Dataset Open Access

The Archaeal Proteome Project advances knowledge about archaeal cell biology through comprehensive proteomics

Schulze, Stefan


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Proteomics</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Archaea</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Haloferax volcanii</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Mass spectrometry</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Glycosylation</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">N-terminal protein processing</subfield>
  </datafield>
  <controlfield tag="005">20210630134821.0</controlfield>
  <controlfield tag="001">5044621</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Florida</subfield>
    <subfield code="0">(orcid)0000-0002-5095-4086</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Adams, Zachary</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National University of Mar del Plata</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Cerletti, Micaela</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National University of Mar del Plata</subfield>
    <subfield code="0">(orcid)0000-0001-8889-4245</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">De Castro, Rosana</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Regensburg</subfield>
    <subfield code="0">(orcid)0000-0002-0522-843X</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Ferreira-Cerca, Sébastien</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Heidelberg University</subfield>
    <subfield code="0">(orcid)0000-0002-7048-6822</subfield>
    <subfield code="4">cur</subfield>
    <subfield code="a">Fufezan, Christian</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Pennsylvania</subfield>
    <subfield code="0">(orcid)0000-0002-2306-1207</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Garcia, Ben A.</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National University of Mar del Plata</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Giménez, María Inés</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Münster</subfield>
    <subfield code="0">(orcid)0000-0001-9670-6101</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Hippler, Michael</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Max Planck Institute for Biophysical Chemistry</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Jevtic, Zivojin</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Regensburg</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Knüppel, Robert</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Pennsylvania</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Legerme, Georgio</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Max Planck Institute for Biophysical Chemistry</subfield>
    <subfield code="0">(orcid)0000-0002-0946-8166</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Lenz, Christof</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Ulm University</subfield>
    <subfield code="0">(orcid)0000-0002-1382-1794</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Marchfelder, Anita</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Florida</subfield>
    <subfield code="0">(orcid)0000-0001-6105-0923</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Maupin-Furlow, Julie</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National University of Mar del Plata</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Paggi, Roberto A.</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Max Planck Institute of Biochemistry</subfield>
    <subfield code="0">(orcid)0000-0003-4691-3246</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Pfeiffer, Friedhelm</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Ruhr University Bochum</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Poetsch, Ansgar</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Max Planck Institute for Biophysical Chemistry</subfield>
    <subfield code="4">col</subfield>
    <subfield code="a">Urlaub, Henning</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Pennsylvania</subfield>
    <subfield code="0">(orcid)0000-0001-7729-1342</subfield>
    <subfield code="4">rth</subfield>
    <subfield code="a">Pohlschroder, Mechthild</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">4397139</subfield>
    <subfield code="z">md5:8b0b9d7ce8804653e9463622c5327828</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_FDR_summary.pkl</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">62368190</subfield>
    <subfield code="z">md5:b3cca2f24e72cdce9de4f0615f4e2554</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_2021-06-25_peptides_incl_glyco.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3767561</subfield>
    <subfield code="z">md5:d59bc50daf5221f6613e4552ca532703</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_2021-06-25_proteins_incl_glyco.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">679584754</subfield>
    <subfield code="z">md5:9bb1e3dbff80922f5e62f6ea9e712ca9</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_2021-06-25_PSMs_incl_glyco.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">36053</subfield>
    <subfield code="z">md5:0079710b440edba5491b92cd172a52ae</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_predicted_CS.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2403076</subfield>
    <subfield code="z">md5:f08e22afbcc3755f59b78cc76b4143ca</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_PSMs_N-glyco_v1_3.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">17579</subfield>
    <subfield code="z">md5:05eb49d8aa12354c936ae81f52c4e487</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_PSMs_non-canonical-N-glyco_v1_3.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">33796</subfield>
    <subfield code="z">md5:c7ec5e0455ee8c44c5415627551967c5</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_results_PSMs_O-glyco_v1_3.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">827038085</subfield>
    <subfield code="z">md5:a52f801e323d9b87d49b212ff69b62e6</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/ArcPP_summarized_results.pkl</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2976734</subfield>
    <subfield code="z">md5:bc0663da2ec8f3df84ba31fafd6c01b7</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/Haloferax_volcanii_ArcPP_20190606_uniprot_cRAP_target_decoy_gluc.fasta</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2976734</subfield>
    <subfield code="z">md5:5439b904da6e4baeb07f1848d453f974</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/Haloferax_volcanii_ArcPP_20190606_uniprot_cRAP_target_decoy_trypsin.fasta</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1422105</subfield>
    <subfield code="z">md5:3a1bdf65fd02e0ab14cdc18a15b9cfa4</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/Haloferax_volcanii_ArcPP_20190606_uniprot.fasta</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">12853818</subfield>
    <subfield code="z">md5:b1035b1fa4d845d5814876ebadd45602</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD000202.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">353841541</subfield>
    <subfield code="z">md5:896d1851482eb8d7a1abf9af390c0e08</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD006877.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">485395123</subfield>
    <subfield code="z">md5:2102c3e3f9c100881eac1b75c00b5e0c</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD007061.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">182745835</subfield>
    <subfield code="z">md5:8a59472dfc1f6dd9a83a1e949c4adf95</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD009116.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">41298903</subfield>
    <subfield code="z">md5:30592a242d73f646a120825fa5c0ef3f</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD010824.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">694084471</subfield>
    <subfield code="z">md5:895a893f85ee1dfc1acedb280d979ba1</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD011012.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">14835100</subfield>
    <subfield code="z">md5:ad852f45499116cf9d46a5959572f057</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD011015.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">57656213</subfield>
    <subfield code="z">md5:4cbd909e8be3bb8324c40426b997f780</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD011050.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">135416898</subfield>
    <subfield code="z">md5:a0b57098467a73a1d1eea7acd5ddeace</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD011056.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">165834958</subfield>
    <subfield code="z">md5:adbc0b81fed380131fc64ae3469ee10e</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD011218.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">524963936</subfield>
    <subfield code="z">md5:b2d4cd26cd780e2cfe6514affac3cc34</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD013046.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">17185417</subfield>
    <subfield code="z">md5:890f0a82a1ed3f099e18a0b4014b7738</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD014974.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">148455709</subfield>
    <subfield code="z">md5:7b988961f5d1850b6f661450c256f868</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD021827.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">183097174</subfield>
    <subfield code="z">md5:448b2166c89082637c2b4489094e992c</subfield>
    <subfield code="u">https://zenodo.org/record/5044621/files/PXD021874.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-06-29</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:5044621</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="4">
    <subfield code="v">11</subfield>
    <subfield code="p">Nature Communications</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Pennsylvania, Department of Biology</subfield>
    <subfield code="0">(orcid)0000-0002-4771-7987</subfield>
    <subfield code="a">Schulze, Stefan</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">The Archaeal Proteome Project advances knowledge about archaeal cell biology through comprehensive proteomics</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://opensource.org/licenses/LGPL-3.0</subfield>
    <subfield code="a">GNU Lesser General Public License v3.0 or later</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Modern proteomics approaches can explore whole proteomes within a single mass spectrometry (MS) run. However, the enormous amount of MS data generated often remains incompletely analyzed due to a lack of sophisticated bioinformatic tools and expertise needed from a diverse array of fields. In particular, in the field of microbiology, efforts to combine large-scale proteomic datasets have so far largely been missing. Thus, despite their relatively small genomes, the proteomes of most archaea remain incompletely characterized. This in turn undermines our ability to gain a greater understanding of archaeal cell biology.&lt;/p&gt;

