<?xml version='1.0' encoding='utf-8'?>
<?xml-stylesheet type="text/xsl" href="/v2/static/oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-10-06T20:18:27Z</responseDate>
  <request identifier="oai:figshare.com:article/34070484" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/34070484</identifier>
        <datestamp>2026-10-05T15:06:32Z</datestamp>
        <setSpec>category_24184</setSpec>
        <setSpec>category_24208</setSpec>
        <setSpec>category_24199</setSpec>
        <setSpec>item_type_3</setSpec>
        <setSpec>month_year_10_2026</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>UniProt Pan-Proteomes 2026_02</dc:title>
          <dc:creator>Giuseppe Insana (18097213)</dc:creator>
          <dc:creator>Tanushree Tunstall (25316195)</dc:creator>
          <dc:creator>Stephanie Lo (22295793)</dc:creator>
          <dc:creator>John Lees (774343)</dc:creator>
          <dc:creator>Maria J Martin (18098052)</dc:creator>
          <dc:creator>The UniProt Consortium (6672080)</dc:creator>
          <dc:subject>Bioinformatic methods development</dc:subject>
          <dc:subject>Bioinformatics and computational biology not elsewhere classified</dc:subject>
          <dc:subject>Sequence analysis</dc:subject>
          <dc:subject>pan proteome</dc:subject>
          <dc:subject>panproteome</dc:subject>
          <dc:subject>pan-proteome</dc:subject>
          <dc:description>UniProt Pan-Proteomes 2026_02&lt;p dir="ltr"&gt;This is the Pan-Proteomes dataset published as part as UniProt release 2026_02 (10-Jun-2026).&lt;/p&gt;&lt;p dir="ltr"&gt;It is the first release of the new UniProt Pan-Proteomes.&lt;/p&gt;&lt;p dir="ltr"&gt;Please note that due to upload limitations, the original pp* subfolders have been replaced by a single compressed .tgz archive.&lt;/p&gt;&lt;p dir="ltr"&gt;The latest version (published with each UniProt release) of the data set is &lt;a href="https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/pan_proteomes/" target="_blank"&gt;available under UniProt FTP site&lt;/a&gt;.&lt;/p&gt;&lt;h2 dir="ltr"&gt;What are Pan-Proteomes?&lt;/h2&gt;&lt;p dir="ltr"&gt;UniProt provides &lt;a href="https://www.uniprot.org/help/pan_proteomes" target="_blank"&gt;Pan-Proteomes&lt;/a&gt; at the species level to capture unique sequences absent from the &lt;a href="https://www.uniprot.org/help/reference_proteome" target="_blank"&gt;reference proteome&lt;/a&gt;, in order to reflect the proteome diversity of the species. A pan-proteome is composed of a set of protein sequences, where each sequence represents a protein cluster from the analyzed proteomes of that species. A protein cluster is a group of similar protein sequences based on specified criteria, such as sequence identity and alignment coverage.&lt;/p&gt;</dc:description>
          <dc:date>2026-10-05T15:06:32Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.6084/m9.figshare.34070484.v2</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/UniProt_Pan-Proteomes_2026_02/34070484</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
