Dataset Open Access

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

Schulze, Stefan


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_FDR_summary.pkl"
      }, 
      "checksum": "md5:8b0b9d7ce8804653e9463622c5327828", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_FDR_summary.pkl", 
      "type": "pkl", 
      "size": 4397139
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_2021-06-25_peptides_incl_glyco.csv"
      }, 
      "checksum": "md5:b3cca2f24e72cdce9de4f0615f4e2554", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_2021-06-25_peptides_incl_glyco.csv", 
      "type": "csv", 
      "size": 62368190
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_2021-06-25_proteins_incl_glyco.csv"
      }, 
      "checksum": "md5:d59bc50daf5221f6613e4552ca532703", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_2021-06-25_proteins_incl_glyco.csv", 
      "type": "csv", 
      "size": 3767561
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_2021-06-25_PSMs_incl_glyco.csv"
      }, 
      "checksum": "md5:9bb1e3dbff80922f5e62f6ea9e712ca9", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_2021-06-25_PSMs_incl_glyco.csv", 
      "type": "csv", 
      "size": 679584754
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_predicted_CS.csv"
      }, 
      "checksum": "md5:0079710b440edba5491b92cd172a52ae", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_predicted_CS.csv", 
      "type": "csv", 
      "size": 36053
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_PSMs_N-glyco_v1_3.csv"
      }, 
      "checksum": "md5:f08e22afbcc3755f59b78cc76b4143ca", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_PSMs_N-glyco_v1_3.csv", 
      "type": "csv", 
      "size": 2403076
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_PSMs_non-canonical-N-glyco_v1_3.csv"
      }, 
      "checksum": "md5:05eb49d8aa12354c936ae81f52c4e487", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_PSMs_non-canonical-N-glyco_v1_3.csv", 
      "type": "csv", 
      "size": 17579
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_results_PSMs_O-glyco_v1_3.csv"
      }, 
      "checksum": "md5:c7ec5e0455ee8c44c5415627551967c5", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_results_PSMs_O-glyco_v1_3.csv", 
      "type": "csv", 
      "size": 33796
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/ArcPP_summarized_results.pkl"
      }, 
      "checksum": "md5:a52f801e323d9b87d49b212ff69b62e6", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "ArcPP_summarized_results.pkl", 
      "type": "pkl", 
      "size": 827038085
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/Haloferax_volcanii_ArcPP_20190606_uniprot_cRAP_target_decoy_gluc.fasta"
      }, 
      "checksum": "md5:bc0663da2ec8f3df84ba31fafd6c01b7", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "Haloferax_volcanii_ArcPP_20190606_uniprot_cRAP_target_decoy_gluc.fasta", 
      "type": "fasta", 
      "size": 2976734
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/Haloferax_volcanii_ArcPP_20190606_uniprot_cRAP_target_decoy_trypsin.fasta"
      }, 
      "checksum": "md5:5439b904da6e4baeb07f1848d453f974", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "Haloferax_volcanii_ArcPP_20190606_uniprot_cRAP_target_decoy_trypsin.fasta", 
      "type": "fasta", 
      "size": 2976734
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/Haloferax_volcanii_ArcPP_20190606_uniprot.fasta"
      }, 
      "checksum": "md5:3a1bdf65fd02e0ab14cdc18a15b9cfa4", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "Haloferax_volcanii_ArcPP_20190606_uniprot.fasta", 
      "type": "fasta", 
      "size": 1422105
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD000202.zip"
      }, 
      "checksum": "md5:b1035b1fa4d845d5814876ebadd45602", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD000202.zip", 
      "type": "zip", 
      "size": 12853818
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD006877.zip"
      }, 
      "checksum": "md5:896d1851482eb8d7a1abf9af390c0e08", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD006877.zip", 
      "type": "zip", 
      "size": 353841541
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD007061.zip"
      }, 
      "checksum": "md5:2102c3e3f9c100881eac1b75c00b5e0c", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD007061.zip", 
      "type": "zip", 
      "size": 485395123
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD009116.zip"
      }, 
      "checksum": "md5:8a59472dfc1f6dd9a83a1e949c4adf95", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD009116.zip", 
      "type": "zip", 
      "size": 182745835
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD010824.zip"
      }, 
      "checksum": "md5:30592a242d73f646a120825fa5c0ef3f", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD010824.zip", 
      "type": "zip", 
      "size": 41298903
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD011012.zip"
      }, 
      "checksum": "md5:895a893f85ee1dfc1acedb280d979ba1", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD011012.zip", 
      "type": "zip", 
      "size": 694084471
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD011015.zip"
