<ddi:DDIInstance xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="ddi:instance:3_3 http://ddialliance.org/Specification/DDI-Lifecycle/3.3/XMLSchema/instance.xsd" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:ddi="ddi:instance:3_3" xmlns:r="ddi:reusable:3_3" xmlns:s="ddi:studyunit:3_3" xmlns:d="ddi:datacollection:3_3" xmlns:a="ddi:archive:3_3" xmlns:c="ddi:conceptualcomponent:3_3" xmlns:cm="ddi:comparative:3_3" xmlns:g="ddi:group:3_3" xmlns:l="ddi:logicalproduct:3_3" xmlns:p="ddi:physicaldataproduct:3_3" xmlns:pi="ddi:physicalinstance:3_3" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xml="http://www.w3.org/XML/1998/namespace" isMaintainable="true" scopeOfUniqueness="Agency">
  <r:URN>urn:ddi:se.researchdata:2024-341:1</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>2024-341</r:ID>
  <r:Version>1</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:2024-341.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:2024-341.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:2024-341.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2024-341.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Cell and Molecular Biology, Uppsala University</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Sara A.</a:FirstGiven>
            <a:LastFamily>Yones</a:LastFamily>
            <a:FullName>
              <r:String>Sara A. Yones</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2024-341.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Cell and Molecular Biology, Uppsala University</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Rajmund</a:FirstGiven>
            <a:LastFamily>Csombordi</a:LastFamily>
            <a:FullName>
              <r:String>Rajmund Csombordi</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2024-341.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Cell and Molecular Biology, Computational Biology and Bioinformatics, Swedish Collegium for Advanced Study (SCAS) / Institute of Computer Science, Warsaw, Uppsala University / Polish Academy of Sciences / Washington National Primate Research Center</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Jan</a:FirstGiven>
            <a:LastFamily>Komorowski</a:LastFamily>
            <a:FullName>
              <r:String>Jan Komorowski</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0002-0766-8789</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2024-341.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Cell and Molecular Biology, Computational Biology and Bioinformatics, Department of Immunology, Genetics and Pathology, Uppsala University</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Klev</a:FirstGiven>
            <a:LastFamily>Diamanti</a:LastFamily>
            <a:FullName>
              <r:String>Klev Diamanti</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0002-4922-8415</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:2024-341.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">2024-341</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="sv">Supplementary tables:MetaFetcheR: An R package for complete mapping of small compound data</r:String>
        <r:String xml:lang="en">Supplementary tables:MetaFetcheR: An R package for complete mapping of small compound data</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:2024-341.Individual-0:2.0</r:URN>
          <r:TypeOfObject>Individual</r:TypeOfObject>
        </r:CreatorReference>
      </r:Creator>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Uppsala universitet</r:String>
          <r:String xml:lang="en">Uppsala University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Uppsala universitet</r:String>
          <r:String xml:lang="en">Uppsala University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:PublicationDate>
        <r:SimpleDate>2021-10-07</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.57804/7sf1-fw75</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="sv">The dataset includes a PDF file containing the results and an Excel file with the following tables:

Table S1	Results of comparing the performance  of MetaFetcheR to MetaboAnalystR using Diamanti et al. 
Table S2	Results of comparing the performance of MetaFetcheR to MetaboAnalystR for Priolo et al.
Table S3	Results of comparing the performance  of MetaFetcheR to MetaboAnalyst 5.0 webtool using Diamanti et al. 
Table S4	Results of comparing the performance of MetaFetcheR to MetaboAnalyst 5.0 webtool for Priolo et al. 
Table S5	Data quality test results for running 100 iterations on HMDB database.
Table S6	Data quality test results for running 100 iterations on KEGG database.
Table S7	Data quality test results for running 100 iterations on ChEBI database.
Table S8	Data quality test results for running 100 iterations on PubChem database.
Table S9	Data quality test results for running 100 iterations on LIPID MAPS database.
Table S10 The list of metabolites that were not mapped by MetaboAnalystR for Diamanti et al.
Table S11 An example of an input matrix for MetaFetcheR.
Table S12 Results of comparing the performance of MetaFetcheR to MS_targeted using Diamanti et al. 
Table S13 Data set from Diamanti et al.
Table S14 Data set from Priolo et al.
Table S15 Results of comparing the performance  of MetaFetcheR to CTS using KEGG identifiers available in Diamanti et al.
Table S16 Results of comparing the performance  of MetaFetcheR to CTS using LIPID MAPS identifiers available in Diamanti et al.
Table S17 Results of comparing the performance  of MetaFetcheR to CTS using KEGG identifiers available in Priolo et al. 
Table S18 Results of comparing the performance  of MetaFetcheR to CTS using KEGG identifiers available in Priolo et al. 

