<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>1</id>
    <completedYear>2005</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>article</type>
    <publisherName>BioMed Central</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2007-07-05</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Large scale hierarchical clustering of protein sequences</title>
    <abstract language="eng">Background: Searching a biological sequence database with a query sequence looking for homologues has become a routine operation in computational biology. In spite of the high degree of sophistication of currently available search routines it is still virtually impossible to identify quickly and clearly a group of sequences that a given query sequence belongs to. Results: We report on our developments in grouping all known protein sequences hierarchically into superfamily and family clusters. Our graph-based algorithms take into account the topology of the sequence space induced by the data itself to construct a biologically meaningful partitioning. We have applied our clustering procedures to a non-redundant set of about 1,000,000 sequences resulting in a hierarchical clustering which is being made available for querying and browsing at http://systers.molgen.mpg.de/. Conclusions: Comparisons with other widely used clustering methods on various data sets show the abilities and strengths of our clustering methods in producing a biologically meaningful grouping of protein sequences.</abstract>
    <parentTitle language="deu">BMC Bioinformatics</parentTitle>
    <identifier type="urn">urn:nbn:de:kobv:526-opus-153</identifier>
    <identifier type="opus3-id">15</identifier>
    <identifier type="doi">10.15771/1471-2105_2005_6_15</identifier>
    <identifier type="issn">1471-2105</identifier>
    <enrichment key="SourceTitle">Krause, A., Stoye, J. &amp; Vingron, M. Large scale hierarchical clustering of protein sequences. BMC Bioinformatics 6, 15 (2005). https://doi.org/10.1186/1471-2105-6-15</enrichment>
    <enrichment key="DOI_VoR">https://doi.org/10.1186/1471-2105-6-15</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 2.0 Generic</licence>
    <author>Antje Krause</author>
    <author>Jens Stoye</author>
    <author>Martin Vingron</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Protein</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Sequenz</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Clusteralgorithmus</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Hierarchisches Clustern</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Proteinfamilie</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>protein</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>sequence</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>cluster algorithm</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>hierarchical clustering</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>protein family</value>
    </subject>
    <collection role="ddc" number="004">Datenverarbeitung; Informatik</collection>
    <collection role="institutes" number="">Fachbereich Ingenieurwesen / Wirtschaftsingenieurwesen (bis 8/2014)</collection>
    <collection role="open_access" number="">open_access</collection>
    <collection role="green_open_access" number="1">Gold Open Access</collection>
    <thesisPublisher>Technische Hochschule Wildau</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-th-wildau/files/1/1471_2105_6_15.pdf</file>
  </doc>
</export-example>