      }, 
      "checksum": "md5:ad852f45499116cf9d46a5959572f057", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD011015.zip", 
      "type": "zip", 
      "size": 14835100
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD011050.zip"
      }, 
      "checksum": "md5:4cbd909e8be3bb8324c40426b997f780", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD011050.zip", 
      "type": "zip", 
      "size": 57656213
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD011056.zip"
      }, 
      "checksum": "md5:a0b57098467a73a1d1eea7acd5ddeace", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD011056.zip", 
      "type": "zip", 
      "size": 135416898
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD011218.zip"
      }, 
      "checksum": "md5:adbc0b81fed380131fc64ae3469ee10e", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD011218.zip", 
      "type": "zip", 
      "size": 165834958
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD013046.zip"
      }, 
      "checksum": "md5:b2d4cd26cd780e2cfe6514affac3cc34", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD013046.zip", 
      "type": "zip", 
      "size": 524963936
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD014974.zip"
      }, 
      "checksum": "md5:890f0a82a1ed3f099e18a0b4014b7738", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD014974.zip", 
      "type": "zip", 
      "size": 17185417
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD021827.zip"
      }, 
      "checksum": "md5:7b988961f5d1850b6f661450c256f868", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD021827.zip", 
      "type": "zip", 
      "size": 148455709
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286/PXD021874.zip"
      }, 
      "checksum": "md5:448b2166c89082637c2b4489094e992c", 
      "bucket": "185b81b2-4605-4170-bb76-6c9529270286", 
      "key": "PXD021874.zip", 
      "type": "zip", 
      "size": 183097174
    }
  ], 
  "owners": [
    87073
  ], 
  "doi": "10.5281/zenodo.5044621", 
  "stats": {
    "version_unique_downloads": 152.0, 
    "unique_views": 49.0, 
    "views": 60.0, 
    "version_views": 287.0, 
    "unique_downloads": 32.0, 
    "version_unique_views": 221.0, 
    "volume": 28996131075.0, 
    "version_downloads": 300.0, 
    "downloads": 63.0, 
    "version_volume": 107897254072.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.5044621", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3724742", 
    "bucket": "https://zenodo.org/api/files/185b81b2-4605-4170-bb76-6c9529270286", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3724742.svg", 
    "html": "https://zenodo.org/record/5044621", 
    "latest_html": "https://zenodo.org/record/5044621", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.5044621.svg", 
    "latest": "https://zenodo.org/api/records/5044621"
  }, 
  "conceptdoi": "10.5281/zenodo.3724742", 
  "created": "2021-06-30T03:45:25.036765+00:00", 
  "updated": "2021-06-30T13:48:21.589260+00:00", 
  "conceptrecid": "3724742", 
  "revision": 2, 
  "id": 5044621, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.5044621", 
    "description": "<p>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.</p>\n\n<p>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 <em>Haloferax volcanii</em>, using state-of-the-art bioinformatic tools, we have:</p>\n\n<ul>\n\t<li>reanalyzed more than 26 Mio. spectra</li>\n\t<li>optimized the analysis using parameter sweeps, multiple search engines implemented in Ursgal, and the combination of results through the combined PEP approach</li>\n\t<li>thoroughly controlled false discovery rates for high confidence protein identifications using the picked protein FDR approach and limiting FDR to 0.5%</li>\n\t<li>identified more than 45k peptides, corresponding to 3069 proteins (&gt;75% of the proteome) with a median sequence coverage of 55%.</li>\n\t<li>analyzed N-terminal protein processing, including N-terminal acetylation and signal peptide cleavage</li>\n\t<li>performed a detailed glycoproteomic analysis, identifying &gt;230 glycopeptides corresponding to 45 glycoproteins</li>\n</ul>\n\n<p>Benefiting from the established bioinformatic infrastructure, we will follow up on this analysis focusing on <em>H. volcanii</em> 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 <em>H. volcanii</em> proteome can serve as a blueprint for comprehensive proteomic analyses performed on a diverse range of archaea and bacteria.</p>\n\n<p>&nbsp;</p>\n\n<p>For further details, please refer to the following publications. Please also cite this work if you use these results for further analyses:</p>\n\n<p>Schulze, S., Adams, Z., Cerletti, M. <em>et al.</em> The Archaeal Proteome Project advances knowledge about archaeal cell biology through comprehensive proteomics. <em>Nat Commun</em> <strong>11, </strong>3145 (2020). <a href=\"https://doi.org/10.1038/s41467-020-16784-7\">https://doi.org/10.1038/s41467-020-16784-7</a></p>\n\n<p>Schulze, S.; Pfeiffer, F.; Garcia, B.A.; Pohlschroder, M. (2021). Comprehensive glycoproteomics shines new light on the complexity and extent of glycosylation in archaea. <em>PLOS Biol</em>.