{"data":{"id":"10.4121/16896406","type":"dois","attributes":{"doi":"10.4121/16896406","prefix":"10.4121","suffix":"16896406","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Béquignon, Olivier","nameType":"Personal","givenName":"Olivier","familyName":"Béquignon","nameIdentifiers":[{"nameIdentifier":"0000-0002-7554-9220","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"Bongers, Brandon","nameType":"Personal","givenName":"Brandon","familyName":"Bongers","nameIdentifiers":[{"nameIdentifier":"0000-0003-1322-2369","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"Jespers, W. (Willem)","givenName":"W. (Willem)","familyName":"Jespers","affiliation":[],"nameIdentifiers":[]},{"name":"IJzerman, Adriaan P.","nameType":"Personal","givenName":"Adriaan P.","familyName":"IJzerman","nameIdentifiers":[{"nameIdentifier":"0000-0002-1182-2259","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]},{"name":"van de Water, Bob","givenName":"Bob","familyName":"van de Water","affiliation":[],"nameIdentifiers":[]},{"name":"Van westen, Gerard JP","nameType":"Personal","givenName":"Gerard JP","familyName":"Van westen","nameIdentifiers":[{"nameIdentifier":"0000-0003-0717-1817","nameIdentifierScheme":"https://orcid.org/"}],"affiliation":[]}],"titles":[{"title":"Papyrus - A large scale curated dataset aimed at bioactivity predictions"}],"publisher":"4TU.ResearchData","container":{},"publicationYear":2022,"subjects":[{"subject":"Theoretical and Computational Chemistry","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0307"},{"subject":"FOS: Chemical sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"Medicinal and Biomolecular Chemistry","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0304"},{"subject":"Artificial Intelligence and Image Processing","subjectScheme":"Australian and New Zealand Standard Research Classification (ANZSRC), 2008","classificationCode":"0801"},{"subject":"FOS: Computer and information sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"Papyrus"},{"subject":"machine Learning Predictions"},{"subject":"cheminformatics tool"},{"subject":"bioactivity data"},{"subject":"curated dataset"}],"contributors":[{"name":"Leiden Academic Centre For Drug Research (LACDR), The Netherlands","nameType":"Organizational","affiliation":[],"contributorType":"Other","nameIdentifiers":[]},{"name":"Leiden University, The