creator>
    <creator>
      <creatorName>Ridder, Lars</creatorName>
      <givenName>Lars</givenName>
      <familyName>Ridder</familyName>
      <affiliation>Netherlands eScience Center</affiliation>
    </creator>
    <creator>
      <creatorName>Verhoeven, Stefan</creatorName>
      <givenName>Stefan</givenName>
      <familyName>Verhoeven</familyName>
      <affiliation>Netherlands eScience Center</affiliation>
    </creator>
    <creator>
      <creatorName>Spaaks, Jurriaan H.</creatorName>
      <givenName>Jurriaan H.</givenName>
      <familyName>Spaaks</familyName>
      <affiliation>Netherlands eScience Center</affiliation>
    </creator>
    <creator>
      <creatorName>Diblen, Faruk</creatorName>
      <givenName>Faruk</givenName>
      <familyName>Diblen</familyName>
      <affiliation>Netherlands eScience Center</affiliation>
    </creator>
    <creator>
      <creatorName>Rogers, Simon</creatorName>
      <givenName>Simon</givenName>
      <familyName>Rogers</familyName>
      <affiliation>University of Glascow</affiliation>
    </creator>
    <creator>
      <creatorName>van der Hooft, Justin J.J.</creatorName>
      <givenName>Justin J.J.</givenName>
      <familyName>van der Hooft</familyName>
      <affiliation>Wageningen University</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Cleaned and pre-processed MS/MS datset (build from all positive ionmode spectra in GNPS) - zip file</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>mass spectrometry, MS/MS data</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-08-10</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3978118</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsPartOf" resourceTypeGeneral="JournalArticle">10.1371/journal.pcbi.1008724</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3978117</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
  </descriptions>
</resource>
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