<?xml version='1.0' encoding='UTF-8'?>
<ProteomeXchangeDataset id="PXD056793" formatVersion="1.4.0" xsi:noNamespaceSchemaLocation="proteomeXchange-1.4.0.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
  <CvList>
    <Cv id="MS" fullName="PSI-MS" uri="https://raw.githubusercontent.com/HUPO-PSI/psi-ms-Cv/master/psi-ms.obo"/>
    <Cv id="MOD" fullName="PSI-MOD" uri="https://raw.githubusercontent.com/HUPO-PSI/psi-mod-CV/master/PSI-MOD.obo"/>
    <Cv id="UNIMOD" fullName="UNIMOD" uri="http://www.unimod.org/obo/unimod.obo"/>
  </CvList>
  <DatasetSummary announceDate="2024-10-19" hostingRepository="PanoramaPublic" title="Carafe enables high quality in silico spectral library generation for data-independent acquisition proteomics">
    <Description>Data-independent acquisition (DIA)-based mass spectrometry is becoming an increasingly popular mass spectrometry acquisition strategy for carrying out quantitative proteomics experiments. Most of the popular DIA search engines make use of in silico generated spectral libraries. However, the generation of high-quality spectral libraries for DIA data analysis remains a challenge, particularly because most such libraries are generated directly from data-dependent acquisition (DDA) data or are from in silico prediction using models trained on DDA data. In this study, we developed Carafe, a tool that generates high-quality experiment-specific in silico spectral libraries by training deep learning models directly on DIA data. We demonstrate the performance of Carafe on a wide range of DIA datasets, where we observe improved fragment ion intensity prediction and peptide detection relative to existing pretrained DDA models.</Description>
    <ReviewLevel>
      <cvParam cvRef="MS" accession="MS:1002854" name="Peer-reviewed dataset"/>
    </ReviewLevel>
    <RepositorySupport>
      <cvParam cvRef="MS" accession="MS:1002856" name="Supported dataset by repository"/>
    </RepositorySupport>
  </DatasetSummary>
  <DatasetIdentifierList>
    <DatasetIdentifier>
      <cvParam cvRef="MS" accession="MS:1001919" name="ProteomeXchange accession number" value="PXD056793"/>
      <cvParam cvRef="MS" accession="MS:1001921" name="ProteomeXchange accession number version number" value="1"/>
    </DatasetIdentifier>
    <DatasetIdentifier>
      <cvParam cvRef="MS" accession="MS:1002872" name="Panorama Public dataset identifier" value="https://panoramaweb.org/Carafe.url"/>
    </DatasetIdentifier>
  </DatasetIdentifierList>
  <DatasetOriginList>
    <DatasetOrigin>
      <cvParam cvRef="MS" accession="MS:1002868" name="Original data"/>
    </DatasetOrigin>
  </DatasetOriginList>
  <SpeciesList>
    <Species>
      <cvParam cvRef="MS" accession="MS:1001469" name="taxonomy: scientific name" value="Homo sapiens"/>
      <cvParam cvRef="MS" accession="MS:1001467" name="taxonomy: NCBI TaxID" value="9606"/>
    </Species>
    <Species>
      <cvParam cvRef="MS" accession="MS:1001469" name="taxonomy: scientific name" value="Saccharomyces cerevisiae"/>
      <cvParam cvRef="MS" accession="MS:1001467" name="taxonomy: NCBI TaxID" value="4932"/>
    </Species>
  </SpeciesList>
  <InstrumentList>
    <Instrument id="instrument_1">
      <cvParam cvRef="MS" accession="MS:1002732" name="Orbitrap Fusion Lumos"/>
    </Instrument>
    <Instrument id="instrument_2">
      <cvParam cvRef="MS" accession="MS:1003028" name="Orbitrap Exploris 480"/>
    </Instrument>
    <Instrument id="instrument_3">
      <cvParam cvRef="MS" accession="MS:1003378" name="Orbitrap Astral"/>
    </Instrument>
  </InstrumentList>
  <ModificationList>
    <cvParam cvRef="UNIMOD" accession="UNIMOD:21" name="Phospho"/>
    <cvParam cvRef="UNIMOD" accession="UNIMOD:4" name="Carbamidomethyl"/>
  </ModificationList>
  <ContactList>
    <Contact id="lab_head">
      <cvParam cvRef="MS" accession="MS:1002332" name="lab head"/>
      <cvParam cvRef="MS" accession="MS:1000586" name="contact name" value="Michael MacCoss"/>
      <cvParam cvRef="MS" accession="MS:1000589" name="contact email" value="maccoss@uw.edu"/>
      <cvParam cvRef="MS" accession="MS:1000590" name="contact affiliation" value="University of Washington"/>
    </Contact>
    <Contact id="dataset_submitter">
      <cvParam cvRef="MS" accession="MS:1002037" name="dataset submitter"/>
      <cvParam cvRef="MS" accession="MS:1000586" name="contact name" value="Chris Hsu"/>
      <cvParam cvRef="MS" accession="MS:1000589" name="contact email" value="chrhsu@uw.edu"/>
      <cvParam cvRef="MS" accession="MS:1000590" name="contact affiliation" value="University of Washington"/>
    </Contact>
  </ContactList>
  <PublicationList>
    <Publication id="pubmed_id_pending">
      <cvParam cvRef="MS" accession="MS:1002866" name="Reference" value="Wen, Bo, Chris Hsu, Wen-Feng Zeng, Michael Riffle, Alexis Chang, Miranda Mudge, Brook L. Nunn, et al. “Carafe Enables High Quality in Silico Spectral Library Generation for Data-Independent Acquisition Proteomics.” bioRxiv, 2024.10.15.618504."/>
    </Publication>
  </PublicationList>
  <KeywordList>
    <cvParam cvRef="MS" accession="MS:1001925" name="submitter keyword" value="spectral library generation"/>
    <cvParam cvRef="MS" accession="MS:1001925" name="submitter keyword" value="Carafe"/>
    <cvParam cvRef="MS" accession="MS:1001925" name="submitter keyword" value="deep learning"/>
    <cvParam cvRef="MS" accession="MS:1001925" name="submitter keyword" value="DIA"/>
  </KeywordList>
  <FullDatasetLinkList>
    <FullDatasetLink>
      <cvParam cvRef="MS" accession="MS:1002873" name="Panorama Public dataset URI" value="https://panoramaweb.org/Carafe.url"/>
    </FullDatasetLink>
  </FullDatasetLinkList>
</ProteomeXchangeDataset>