Netherlands","nameType":"Organizational","affiliation":[],"contributorType":"Other","nameIdentifiers":[]}],"dates":[{"date":"2022-04-04","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[],"relatedItems":[],"sizes":[],"formats":["g-zipped tab-separated files and g-zipped SD files"],"version":"3","rightsList":[{"rights":"Creative Commons Attribution Share Alike 4.0 International","rightsUri":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-sa-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This repository contains the Papyrus dataset, an aggregated dataset of small molecule bioactivities, as described in the manuscript \"Papyrus - A large scale curated dataset aimed at bioactivity predictions\" (Work in Progress).With the recent rapid growth of publicly available ligand-protein bioactivity data, there is a trove of viable data that can be used to train machine learning algorithms. However, not all data is equal in terms of size and quality, and a significant portion of researcher’s time is needed to adapt the data to their needs. On top of that, finding the right data for a research question can often be a challenge on its own. As an answer to that, we have constructed the Papyrus dataset, comprised of around 60 million datapoints. This dataset contains multiple large publicly available datasets such as ChEMBL and ExCAPE-DB combined with smaller datasets containing high quality data. This aggregated data has been standardised and normalised in a manner that is suitable for machine learning. We show how data can be filtered in a variety of ways, and also perform some rudimentary quantitative structure-activity relationship and proteochemometrics modeling. Our ambition is to create a benchmark set that can be used for constructing predictive models, while also providing a solid baseline for related research.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[{"awardTitle":"Enhacing TRANslational SAFEty Assessment through Integrative Knowledge Management","funderName":"European Commission","awardNumber":"777365"}],"xml":"PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KPHJlc291cmNlIHhtbG5zPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCIgeG1sbnM6eHNpPSJodHRwOi8vd3d3LnczLm9yZy8yMDAxL1hNTFNjaGVtYS1pbnN0YW5jZSIgeHNpOnNjaGVtYUxvY2F0aW9uPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCBodHRwOi8vc2NoZW1hLmRhdGFjaXRlLm9yZy9tZXRhL2tlcm5lbC00LjQvbWV0YWRhdGEueHNkIj4KICA8aWRlbnRpZmllciBpZGVudGlmaWVyVHlwZT0iRE9JIj4xMC40MTIxLzE2ODk2NDA2PC9pZGVudGlmaWVyPgogIDxjcmVhdG9ycz4KICAgIDxjcmVhdG9yPgogICAgICA8Y3JlYXRvck5hbWUgbmFtZVR5cGU9IlBlcnNvbmFsIj5PbGl2aWVyIELDqXF1aWdub248L2NyZWF0b3JOYW1lPgogICAgICA8Z2l2ZW5OYW1lPk9saXZpZXI8L2dpdmVuTmFtZT4KICAgICAgPGZhbWlseU5hbWU+QsODwqlxdWlnbm9uPC9mYW1pbHlOYW1lPgogICAgICA8bmFtZUlkZW50aWZpZXIgbmFtZUlkZW50aWZpZXJTY2hlbWU9Imh0dHBzOi8vb3JjaWQub3JnLyI+MDAwMC0wMDAyLTc1NTQtOTIyMDwvbmFtZUlkZW50aWZpZXI+CiAgICA8L2NyZWF0b3I+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lIG5hbWVUeXBlPSJQZXJzb25hbCI+QnJhbmRvbiBCb25nZXJzPC9jcmVhdG9yTmFtZT4KICAgICAgPGdpdmVuTmFtZT5CcmFuZG9uPC9naXZlbk5hbWU+CiAgICAgIDxmYW1pbHlOYW1lPkJvbmdlcnM8L2ZhbWlseU5hbWU+CiAgICAgIDxuYW1lSWRlbnRpZmllciBuYW1lSWRlbnRpZmllclNjaGVtZT0iaHR0cHM6Ly9vcmNpZC5vcmcvIj4wMDAwLTAwMDMtMTMyMi0yMzY5PC9uYW1lSWRlbnRpZmllcj4KICAgIDwvY3JlYXRvcj4KICAgIDxjcmVhdG9yPgogICAgICA8Y3JlYXRvck5hbWU+Vy4gKFdpbGxlbSkgSmVzcGVyczwvY3JlYXRvck5hbWU+CiAgICAgIDxnaXZlbk5hbWU+Vy4gKFdpbGxlbSk8L2dpdmVuTmFtZT4KICAgICAgPGZhbWlseU5hbWU+SmVzcGVyczwvZmFtaWx5TmFtZT4KICAgIDwvY3JlYXRvcj4KICAgIDxjcmVhdG9yPgogICAgICA8Y3JlYXRvck5hbWUgbmFtZVR5cGU9IlBlcnNvbmFsIj5BZHJpYWFuIFAuIElKemVybWFuPC9jcmVhdG9yTmFtZT4KICAgICAgPGdpdmVuTmFtZT5BZHJpYWFuIFAuPC9naXZlbk5hbWU+CiAgICAgIDxmYW1pbHlOYW1lPklKemVybWFuPC9mYW1pbHlOYW1lPgogICAgICA8bmFtZUlkZW50aWZpZXIgbmFtZUlkZW50aWZpZXJTY2hlbWU9Imh0dHBzOi8vb3JjaWQub3JnLyI+MDAwMC0wMDAyLTExODItMjI1OTwvbmFtZUlkZW50aWZpZXI+CiAgICA8L2NyZWF0b3I+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lPkJvYiB2YW4gZGUgV2F0ZXI8L2NyZWF0b3JOYW1lPgogICAgICA8Z2l2ZW5OYW1lPkJvYjwvZ2l2ZW5OYW1lPgogICAgICA8ZmFtaWx5TmFtZT52YW4gZGUgV2F0ZXI8L2ZhbWlseU5hbWU+CiAgICA8L2NyZWF0b3I+CiAgICA8Y3JlYXRvcj4KICAgICAgPGNyZWF0b3JOYW1lIG5hbWVUeXBlPSJQZXJzb25hbCI+R2VyYXJkIEpQIFZhbiB3ZXN0ZW48L2NyZWF0b3JOYW1lPgogICAgICA8Z2l2ZW5OYW1lPkdlcmFyZCBKUDwvZ2l2ZW5OYW1lPgogICAgICA8ZmFtaWx5TmFtZT5WYW4gd2VzdGVuPC9mYW1pbHlOYW1lPgogICAgICA8bmFtZUlkZW50aWZpZXIgbmFtZUlkZW50aWZpZXJTY2hlbWU9Imh0dHBzOi8vb3JjaWQub3JnLyI+MDAwMC0wMDAzLTA3MTctMTgxNzwvbmFtZUlkZW50aWZpZXI+CiAgICA8L2NyZWF0b3I+CiAgPC9jcmVhdG9ycz4KICA8dGl0bGVzPgogICAgPHRpdGxlPlBhcHlydXMgLSBBIGxhcmdlIHNjYWxlIGN1cmF0ZWQgZGF0YXNldCBhaW1lZCBhdCBiaW9hY3Rpdml0eSBwcmVkaWN0aW9uczwvdGl0bGU+CiAgPC90aXRsZXM+CiAgPHB1Ymxpc2hlcj40VFUuUmVzZWFyY2hEYXRhPC9wdWJsaXNoZXI+CiAgPHB1YmxpY2F0aW9uWWVhcj4yMDIyPC9wdWJsaWNhdGlvblllYXI+CiAgPHJlc291cmNlVHlwZSByZXNvdXJjZVR5cGVHZW5lcmFsPSJEYXRhc2V0Ij5EYXRhc2V0PC9yZXNvdXJjZVR5cGU+CiAgPHN1YmplY3RzPgogICAgPHN1YmplY3Qgc3ViamVjdFNjaGVtZT0iQXVzdHJhbGlhbiBhbmQgTmV3IFplYWxhbmQgU3RhbmRhcmQgUmVzZWFyY2ggQ2xhc3NpZmljYXRpb24gKEFOWlNSQyksIDIwMDgiIGNsYXNzaWZpY2F0aW9uQ29kZT0iMDMwNyI+VGhlb3JldGljYWwgYW5kIENvbXB1dGF0aW9uYWwgQ2hlbWlzdHJ5PC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc3ViamVjdFNjaGVtZT0iQXVzdHJhbGlhbiBhbmQgTmV3IFplYWxhbmQgU3RhbmRhcmQgUmVzZWFyY2ggQ2xhc3NpZmljYXRpb24gKEFOWlNSQyksIDIwMDgiIGNsYXNzaWZpY2F0aW9uQ29kZT0iMDMwNCI+TWVkaWNpbmFsIGFuZCBCaW9tb2xlY3VsYXIgQ2hlbWlzdHJ5PC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc3ViamVjdFNjaGVtZT0iQXVzdHJhbGlhbiBhbmQgTmV3IFplYWxhbmQgU3RhbmRhcmQgUmVzZWFyY2ggQ2xhc3NpZmljYXRpb24gKEFOWlNSQyksIDIwMDgiIGNsYXNzaWZpY2F0aW9uQ29kZT0iMDgwMSI+QXJ0aWZpY2lhbCBJbnRlbGxpZ2VuY2UgYW5kIEltYWdlIFByb2Nlc3Npbmc8L3N1YmplY3Q+CiAgICA8c3ViamVjdD5QYXB5cnVzPC9zdWJqZWN0PgogICAgPHN1YmplY3Q+bWFjaGluZSBMZWFybmluZyBQcmVkaWN0aW9uczwvc3ViamVjdD4KICAgIDxzdWJqZWN0PmNoZW1pbmZvcm1hdGljcyB0b29sPC9zdWJqZWN0PgogICAgPHN1YmplY3Q+YmlvYWN0aXZpdHkgZGF0YTwvc3ViamVjdD4KICAgIDxzdWJqZWN0PmN1cmF0ZWQgZGF0YXNldDwvc3ViamVjdD4KICA8L3N1YmplY3RzPgogIDxjb250cmlidXRvcnM+CiAgICA8Y29udHJpYnV0b3IgY29udHJpYnV0b3JUeXBlPSJPdGhlciI+CiAgICAgIDxjb250cmlidXRvck5hbWUgbmFtZVR5cGU9Ik9yZ2FuaXphdGlvbmFsIj5MZWlkZW4gQWNhZGVtaWMgQ2VudHJlIGZvciBEcnVnIFJlc2VhcmNoIChMQUNEUiksIFRoZSBOZXRoZXJsYW5kczwvY29udHJpYnV0b3JOYW1lPgogICAgPC9jb250cmlidXRvcj4KICAgIDxjb250cmlidXRvciBjb250cmlidXRvclR5cGU9Ik90aGVyIj4KICAgICAgPGNvbnRyaWJ1dG9yTmFtZSBuYW1lVHlwZT0iT3JnYW5pemF0aW9uYWwiPkxlaWRlbiBVbml2ZXJzaXR5LCBUaGUgTmV0aGVybGFuZHM8L2NvbnRyaWJ1dG9yTmFtZT4KICAgIDwvY29udHJpYnV0b3I+CiAgPC9jb250cmlidXRvcnM+CiAgPGRhdGVzPgogICAgPGRhdGUgZGF0ZVR5cGU9Iklzc3VlZCI+MjAyMi0wNC0wNDwvZGF0ZT4KICA8L2RhdGVzPgogIDxmb3JtYXRzPgogICAgPGZvcm1hdD5nLXppcHBlZCB0YWItc2VwYXJhdGVkIGZpbGVzIGFuZCBnLXppcHBlZCBTRCBmaWxlczwvZm9ybWF0PgogIDwvZm9ybWF0cz4KICA8dmVyc2lvbj4zPC92ZXJzaW9uPgogIDxyaWdodHNMaXN0PgogICAgPHJpZ2h0cyByaWdodHNVUkk9Imh0dHBzOi8vY3JlYXRpdmVjb21tb25zLm9yZy9saWNlbnNlcy9ieS1zYS80LjAvIj5DQyBCWS1TQSA0LjA8L3JpZ2h0cz4KICA8L3JpZ2h0c0xpc3Q+CiAgPGRlc2NyaXB0aW9ucz4KICAgIDxkZXNjcmlwdGlvbiBkZXNjcmlwdGlvblR5cGU9IkFic3RyYWN0Ij4mbHQ7cCZndDtUaGlzIHJlcG9zaXRvcnkgY29udGFpbnMgdGhlIFBhcHlydXMgZGF0YXNldCwgYW4gYWdncmVnYXRlZCBkYXRhc2V0IG9mIHNtYWxsIG1vbGVjdWxlIGJpb2FjdGl2aXRpZXMsIGFzIGRlc2NyaWJlZCBpbiB0aGUgbWFudXNjcmlwdCAiUGFweXJ1cyAtIEEgbGFyZ2Ugc2NhbGUgY3VyYXRlZCBkYXRhc2V0IGFpbWVkIGF0IGJpb2FjdGl2aXR5IHByZWRpY3Rpb25zIiAoV29yayBpbiBQcm9ncmVzcykuJmx0Oy9wJmd0OyZsdDtwJmd0O1dpdGggdGhlCnJlY2VudCByYXBpZCBncm93dGggb2YgcHVibGljbHkgYXZhaWxhYmxlIGxpZ2FuZC1wcm90ZWluIGJpb2FjdGl2aXR5IGRhdGEsCnRoZXJlIGlzIGEgdHJvdmUgb2YgdmlhYmxlIGRhdGEgdGhhdCBjYW4gYmUgdXNlZCB0byB0cmFpbiBtYWNoaW5lIGxlYXJuaW5nCmFsZ29yaXRobXMuIEhvd2V2ZXIsIG5vdCBhbGwgZGF0YSBpcyBlcXVhbCBpbiB0ZXJtcyBvZiBzaXplIGFuZCBxdWFsaXR5LCBhbmQgYQpzaWduaWZpY2FudCBwb3J0aW9uIG9mIHJlc2VhcmNoZXLigJlzIHRpbWUgaXMgbmVlZGVkIHRvIGFkYXB0IHRoZSBkYXRhIHRvIHRoZWlyCm5lZWRzLiBPbiB0b3Agb2YgdGhhdCwgZmluZGluZyB0aGUgcmlnaHQgZGF0YSBmb3IgYSByZXNlYXJjaCBxdWVzdGlvbiBjYW4gb2Z0ZW4KYmUgYSBjaGFsbGVuZ2Ugb24gaXRzIG93bi4gQXMgYW4gYW5zd2VyIHRvIHRoYXQsIHdlIGhhdmUgY29uc3RydWN0ZWQgdGhlClBhcHlydXMgZGF0YXNldCwgY29tcHJpc2VkIG9mIGFyb3VuZCA2MCBtaWxsaW9uIGRhdGFwb2ludHMuIFRoaXMgZGF0YXNldApjb250YWlucyBtdWx0aXBsZSBsYXJnZSBwdWJsaWNseSBhdmFpbGFibGUgZGF0YXNldHMgc3VjaCBhcyBDaEVNQkwgYW5kCkV4Q0FQRS1EQiBjb21iaW5lZCB3aXRoIHNtYWxsZXIgZGF0YXNldHMgY29udGFpbmluZyBoaWdoIHF1YWxpdHkgZGF0YS4gVGhpcwphZ2dyZWdhdGVkIGRhdGEgaGFzIGJlZW4gc3RhbmRhcmRpc2VkIGFuZCBub3JtYWxpc2VkIGluIGEgbWFubmVyIHRoYXQgaXMKc3VpdGFibGUgZm9yIG1hY2hpbmUgbGVhcm5pbmcuIFdlIHNob3cgaG93IGRhdGEgY2FuIGJlIGZpbHRlcmVkIGluIGEgdmFyaWV0eSBvZgp3YXlzLCBhbmQgYWxzbyBwZXJmb3JtIHNvbWUgcnVkaW1lbnRhcnkgcXVhbnRpdGF0aXZlIHN0cnVjdHVyZS1hY3Rpdml0eQpyZWxhdGlvbnNoaXAgYW5kIHByb3Rlb2NoZW1vbWV0cmljcyBtb2RlbGluZy4gT3VyIGFtYml0aW9uIGlzIHRvIGNyZWF0ZSBhCmJlbmNobWFyayBzZXQgdGhhdCBjYW4gYmUgdXNlZCBmb3IgY29uc3RydWN0aW5nIHByZWRpY3RpdmUgbW9kZWxzLCB3aGlsZSBhbHNvCnByb3ZpZGluZyBhIHNvbGlkIGJhc2VsaW5lIGZvciByZWxhdGVkIHJlc2VhcmNoLiZsdDsvcCZndDs8L2Rlc2NyaXB0aW9uPgogIDwvZGVzY3JpcHRpb25zPgogIDxmdW5kaW5nUmVmZXJlbmNlcz4KICAgIDxmdW5kaW5nUmVmZXJlbmNlPgogICAgICA8ZnVuZGVyTmFtZT5FdXJvcGVhbiBDb21taXNzaW9uPC9mdW5kZXJOYW1lPgogICAgICA8YXdhcmROdW1iZXI+Nzc3MzY1PC9hd2FyZE51bWJlcj4KICAgICAgPGF3YXJkVGl0bGU+RW5oYWNpbmcgVFJBTnNsYXRpb25hbCBTQUZFdHkgQXNzZXNzbWVudCB0aHJvdWdoIEludGVncmF0aXZlIEtub3dsZWRnZSBNYW5hZ2VtZW50PC9hd2FyZFRpdGxlPgogICAgPC9mdW5kaW5nUmVmZXJlbmNlPgogIDwvZnVuZGluZ1JlZmVyZW5jZXM+CjwvcmVzb3VyY2U+","url":"https://data.4tu.nl/articles/_/16896406","contentUrl":null,"metadataVersion":8,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2021-10-28T13:37:08.000Z","registered":"2021-10-28T13:37:09.000Z","published":"2022","updated":"2022-08-30T13:48:26.000Z"},"relationships":{"client":{"data":{"id":"delft.data4tu","type":"clients"}},"provider":{"data":{"id":"scpr","type":"providers"}},"media":{"data":{"id":"10.4121/16896406","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}