Poster Open Access

Fast open modification spectral library searching through approximate nearest neighbor indexing

Bittremieux, Wout; Meysman, Pieter; Noble, William Stafford; Laukens, Kris


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.1418398">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Text"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.1418398</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.1418398"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-3105-1359">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-3105-1359</dct:identifier>
        <foaf:name>Bittremieux, Wout</foaf:name>
        <foaf:givenName>Wout</foaf:givenName>
        <foaf:familyName>Bittremieux</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Washington</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-5903-633X">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-5903-633X</dct:identifier>
        <foaf:name>Meysman, Pieter</foaf:name>
        <foaf:givenName>Pieter</foaf:givenName>
        <foaf:familyName>Meysman</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Antwerp</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-7283-4715">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-7283-4715</dct:identifier>
        <foaf:name>Noble, William Stafford</foaf:name>
        <foaf:givenName>William Stafford</foaf:givenName>
        <foaf:familyName>Noble</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Washington</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-8217-2564">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-8217-2564</dct:identifier>
        <foaf:name>Laukens, Kris</foaf:name>
        <foaf:givenName>Kris</foaf:givenName>
        <foaf:familyName>Laukens</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Antwerp</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Fast open modification spectral library searching through approximate nearest neighbor indexing</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">2018</dct:issued>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2018-09-17</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/1418398"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/1418398</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.1418397"/>
    <dct:description>&lt;p&gt;Open modification searching (OMS) is a powerful search strategy that identifies peptides carrying any type of modification by allowing a modified spectrum to match against its unmodified variant by using a very wide precursor mass window. A drawback of this strategy, however, is that it leads to a large increase in search time. Although performing an open search can be done using existing spectral library search engines by simply setting a wide precursor mass window, none of these tools have been optimized for OMS, leading to excessive runtimes and suboptimal identification results.&lt;/p&gt; &lt;p&gt;Here we present the ANN-SoLo tool for fast and accurate open spectral library searching. ANN-SoLo uses approximate nearest neighbor indexing to speed up OMS by selecting only a limited number of the most relevant library spectra to compare to an unknown query spectrum. This approach is combined with a cascade search strategy to maximize the number of identified unmodified and modified spectra while strictly controlling the false discovery rate, as well as a shifted dot product score to sensitively match modified spectra to their unmodified counterparts.&lt;/p&gt; &lt;p&gt;ANN-SoLo achieves state-of-the-art performance in terms of speed and the number of identifications. On a previously published human cell line data set, ANN-SoLo confidently identifies more spectra than SpectraST or MSFragger and achieves a speedup of an order of magnitude compared to SpectraST.&lt;/p&gt; &lt;p&gt;ANN-SoLo is implemented in Python and C++. It is freely available under the Apache 2.0 license at https://github.com/bittremieux/ANN-SoLo.&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.1418398"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.1418398"/>
        <dcat:byteSize>1419753</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/1418398/files/Genome_Science_retreat_2018_Fast_open_modification_spectral_library_searching_through_approximate_nearest_neighbor_indexing.pdf"/>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
76
96
views
downloads
All versions This version
Views 7676
Downloads 9696
Data volume 136.3 MB136.3 MB
Unique views 7373
Unique downloads 9494

Share

Cite as