June 8, 2017 Poster Open Access

Bittremieux, Wout; Laukens, Kris

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.584067</identifier>
  <creators>
    <creator>
      <creatorName>Bittremieux, Wout</creatorName>
      <givenName>Wout</givenName>
      <familyName>Bittremieux</familyName>
      <affiliation>University of Antwerp</affiliation>
    </creator>
    <creator>
      <creatorName>Laukens, Kris</creatorName>
      <givenName>Kris</givenName>
      <familyName>Laukens</familyName>
      <affiliation>University of Antwerp</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Mass spectrometry proteomics: Ready for the deep learning (r)evolution?</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2017</publicationYear>
  <dates>
    <date dateType="Issued">2017-06-08</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Poster</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/584067</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.789761</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by-sa/4.0/legalcode">Creative Commons Attribution Share Alike 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;In the past few years deep learning (DL) has revolutionized machine learning research, achieving tremendous increases in performance on a variety of problems, ranging from image recognition to natural language processing. In bioinformatics deep neural networks have already been used to solve important problems in genomics, but they have not seen a lot of use in biological mass spectrometry (MS) yet. Nevertheless, there is a huge opportunity to apply DL to MS research as well. Here we show how powerful DL models can usher in a shift from a model-driven approach, using hard-coded rules based on expert knowledge, for example such as complex fragmentation rules, to a data-driven one, where underlying rules are automatically inferred by advanced machine learning models.&lt;/p&gt;</description>
  </descriptions>
</resource>