{"authors":[{"id":"orcid_______::22f4e6a354a54d10b1b19e47d6186bbb","fullName":"Friesacher, Hannah Rosa","name":"Hannah Rosa","surname":"Friesacher","rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0002-0047-0964"},"provenance":null}},{"id":null,"fullName":"Svensson, Emma","name":"Emma","surname":"Svensson","rank":2,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0001-5598-0286"},"provenance":null}},{"id":null,"fullName":"Winiwarter, Susanne","name":"Susanne","surname":"Winiwarter","rank":3,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-9808-1683"},"provenance":null}},{"id":null,"fullName":"Mervin, Lewis","name":"Lewis","surname":"Mervin","rank":4,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-7271-0824"},"provenance":null}},{"id":null,"fullName":"Arany, Adam","name":"Adam","surname":"Arany","rank":5,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-4901-7650"},"provenance":null}},{"id":null,"fullName":"Engkvist, Ola","name":"Ola","surname":"Engkvist","rank":6,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-4970-6461"},"provenance":null}}],"openAccessColor":null,"publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"eng","label":"English"},"countries":[{"code":"BE","label":"Belgium","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Biochemistry & Molecular Biology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Science & Technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"INFORMATION"},"provenance":null},{"subject":{"scheme":"keyword","value":"Distribution shift"},"provenance":null},{"subject":{"scheme":"keyword","value":"Drug discovery"},"provenance":null},{"subject":{"scheme":"keyword","value":"PREDICTION"},"provenance":null},{"subject":{"scheme":"keyword","value":"Chemistry, Multidisciplinary"},"provenance":null},{"subject":{"scheme":"keyword","value":"Temporal evaluation"},"provenance":null},{"subject":{"scheme":"FOS","value":"01 natural sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science, Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null},{"subject":{"scheme":"keyword","value":"DRUG DISCOVERY"},"provenance":null},{"subject":{"scheme":"keyword","value":"Chemistry"},"provenance":null},{"subject":{"scheme":"keyword","value":"LIPOPHILICITY"},"provenance":null},{"subject":{"scheme":"keyword","value":"Physical Sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science"},"provenance":null},{"subject":{"scheme":"keyword","value":"Probability calibration"},"provenance":null},{"subject":{"scheme":"keyword","value":"NETWORK"},"provenance":null},{"subject":{"scheme":"FOS","value":"0101 mathematics"},"provenance":null},{"subject":{"scheme":"keyword","value":"Life Sciences & Biomedicine"},"provenance":null},{"subject":{"scheme":"keyword","value":"Uncertainty quantification"},"provenance":null}],"mainTitle":"Temporal distribution shift in real-world pharmaceutical data: Implications for uncertainty quantification in QSAR models","subTitle":null,"descriptions":["The estimation of uncertainties associated with predictions from quantitative structure-activity relationship (QSAR) models can accelerate the drug discovery process by identifying promising experiments and allowing an efficient allocation of resources. Several computational tools exist that estimate the predictive uncertainty in machine learning models. However, deviations from the i.i.d. setting have been shown to impair the performance of these uncertainty quantification methods. We use a real-world pharmaceutical dataset to address the pressing need for a comprehensive, large-scale evaluation of uncertainty estimation methods in the context of realistic distribution shifts over time. We investigate the performance of several uncertainty estimation methods, including ensemble-based and Bayesian approaches. Furthermore, we use this real-world setting to systematically assess the distribution shifts in label and descriptor space and their impact on the capability of the uncertainty estimation methods. Our study reveals significant shifts over time in both label and descriptor space and a clear connection between the magnitude of the shift and the nature of the assay. Moreover, we show that pronounced distribution shifts impair the performance of popular uncertainty estimation methods used in QSAR models. This work