Dataset Open Access

Robustness and applicability of transcription factor and pathway analysis tools on single-cell RNA-seq data

Christian H. Holland; Jovan Tanevski; Javier Perales-Patón; Jan Gleixner; Manu P. Kumar; Elisabetta Mereu; Brian A. Joughin; Oliver Stegle; Douglas A. Lauffenburger; Holger Heyn; Bence Szalai; Julio Saez-Rodriguez

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.3564179">
    <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.3564179</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3564179"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-3060-5786">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-3060-5786</dct:identifier>
        <foaf:name>Christian H. Holland</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Institute of Computational Biomedicine, Heidelberg University, Faculty of Medicine, Bioquant - Im Neuenheimer Feld 267, 69120 Heidelberg, 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>Jovan Tanevski</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Institute of Computational Biomedicine, Heidelberg University, Faculty of Medicine, Bioquant - Im Neuenheimer Feld 267, 69120 Heidelberg, 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>Javier Perales-Patón</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Institute of Computational Biomedicine, Heidelberg University, Faculty of Medicine, Bioquant - Im Neuenheimer Feld 267, 69120 Heidelberg, 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>Jan Gleixner</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120 Heidelberg, 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>Manu P. Kumar</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Department of Biological Engineering, MIT, Cambridge MA</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>Elisabetta Mereu</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>CNAG-CRG, Centre for Genomic Regulation (CRG), Barcelona Institute of Science and Technology (BIST), Barcelona, Spain</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>Brian A. Joughin</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Department of Biological Engineering, MIT, Cambridge MA</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>Oliver Stegle</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120 Heidelberg, 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>Douglas A. Lauffenburger</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Department of Biological Engineering, MIT, Cambridge MA</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>Holger Heyn</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>CNAG-CRG, Centre for Genomic Regulation (CRG), Barcelona Institute of Science and Technology (BIST), Barcelona, Spain</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>Bence Szalai</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Semmelweis University, Faculty of Medicine, Department of Physiology, Budapest, Hungary</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-8552-8976">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-8552-8976</dct:identifier>
        <foaf:name>Julio Saez-Rodriguez</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Institute of Computational Biomedicine, Heidelberg University, Faculty of Medicine, Bioquant - Im Neuenheimer Feld 267, 69120 Heidelberg, Germany</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Robustness and applicability of transcription factor and pathway analysis tools on single-cell RNA-seq data</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">2019</dct:issued>
    <dcat:keyword>scRNA-seq</dcat:keyword>
    <dcat:keyword>functional analysis</dcat:keyword>
    <dcat:keyword>transcription factor analysis</dcat:keyword>
    <dcat:keyword>pathway analysis</dcat:keyword>
    <dcat:keyword>benchmark</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-12-10</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3564179"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3564179</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3564178"/>
    <owl:versionInfo>Version 2019-12-10</owl:versionInfo>
    <dct:description>&lt;p&gt;Data used to test the robustness and applicability of transcription factor and pathway analysis tools on single-cell RNA-seq data, described in &lt;a href="https://doi.org/10.1186/s13059-020-1949-z"&gt;Holland et al. 2020&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;The folder&amp;nbsp;&lt;em&gt;data &lt;/em&gt;contains&lt;em&gt;&amp;nbsp;&lt;/em&gt;raw data and the folder &lt;em&gt;output&lt;/em&gt; contains intermediate and final results of all analyses.&amp;nbsp;&lt;/p&gt; &lt;p&gt;The associated analyses code and more information are available on&amp;nbsp;&lt;a href="https://github.com/saezlab/FootprintMethods_on_scRNAseq"&gt;GitHub&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Abstract&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Background&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;Many functional analysis tools have been developed to extract functional and mechanistic insight from bulk transcriptome data. With the advent of single-cell RNA sequencing (scRNA-seq), it is in principle possible to do such an analysis for single cells. However, scRNA-seq data has characteristics such as drop-out events and low library sizes. It is thus not clear if functional TF and pathway analysis tools established for bulk sequencing can be applied to scRNA-seq in a meaningful way.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Results&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;To address this question, we perform benchmark studies on simulated and real scRNA-seq data. We include the bulk-RNA tools PROGENy, GO enrichment, and DoRothEA that estimate pathway and transcription factor (TF) activities, respectively, and compare them against the tools SCENIC/AUCell and metaVIPER, designed for scRNA-seq. For the in silico study, we simulate single cells from TF/pathway perturbation bulk RNA-seq experiments. We complement the simulated data with real scRNA-seq data upon CRISPR-mediated knock-out. Our benchmarks on simulated and real data reveal comparable performance to the original bulk data. Additionally, we show that the TF and pathway activities preserve cell type-specific variability by analyzing a mixture sample sequenced with 13 scRNA-seq protocols. We also provide the benchmark data for further use by the community.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Conclusions&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;Our analyses suggest that bulk-based functional analysis tools that use manually curated footprint gene sets can be applied to scRNA-seq data, partially outperforming dedicated single-cell tools. Furthermore, we find that the performance of functional analysis tools is more sensitive to the gene sets than to the statistic used.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;For questions related to the data please write an email to christian.holland@bioquant.uni-heidelberg.de or use the &lt;a href="https://github.com/saezlab/FootprintMethods_on_scRNAseq/issues"&gt;GitHub issue system&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.3564179"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3564179"/>
        <dcat:byteSize>5485871322</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3564179/files/data.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3564179"/>
        <dcat:byteSize>5378455338</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3564179/files/output.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
992
2,155
views
downloads
All versions This version
Views 992992
Downloads 2,1552,155
Data volume 11.6 TB11.6 TB
Unique views 913913
Unique downloads 533533
More info on how stats are collected.
Indexed in
Publication date:
December 10, 2019
DOI:
10.5281/zenodo.3564179

Zenodo DOI Badge

DOI 

10.5281/zenodo.3564179

Markdown 

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3564179.svg)](https://doi.org/10.5281/zenodo.3564179)

reStructedText 

.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.3564179.svg
   :target: https://doi.org/10.5281/zenodo.3564179

HTML 

<a href="https://doi.org/10.5281/zenodo.3564179"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.3564179.svg" alt="DOI"></a>

Image URL 

https://zenodo.org/badge/DOI/10.5281/zenodo.3564179.svg

Target URL 

https://doi.org/10.5281/zenodo.3564179

Keyword(s):
scRNA-seq functional analysis transcription factor analysis pathway analysis benchmark
License (for files):
Creative Commons Attribution 4.0 International

Versions

Version Version 2019-12-10 10.5281/zenodo.3564179 Dec 10, 2019
Cite all versions? You can cite all versions by using the DOI 10.5281/zenodo.3564178. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export