&lt;p&gt;Therefore, we have initiated the Archaeal Proteome Project (ArcPP), a community effort that works towards a comprehensive analysis of archaeal proteomes. Starting with the model archaeon &lt;em&gt;Haloferax volcanii&lt;/em&gt;, using state-of-the-art bioinformatic tools, we have:&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;reanalyzed more than 26 Mio. spectra&lt;/li&gt;
	&lt;li&gt;optimized the analysis using parameter sweeps, multiple search engines implemented in Ursgal, and the combination of results through the combined PEP approach&lt;/li&gt;
	&lt;li&gt;thoroughly controlled false discovery rates for high confidence protein identifications using the picked protein FDR approach and limiting FDR to 0.5%&lt;/li&gt;
	&lt;li&gt;identified more than 45k peptides, corresponding to 3069 proteins (&amp;gt;75% of the proteome) with a median sequence coverage of 55%.&lt;/li&gt;
	&lt;li&gt;analyzed N-terminal protein processing, including N-terminal acetylation and signal peptide cleavage&lt;/li&gt;
	&lt;li&gt;performed a detailed glycoproteomic analysis, identifying &amp;gt;230 glycopeptides corresponding to 45 glycoproteins&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Benefiting from the established bioinformatic infrastructure, we will follow up on this analysis focusing on &lt;em&gt;H. volcanii&lt;/em&gt; proteogenomics as well as the characterization of additional post-translational modifications. Furthermore, ArcPP will integrate quantitative results obtained from the individual datasets in order to identify common regulatory mechanisms. These studies on the &lt;em&gt;H. volcanii&lt;/em&gt; proteome can serve as a blueprint for comprehensive proteomic analyses performed on a diverse range of archaea and bacteria.&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;For further details, please refer to the following publications. Please also cite this work if you use these results for further analyses:&lt;/p&gt;

&lt;p&gt;Schulze, S., Adams, Z., Cerletti, M. &lt;em&gt;et al.&lt;/em&gt; The Archaeal Proteome Project advances knowledge about archaeal cell biology through comprehensive proteomics. &lt;em&gt;Nat Commun&lt;/em&gt; &lt;strong&gt;11, &lt;/strong&gt;3145 (2020). &lt;a href="https://doi.org/10.1038/s41467-020-16784-7"&gt;https://doi.org/10.1038/s41467-020-16784-7&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;Schulze, S.; Pfeiffer, F.; Garcia, B.A.; Pohlschroder, M. (2021). Comprehensive glycoproteomics shines new light on the complexity and extent of glycosylation in archaea. &lt;em&gt;PLOS Biol&lt;/em&gt;.&amp;nbsp; https://doi.org/10.1371/journal.pbio.3001277&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;An interactive website to explore the combined results can be found at &lt;a href="https://archaealproteomeproject.org/"&gt;https://archaealproteomeproject.org/&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;Scripts and metadata used for the analysis can be found at &lt;a href="https://github.com/arcpp/ArcPP"&gt;https://github.com/arcpp/ArcPP&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Updates version 1.3.0:&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;- includes dataset PXD021827&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Updates version 1.2.0:&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;- Includes dataset PXD021874&lt;br&gt;
- Includes results from a comprehensive glycoproteomic analysis of ArcPP datasets&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Updates version 1.1.0:&lt;/strong&gt;&lt;br&gt;
- &lt;em&gt;Natrialba magadii&lt;/em&gt; results are included in PXD009116.zip&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3724742</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.5044621</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
287
300
views
downloads
All versions This version
Views 28760
Downloads 30063
Data volume 107.9 GB29.0 GB
Unique views 22149
Unique downloads 15232

Share

Cite as