Dataset Open Access

Protein language model embeddings and predictions of the human proteome

Christian Dallago; Burkhard Rost


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.5047020">
    <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.5047020</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-4650-6181">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-4650-6181</dct:identifier>
        <foaf:name>Christian Dallago</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Technical University of Munich</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-0179-8424">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-0179-8424</dct:identifier>
        <foaf:name>Burkhard Rost</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Technical University of Munich</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Protein language model embeddings and predictions of the human proteome</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>protein subcellular location</dcat:keyword>
    <dcat:keyword>protein embeddings</dcat:keyword>
    <dcat:keyword>protein language models</dcat:keyword>
    <dcat:keyword>protein secondary structure</dcat:keyword>
    <dcat:keyword>protein prediction</dcat:keyword>
    <dcat:keyword>human proteome</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-06-30</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/5047020"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5047020</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://doi.org/10.1101/2020.07.12.199554"/>
    <dct:relation rdf:resource="https://doi.org/10.1093/nar/gkab354/6276913"/>
    <dct:relation rdf:resource="https://doi.org/10.1101/2021.04.25.441334"/>
    <dct:relation rdf:resource="https://doi.org/10.1002/cpz1.113"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.5047019"/>
    <owl:versionInfo>2021.06.09</owl:versionInfo>
    <dct:description>&lt;p&gt;Residue and sequence embeddings of the human proteome (SwissProt for organism Human, downloaded on&amp;nbsp;2021.06.09)&amp;nbsp;computed using bio_embeddings (bioembeddings.com) using the ProtT5 embedder at full precision (https://www.biorxiv.org/content/10.1101/2020.07.12.199554v3).&lt;/p&gt; &lt;p&gt;Additionally:&lt;/p&gt; &lt;p&gt;- Sequence-level&amp;nbsp;predictions of subcellular localization in 10 classes using LA (https://www.biorxiv.org/content/10.1101/2021.04.25.441334v1)&lt;/p&gt; &lt;p&gt;- Residue-level three state secondary structure prediction (alpha, sheet or other) using models reported&amp;nbsp;in the ProtTrans paper (https://www.biorxiv.org/content/10.1101/2020.07.12.199554v3)&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;Files included:&lt;/p&gt; &lt;p&gt;- human.fasta --&amp;gt; FASTA-formatted sequences of human from SwissProt&lt;/p&gt; &lt;p&gt;-&amp;nbsp;DSSP3_human_ProtT5Sec.fasta --&amp;gt; Secondary structure predictions in three states for each residue of each protein&amp;nbsp;in human.fasta. &amp;quot;H&amp;quot; stands for Helix; &amp;quot;E&amp;quot; stands for Sheet; &amp;quot;C&amp;quot; stands for Other.&lt;/p&gt; &lt;p&gt;-&amp;nbsp;subcell_human_LA_ProtT5.csv --&amp;gt; Subcellular location (10 states) and memrane-boundness (2 states)&amp;nbsp;for each protein in human.fasta&lt;/p&gt; &lt;p&gt;-&amp;nbsp;embeddings_file.h5 --&amp;gt; per-residue embeddings of sequences in human.fasta. Each dataset&amp;nbsp;in the .h5 file represents a protein sequence and contains a matrix of length Lx1024, with L being the length of the protein sequence. Datasets are indexed using integers. The original sequence identifier (from the FASTA header) can be accessed through the &amp;quot;original_id&amp;quot; attribute. See&amp;nbsp;https://docs.bioembeddings.com/v0.2.0/notebooks/open_embedding_file.html for information on how to open the file&lt;/p&gt; &lt;p&gt;-&amp;nbsp;reduced_embeddings_file.h5 --&amp;gt; per-sequence embeddings of sequences in human.fasta (obtained by mean-pooling the residue-embeddings along the length dimension of the protein sequence). Each dataset&amp;nbsp;in the .h5 file represents a protein sequence and contains a vector of size 1024 (meaning, each sequence has the same dimension).&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:rights>
          <dct:RightsStatement rdf:about="https://opensource.org/licenses/afl-3.0">
            <rdfs:label>Academic Free License v3.0</rdfs:label>
          </dct:RightsStatement>
        </dct:rights>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
        <dcat:byteSize>13722773</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5047020/files/DSSP3_human_ProtT5Sec.fasta"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
        <dcat:byteSize>46557163296</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5047020/files/embeddings_file.h5"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
        <dcat:byteSize>13611513</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5047020/files/human.fasta"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
        <dcat:byteSize>92008224</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5047020/files/reduced_embeddings_file.h5"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5047020"/>
        <dcat:byteSize>1020481</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5047020/files/subcell_human_LA_ProtT5.csv"/>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
184
114
views
downloads
All versions This version
Views 184184
Downloads 114114
Data volume 93.9 GB93.9 GB
Unique views 163163
Unique downloads 9090

Share

Cite as