<?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>2026-10-13T23:51:49Z</responseDate>
  <request identifier="oai:figshare.com:article/33939871" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/33939871</identifier>
        <datestamp>2026-09-18T17:53:58Z</datestamp>
        <setSpec>category_1</setSpec>
        <setSpec>category_4</setSpec>
        <setSpec>category_12</setSpec>
        <setSpec>category_13</setSpec>
        <setSpec>category_14</setSpec>
        <setSpec>category_24</setSpec>
        <setSpec>category_39</setSpec>
        <setSpec>category_734</setSpec>
        <setSpec>category_61</setSpec>
        <setSpec>category_128</setSpec>
        <setSpec>category_132</setSpec>
        <setSpec>category_134</setSpec>
        <setSpec>portal_5</setSpec>
        <setSpec>item_type_3</setSpec>
        <setSpec>month_year_09_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>&lt;p&gt;Complete per-domain classification of the archaeal proteome dataset.&lt;/p&gt;</dc:title>
          <dc:creator>R. Dustin Schaeffer (669735)</dc:creator>
          <dc:creator>Jimin Pei (481020)</dc:creator>
          <dc:creator>Rui Guo (134395)</dc:creator>
          <dc:creator>Jing Zhang (23775)</dc:creator>
          <dc:creator>Kirill Medvedev (24259167)</dc:creator>
          <dc:creator>Qian Cong (150388)</dc:creator>
          <dc:creator>Nick Grishin (3418790)</dc:creator>
          <dc:subject>Biophysics</dc:subject>
          <dc:subject>Biochemistry</dc:subject>
          <dc:subject>Cell Biology</dc:subject>
          <dc:subject>Genetics</dc:subject>
          <dc:subject>Molecular Biology</dc:subject>
          <dc:subject>Evolutionary Biology</dc:subject>
          <dc:subject>Ecology</dc:subject>
          <dc:subject>Biological Sciences not elsewhere classified</dc:subject>
          <dc:subject>Developmental Biology</dc:subject>
          <dc:subject>Hematology</dc:subject>
          <dc:subject>Infectious Diseases</dc:subject>
          <dc:subject>Virology</dc:subject>
          <dc:subject>structural novelty unknown</dc:subject>
          <dc:subject>structural cluster context</dc:subject>
          <dc:subject>groups defined across</dc:subject>
          <dc:subject>folded structural orphans</dc:subject>
          <dc:subject>divergent sequences rather</dc:subject>
          <dc:subject>deepest phylogenetic distances</dc:subject>
          <dc:subject>broadly conserved across</dc:subject>
          <dc:subject>applied successive filters</dc:subject>
          <dc:subject>457 ecod x</dc:subject>
          <dc:subject>protein fold repertoire</dc:subject>
          <dc:subject>structure prediction confidence</dc:subject>
          <dc:subject>confidence structure predictions</dc:subject>
          <dc:subject>proteins lacking high</dc:subject>
          <dc:subject>ecod ).</dc:subject>
          <dc:subject>protein length</dc:subject>
          <dc:subject>confidence classification</dc:subject>
          <dc:subject>yet account</dc:subject>
          <dc:subject>unclassified fraction</dc:subject>
          <dc:subject>systematic domain</dc:subject>
          <dc:subject>small number</dc:subject>
          <dc:subject>sequence comparison</dc:subject>
          <dc:subject>roughly 40</dc:subject>
          <dc:subject>results demonstrate</dc:subject>
          <dc:subject>reducing 8</dc:subject>
          <dc:subject>protein domains</dc:subject>
          <dc:subject>novel structures</dc:subject>
          <dc:subject>major lineages</dc:subject>
          <dc:subject>level classification</dc:subject>
          <dc:subject>known folds</dc:subject>
          <dc:subject>group assignment</dc:subject>
          <dc:subject>free proteins</dc:subject>
          <dc:subject>evolutionary classification</dc:subject>
          <dc:subject>domain level</dc:subject>
          <dc:subject>domain classification</dc:subject>
          <dc:subject>dataset ).</dc:subject>
          <dc:subject>5 %),</dc:subject>
          <dc:subject>452 domain</dc:subject>
          <dc:subject>075 proteins</dc:subject>
          <dc:description>&lt;p&gt;One row per classified domain (204,758 domains across 115,623 proteins; 36 columns): domain and protein identifiers (with cross-reference to the published accession and the EPP resource), source organism and GTDB taxonomy, structure provenance (pre-existing AFDB / de novo AlphaFold3) and mean pLDDT, the ECOD X-/H-/T-group assignment with DPAM confidence and match scores, Pfam annotation, and sequence and structural cluster membership at protein and domain levels (PSC, PXC, DSC, DXC). A full column dictionary accompanies the file. The same table is deposited at Zenodo (DOI &lt;a href="https://doi.org/10.5281/zenodo.21656443" target="_blank"&gt;10.5281/zenodo.21656443&lt;/a&gt;).&lt;/p&gt; &lt;p&gt;(GZ)&lt;/p&gt;</dc:description>
          <dc:date>2026-09-18T17:51:36Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.1371/journal.pcbi.1014188.s004</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/_p_Complete_per-domain_classification_of_the_archaeal_proteome_dataset_p_/33939871</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