highlights the challenges of identifying uncertainty quantification methods that remain reliable under distribution shifts introduced by real-world data."],"publicationDate":"2025-12-01","publisher":"Elsevier BV","embargoEndDate":"2025-02-01","sources":["Crossref","Artificial Intelligence in the Life Sciences"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Artificial Intelligence in the Life Sciences","issnPrinted":"2667-3185","issnOnline":null,"issnLinking":null,"ep":null,"iss":null,"sp":"100132","vol":"8","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::42ba43fc055591cf73ef3ca46af0ae52","originalIds":["S266731852500008X","10.1016/j.ailsci.2025.100132","50|doiboost____|5f6e18d9109ad7c7ea39fc164fc2f2b8","50|datacite____::42ba43fc055591cf73ef3ca46af0ae52","10.48550/arxiv.2502.03982","50|od________18::16025e092c9949c35bd91a2c3f6d6712","oai:arXiv.org:2502.03982","50|dblp________::06970c900d1620d598383a8b0af569ec","50|od______1131::292f9aa81ec59fd17b31e5a7e1a2f79f","oai:lirias2repo.kuleuven.be:20.500.12942/770975","oai:zenodo.org:17007105","50|od______2659::5f6e18d9109ad7c7ea39fc164fc2f2b8","50|r3c4b2081b22::5f6e18d9109ad7c7ea39fc164fc2f2b8"],"pids":[{"scheme":"doi","value":"10.1016/j.ailsci.2025.100132"},{"scheme":"doi","value":"10.48550/arxiv.2502.03982"},{"scheme":"arXiv","value":"2502.03982"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":2.0,"influence":2.2278492E-9,"popularity":3.590891E-9,"impulse":2.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C4"}},"projects":[{"id":"corda__h2020::673ee2765cfbdfcba9112920a874fb1e","code":"956832","acronym":"AIDD","title":"Advanced machine learning for Innovative Drug Discovery","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/956832"}]}],"organizations":[{"legalName":"Chalmers University of Technology","acronym":"Chalmers University of Technology","id":"openorgs____::a84ddd5e002000d5c3caee5bcd9e2cfe","pids":[{"scheme":"fundref","value":"501100002835"},{"scheme":"ISNI","value":"0000000107756028"},{"scheme":"ROR","value":"https://ror.org/040wg7k59"},{"scheme":"wikidata","value":"Q836805"},{"scheme":"PIC","value":"999980373"},{"scheme":"FundRef","value":"501100002835"},{"scheme":"OrgReg","value":"SE0009"},{"scheme":"FundRef","value":"501100022277"},{"scheme":"OrgRef","value":"5690"},{"scheme":"FundRef","value":"501100006552"},{"scheme":"GRID","value":"grid.5371.0"},{"scheme":"mag_id","value":"66862912"},{"scheme":"Wikidata","value":"Q929994"},{"scheme":"fundref","value":"501100022277"},{"scheme":"fundref","value":"501100006552"},{"scheme":"Wikidata","value":"Q836805"},{"scheme":"wikidata","value":"Q929994"}]},{"legalName":"KU Leuven","acronym":"KUL","id":"openorgs____::ccc0a066b56d2cfaf90c2ae369df16f5","pids":[{"scheme":"OrgReg","value":"BE0056"},{"scheme":"FundRef","value":"501100004040"},{"scheme":"RRID","value":"RRID:nlx_149306"},{"scheme":"GRID","value":"grid.5596.f"},{"scheme":"wikidata","value":"Q833670"},{"scheme":"ROR","value":"https://ror.org/05f950310"},{"scheme":"OrgRef","value":"3086876"},{"scheme":"fundref","value":"501100004040"},{"scheme":"FundRef","value":"501100004497"},{"scheme":"OrgRef","value":"25524686"},{"scheme":"fundref","value":"501100004497"},{"scheme":"PIC","value":"999991334"},{"scheme":"OrgRef","value":"29975400"},{"scheme":"ISNI","value":"0000000106687884"},{"scheme":"RRID","value":"RRID:SCR_001099"},{"scheme":"Wikidata","value":"Q833670"}]},{"legalName":"Johannes Kepler University of Linz","acronym":"JKU","id":"openorgs____::ed353c4c5a10d92457fa9230b85ca987","pids":[{"scheme":"OrgRef","value":"47002155"},{"scheme":"ROR","value":"https://ror.org/052r2xn60"},{"scheme":"RRID","value":"RRID:nlx_156101"},{"scheme":"RRID","value":"RRID:SCR_011333"},{"scheme":"Wikidata","value":"Q682739"},{"scheme":"mag_id","value":"121883995"},{"scheme":"wikidata","value":"Q682739"},{"scheme":"ISNI","value":"0000000119415140"},{"scheme":"GRID","value":"grid.9970.7"},{"scheme":"fundref","value":"501100013695"},{"scheme":"FundRef","value":"501100013695"}]},{"legalName":"AstraZeneca (Sweden)","acronym":"AstraZeneca (Sweden)","id":"openorgs____::a6d2e34a262a205add3b3f048bf5dd59","pids":[{"scheme":"ISNI","value":"0000000115196403"},{"scheme":"PIC","value":"999941379"},{"scheme":"ROR","value":"https://ror.org/04wwrrg31"},{"scheme":"GRID","value":"grid.418151.8"}]},{"legalName":"AstraZeneca (United Kingdom)","acronym":"AstraZeneca (United Kingdom)","id":"openorgs____::ca28f2bc8e1fc4cfa65b02026a072d38","pids":[{"scheme":"FundRef","value":"100004325"},{"scheme":"wikidata","value":"Q731938"},{"scheme":"fundref","value":"501100004628"},{"scheme":"GRID","value":"grid.417815.e"},{"scheme":"Wikidata","value":"Q731938"},{"scheme":"fundref","value":"100004325"},{"scheme":"ISNI","value":"0000000459294381"},{"scheme":"mag_id","value":"105036370"},{"scheme":"ROR","value":"https://ror.org/04r9x1a08"},{"scheme":"OrgRef","value":"441872"},{"scheme":"PIC","value":"998178404"},{"scheme":"FundRef","value":"501100004628"}]}],"communities":[{"code":"eosc","label":"EOSC","provenance":null}],"collectedFrom":[{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"},{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},{"key":"opendoar____::fe709c654eac84d5239d1a12a4f71877","value":"Lirias"},{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},{"key":"re3data_____::c4b2081b224be6b3e79d0e5e5556f631","value":"European Union Open Data Portal"}],"instances":[{"pids":[{"scheme":"doi","value":"10.1016/j.ailsci.2025.100132"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":"gold"},"type":"Article","urls":["https://doi.org/10.1016/j.ailsci.2025.100132"],"publicationDate":"2025-12-01","refereed":"peerReviewed","hostedBy":{"key":"doajarticles::4fb683619d44e078494e582e7351dbb4","value":"Artificial Intelligence in the Life Sciences"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2502.03982"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2502.03982"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"pids":[{"scheme":"arXiv","value":"2502.03982"}],"accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Preprint","urls":["http://arxiv.org/abs/2502.03982"],"publicationDate":"2025-02-06","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},"collectedFrom":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.48550/arxiv.2502.03982"}],"type":"Preprint","urls":["https://doi.org/10.48550/arXiv.2502.03982"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},"collectedFrom":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.ailsci.2025.100132"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["https://doi.org/10.1016/j.ailsci.2025.100132","https://lirias.kuleuven.be/handle/20.500.12942/770975"],"publicationDate":"2025-12-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::fe709c654eac84d5239d1a12a4f71877","value":"Lirias"},"collectedFrom":{"key":"opendoar____::fe709c654eac84d5239d1a12a4f71877","value":"Lirias"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.ailsci.2025.100132"},{"scheme":"oai","value":"oai:zenodo.org:17007105"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["http://dx.doi.org/10.1016/j.ailsci.2025.100132","https://zenodo.org/records/17007105"],"publicationDate":"2025-07-10","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},"collectedFrom":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.ailsci.2025.100132"}],"accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":"gold"},"type":"Article","urls":["http://dx.doi.org/10.1016/j.ailsci.2025.100132"],"publicationDate":"2025-01-01","refereed":"peerReviewed","hostedBy":{"key":"doajarticles::4fb683619d44e078494e582e7351dbb4","value":"Artificial Intelligence in the Life Sciences"},"collectedFrom":{"key":"re3data_____::c4b2081b224be6b3e79d0e5e5556f631","value":"European Union Open Data Portal"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda__h2020::673ee2765cfbdfcba9112920a874fb1e","relatedRecordType":"project","relationProvenance":"sysimport:actionset","trust":"0.91"},"collectedfrom":[{"dsId":"openaire____::a55eb91348674d853191f4f4fd73d078","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon 2020"}],"projectTitle":"Advanced machine learning for Innovative Drug Discovery","code":"956832","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::H2020","description":"Horizon 2020 Framework Programme","name":"H2020"},"level1":{"id":"ec__________::EC::H2020::MSCA-ITN-EID","description":"European Industrial Doctorates","name":"MSCA-ITN-EID"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2021-01-01","endDate":"2025-03-31"}],"otherTitles":null,"inDiamondJournal":true,"green":true,"isGreen":true,"isInDiamondJournal":true}