&nbsp; https://doi.org/10.1371/journal.pbio.3001277</p>\n\n<p>&nbsp;</p>\n\n<p>An interactive website to explore the combined results can be found at <a href=\"https://archaealproteomeproject.org/\">https://archaealproteomeproject.org/</a></p>\n\n<p>Scripts and metadata used for the analysis can be found at <a href=\"https://github.com/arcpp/ArcPP\">https://github.com/arcpp/ArcPP</a></p>\n\n<p>&nbsp;</p>\n\n<p><strong>Updates version 1.3.0:</strong></p>\n\n<p>- includes dataset PXD021827</p>\n\n<p><strong>Updates version 1.2.0:</strong></p>\n\n<p>- Includes dataset PXD021874<br>\n- Includes results from a comprehensive glycoproteomic analysis of ArcPP datasets</p>\n\n<p><strong>Updates version 1.1.0:</strong><br>\n- <em>Natrialba magadii</em> results are included in PXD009116.zip</p>", 
    "contributors": [
      {
        "orcid": "0000-0002-5095-4086", 
        "affiliation": "University of Florida", 
        "type": "DataCollector", 
        "name": "Adams, Zachary"
      }, 
      {
        "affiliation": "National University of Mar del Plata", 
        "type": "DataCollector", 
        "name": "Cerletti, Micaela"
      }, 
      {
        "orcid": "0000-0001-8889-4245", 
        "affiliation": "National University of Mar del Plata", 
        "type": "DataCollector", 
        "name": "De Castro, Rosana"
      }, 
      {
        "orcid": "0000-0002-0522-843X", 
        "affiliation": "University of Regensburg", 
        "type": "DataCollector", 
        "name": "Ferreira-Cerca, S\u00e9bastien"
      }, 
      {
        "orcid": "0000-0002-7048-6822", 
        "affiliation": "Heidelberg University", 
        "type": "DataCurator", 
        "name": "Fufezan, Christian"
      }, 
      {
        "orcid": "0000-0002-2306-1207", 
        "affiliation": "University of Pennsylvania", 
        "type": "DataCollector", 
        "name": "Garcia, Ben A."
      }, 
      {
        "affiliation": "National University of Mar del Plata", 
        "type": "DataCollector", 
        "name": "Gim\u00e9nez, Mar\u00eda In\u00e9s"
      }, 
      {
        "orcid": "0000-0001-9670-6101", 
        "affiliation": "University of M\u00fcnster", 
        "type": "DataCollector", 
        "name": "Hippler, Michael"
      }, 
      {
        "affiliation": "Max Planck Institute for Biophysical Chemistry", 
        "type": "DataCollector", 
        "name": "Jevtic, Zivojin"
      }, 
      {
        "affiliation": "University of Regensburg", 
        "type": "DataCollector", 
        "name": "Kn\u00fcppel, Robert"
      }, 
      {
        "affiliation": "University of Pennsylvania", 
        "type": "DataCollector", 
        "name": "Legerme, Georgio"
      }, 
      {
        "orcid": "0000-0002-0946-8166", 
        "affiliation": "Max Planck Institute for Biophysical Chemistry", 
        "type": "DataCollector", 
        "name": "Lenz, Christof"
      }, 
      {
        "orcid": "0000-0002-1382-1794", 
        "affiliation": "Ulm University", 
        "type": "DataCollector", 
        "name": "Marchfelder, Anita"
      }, 
      {
        "orcid": "0000-0001-6105-0923", 
        "affiliation": "University of Florida", 
        "type": "DataCollector", 
        "name": "Maupin-Furlow, Julie"
      }, 
      {
        "affiliation": "National University of Mar del Plata", 
        "type": "DataCollector", 
        "name": "Paggi, Roberto A."
      }, 
      {
        "orcid": "0000-0003-4691-3246", 
        "affiliation": "Max Planck Institute of Biochemistry", 
        "type": "DataCollector", 
        "name": "Pfeiffer, Friedhelm"
      }, 
      {
        "affiliation": "Ruhr University Bochum", 
        "type": "DataCollector", 
        "name": "Poetsch, Ansgar"
      }, 
      {
        "affiliation": "Max Planck Institute for Biophysical Chemistry", 
        "type": "DataCollector", 
        "name": "Urlaub, Henning"
      }, 
      {
        "orcid": "0000-0001-7729-1342", 
        "affiliation": "University of Pennsylvania", 
        "type": "ProjectManager", 
        "name": "Pohlschroder, Mechthild"
      }
    ], 
    "title": "The Archaeal Proteome Project advances knowledge about archaeal cell biology through comprehensive proteomics", 
    "license": {
      "id": "LGPL-3.0+"
    }, 
    "journal": {
      "volume": "11", 
      "title": "Nature Communications"
    }, 
    "relations": {
      "version": [
        {
          "count": 4, 
          "index": 3, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3724742"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5044621"
          }
        }
      ]
    }, 
    "version": "1.3.0", 
    "keywords": [
      "Proteomics", 
      "Archaea", 
      "Haloferax volcanii", 
      "Mass spectrometry", 
      "Glycosylation", 
      "N-terminal protein processing"
    ], 
    "publication_date": "2021-06-29", 
    "creators": [
      {
        "orcid": "0000-0002-4771-7987", 
        "affiliation": "University of Pennsylvania, Department of Biology", 
        "name": "Schulze, Stefan"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3724742", 
        "relation": "isVersionOf"
      }
    ]
  }
}
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