Se engelsk beskrivning för mer information.

Datasetet har ursprungligen publicerats i DiVA och flyttades över till SND 2024.</r:Content>
      <r:Content xml:lang="en">The dataset includes a PDF file containing the results and an Excel file with the following tables:

Table S1	Results of comparing the performance  of MetaFetcheR to MetaboAnalystR using Diamanti et al. 
Table S2	Results of comparing the performance of MetaFetcheR to MetaboAnalystR for Priolo et al.
Table S3	Results of comparing the performance  of MetaFetcheR to MetaboAnalyst 5.0 webtool using Diamanti et al. 
Table S4	Results of comparing the performance of MetaFetcheR to MetaboAnalyst 5.0 webtool for Priolo et al. 
Table S5	Data quality test results for running 100 iterations on HMDB database.
Table S6	Data quality test results for running 100 iterations on KEGG database.
Table S7	Data quality test results for running 100 iterations on ChEBI database.
Table S8	Data quality test results for running 100 iterations on PubChem database.
Table S9	Data quality test results for running 100 iterations on LIPID MAPS database.
Table S10 The list of metabolites that were not mapped by MetaboAnalystR for Diamanti et al.
Table S11 An example of an input matrix for MetaFetcheR.
Table S12 Results of comparing the performance of MetaFetcheR to MS_targeted using Diamanti et al. 
Table S13 Data set from Diamanti et al.
Table S14 Data set from Priolo et al.
Table S15 Results of comparing the performance  of MetaFetcheR to CTS using KEGG identifiers available in Diamanti et al.
Table S16 Results of comparing the performance  of MetaFetcheR to CTS using LIPID MAPS identifiers available in Diamanti et al.
Table S17 Results of comparing the performance  of MetaFetcheR to CTS using KEGG identifiers available in Priolo et al. 
Table S18 Results of comparing the performance  of MetaFetcheR to CTS using KEGG identifiers available in Priolo et al. 
(See the "index" tab in the Excel file for more information)

Small-compound databases contain a large amount of information for metabolites and metabolic pathways. However, the plethora of such databases and the redundancy of their information lead to major issues with analysis and standardization. Lack of preventive establishment of means of data access at the infant stages of a project might lead to mislabelled compounds, reduced statistical power and large delays in delivery of results.

We developed MetaFetcheR, an open-source R package that links metabolite data from several small-compound databases, resolves inconsistencies and covers a variety of use-cases of data fetching. We showed that the performance of MetaFetcheR was superior to existing approaches and databases by benchmarking the performance of the algorithm in three independent case studies based on two published datasets.

The dataset was originally published in DiVA and moved to SND in 2024.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:2024-341.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="10201" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Computer Sciences</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10201" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Datavetenskap (datalogi)</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="10203" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Bioinformatics (Computational Biology)</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10203" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Bioinformatik (beräkningsbiologi)</r:Subject>
        <r:Keyword xml:lang="en" controlledVocabularyID="p18492" controlledVocabularyName="YSO">cell biology</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="p18492" controlledVocabularyName="YSO">cellbiologi</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="p7549" controlledVocabularyName="YSO">molecular biology</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="p7549" controlledVocabularyName="YSO">molekylärbiologi</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="p27250" controlledVocabularyName="YSO">data</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="p27250" controlledVocabularyName="YSO">data</r:Keyword>
      </r:TopicalCoverage>
      <r:SpatialCoverage />
    </r:Coverage>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:2024-341.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:2024-341.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary">openAccess</a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>2</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>