Dataset Open Access

Single-Cell Gene Expression Profiles for Classification Problems

Gualandi, Stefano; Codegoni, Andrea; Vercesi, Eleonora


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.4604569">
    <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.4604569</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4604569"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-2111-3528">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-2111-3528</dct:identifier>
        <foaf:name>Gualandi, Stefano</foaf:name>
        <foaf:givenName>Stefano</foaf:givenName>
        <foaf:familyName>Gualandi</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pavia</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>Codegoni, Andrea</foaf:name>
        <foaf:givenName>Andrea</foaf:givenName>
        <foaf:familyName>Codegoni</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pavia</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>Vercesi, Eleonora</foaf:name>
        <foaf:givenName>Eleonora</foaf:givenName>
        <foaf:familyName>Vercesi</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Pavia</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Single-Cell Gene Expression Profiles for Classification Problems</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">2021</dct:issued>
    <dcat:keyword>Gene-expression-profile, Leukemia, Brain, Pancreas, Gene Mover Distance</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-03-15</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4604569"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4604569</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="http://arxiv.org/abs/2102.01218"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4604568"/>
    <owl:versionInfo>v1.0.0</owl:versionInfo>
    <dct:description>&lt;p&gt;This repository contains a collection of three datasets we use to introduce the Gene Mover Distance in [1] and described below. The three datasets are exported with a basic text-based format (.csv file) like other public datasets largely used in the Machine Learning community.&lt;/p&gt; &lt;p&gt;The three datasets are extracted from the Gene Expression Omnibus (GEO) database [2], where they appear, respectively,&amp;nbsp;with access number&amp;nbsp;GSE116256 (blood leukemia, [3]), GSE84133 (human pancreas, [4]), and GSE67835 (human brain, [5]). In GEO, the datasets are decomposed into several files, which contain much more details than those reported in this version.&lt;/p&gt; &lt;p&gt;However, the proposed format should facilitate other researchers in using this data.&lt;/p&gt; &lt;p&gt;The Gene Mover&amp;#39;s Distance is a measure of similarity between a pair of cells based on their gene expression profiles obtained via single-cell RNA sequencing. The underlying idea of GMD is to interpret the gene expression array of a single cell as a discrete probability measure. The distance between two cells is hence computed by solving an Optimal Transport problem between the two corresponding discrete measures. The Gene Mover&amp;#39;s Distance can be used, for instance, to solve two classification problems: the classification of cells according to their condition and according to their type.&lt;/p&gt; &lt;p&gt;The repository contains a python script to check the basic statistics of the data.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;[1] Bellazzi, R., Codegoni, A., Gualandi, S., Nicora, G., Vercesi, E. &lt;em&gt;The Gene Mover&amp;#39;s Distance: Single-cell similarity via Optimal Transport&lt;/em&gt;. &lt;a href="https://arxiv.org/abs/2102.01218"&gt;https://arxiv.org/abs/2102.01218&lt;/a&gt;&lt;/p&gt; &lt;p&gt;[2] Gene Expression Omnibus (GEO) database, &lt;a href="http://www.ncbi.nlm.nih.gov/geo"&gt;http://www.ncbi.nlm.nih.gov/geo&lt;/a&gt;&lt;/p&gt; &lt;p&gt;[3] van Galen, P., Hovestadt, V., Wadsworth II, M.H., Hughes, T.K., Griffin, G.K., Battaglia, S., Verga, J.A., Stephansky, J., Pastika, T.J., Story, J.L. and Pinkus, G.S., 2019. &lt;em&gt;Single-cell RNA-seq reveals AML hierarchies relevant to disease progression and immunity&lt;/em&gt;. Cell, 176(6), pp.1265-1281.&lt;/p&gt; &lt;p&gt;[4] Baron, M., Veres, A., Wolock, S.L., Faust, A.L., Gaujoux, R., Vetere, A., Ryu, J.H., Wagner, B.K., Shen-Orr, S.S., Klein, A.M. and Melton, D.A., 2016.&lt;em&gt; A single-cell transcriptomic map of the human and mouse pancreas reveals inter-and intra-cell population structure&lt;/em&gt;. Cell systems, 3(4), pp.346-360.&lt;/p&gt; &lt;p&gt;[5] Darmanis, S., Sloan, S.A., Zhang, Y., Enge, M., Caneda, C., Shuer, L.M., Gephart, M.G.H., Barres, B.A. and Quake, S.R., 2015. &lt;em&gt;A survey of human brain transcriptome diversity at the single cell level&lt;/em&gt;. Proceedings of the National Academy of Sciences, 112(23), pp.7285-7290.&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.4604569"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4604569">https://doi.org/10.5281/zenodo.4604569</dcat:accessURL>
        <dcat:byteSize>78747182</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4604569/files/gmd_v1.0.0.zip">https://zenodo.org/record/4604569/files/gmd_v1.0.0.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
118
11
views
downloads
All versions This version
Views 118118
Downloads 1111
Data volume 866.2 MB866.2 MB
Unique views 109109
Unique downloads 99

Share

Cite as