{"id":"https://openalex.org/W4399406078","doi":"https://doi.org/10.1145/3807503.3819476","title":"Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching","display_name":"Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W4399406078","doi":"https://doi.org/10.1145/3807503.3819476"},"language":"en","primary_location":{"id":"doi:10.1145/3807503.3819476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819476","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3819476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113242286","display_name":"Yunni Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunni Qu","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0003-7408-7436","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bhargav Vaduri","orcid":"https://orcid.org/0009-0006-6232-8206"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhargav Vaduri","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0006-6232-8206","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Karthikeya Jatoth","orcid":"https://orcid.org/0009-0003-2179-0136"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthikeya Jatoth","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0003-2179-0136","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"James Wellnitz","orcid":"https://orcid.org/0000-0002-9181-3431"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Wellnitz","raw_affiliation_strings":["Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0000-0002-9181-3431","affiliations":[{"raw_affiliation_string":"Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dzung Dinh","orcid":"https://orcid.org/0009-0004-5143-8173"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dzung Dinh","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0004-5143-8173","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Seth Veenbaas","orcid":"https://orcid.org/0009-0003-5786-0407"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seth Veenbaas","raw_affiliation_strings":["Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0003-5786-0407","affiliations":[{"raw_affiliation_string":"Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jonathan Chapman","orcid":"https://orcid.org/0009-0009-6573-8835"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Chapman","raw_affiliation_strings":["Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0009-6573-8835","affiliations":[{"raw_affiliation_string":"Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078536199","display_name":"Alexander Tropsha","orcid":"https://orcid.org/0000-0003-3802-8896"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Tropsha","raw_affiliation_strings":["Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0000-0003-3802-8896","affiliations":[{"raw_affiliation_string":"Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050408389","display_name":"Junier B. Oliva","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junier Oliva","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"],"raw_orcid":"https://orcid.org/0000-0002-2601-5652","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00159604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9514999985694885,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9514999985694885,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.9455999732017517,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11489","display_name":"Air Traffic Management and Optimization","score":0.9348999857902527,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/expansive","display_name":"Expansive","score":0.9234934449195862},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7550606727600098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4712895452976227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27812737226486206},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18570393323898315},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11742475628852844}],"concepts":[{"id":"https://openalex.org/C2780502288","wikidata":"https://www.wikidata.org/wiki/Q28838156","display_name":"Expansive","level":3,"score":0.9234934449195862},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7550606727600098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4712895452976227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27812737226486206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18570393323898315},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11742475628852844},{"id":"https://openalex.org/C30407753","wikidata":"https://www.wikidata.org/wiki/Q186191","display_name":"Compressive strength","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3807503.3819476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819476","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.01825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01825","pdf_url":"https://arxiv.org/pdf/2406.01825","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.01825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.01825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3807503.3819476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819476","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2223411813","display_name":null,"funder_award_id":"IIS-2133595","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3092085164","display_name":null,"funder_award_id":"1R01AA026879","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4387722320","display_name":null,"funder_award_id":"DMS-2324394","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7448232870","display_name":null,"funder_award_id":"1OT2OD032581-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7607605106","display_name":null,"funder_award_id":"R01GM140154","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3207631643","https://openalex.org/W4300921257","https://openalex.org/W4298284054","https://openalex.org/W2271765275","https://openalex.org/W2964116984","https://openalex.org/W2910590812","https://openalex.org/W1571623370","https://openalex.org/W4302368440"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"models":[3,47,87],"are":[4],"increasingly":[5],"deployed":[6],"for":[7,99,170],"virtual":[8,171],"screening":[9,135,172],"in":[10,37,164],"drug":[11],"discovery,":[12],"where":[13,173],"the":[14,32,42,59,68,130],"goal":[15],"is":[16,168],"to":[17,125,149,151,178],"identify":[18],"novel,":[19],"chemically":[20],"diverse":[21],"scaffolds":[22,70],"while":[23,155],"minimizing":[24],"experimental":[25,75,179],"costs.":[26],"This":[27],"creates":[28],"a":[29,80,103,117,138,142],"fundamental":[30],"challenge:":[31],"most":[33,71],"valuable":[34],"discoveries":[35],"lie":[36],"out-of-distribution":[38],"(OOD)":[39],"regions":[40],"beyond":[41],"training":[43,60,120],"data,":[44],"yet":[45],"ML":[46],"often":[48],"degrade":[49],"under":[50],"distribution":[51],"shift.":[52],"Standard":[53],"novelty-rejection":[54],"strategies":[55],"ensure":[56],"reliability":[57],"within":[58],"domain":[61],"but":[62],"limit":[63],"discovery":[64],"by":[65],"rejecting":[66],"precisely":[67],"novel":[69,143],"worth":[72],"finding.":[73],"Moreover,":[74],"budgets":[76],"permit":[77],"testing":[78],"only":[79,116,174],"small":[81],"fraction":[82],"of":[83,133],"nominated":[84],"candidates,":[85],"demanding":[86],"that":[88,105],"produce":[89],"reliable":[90,157],"confidence":[91,158],"estimates.":[92],"We":[93,181],"introduce":[94],"EXPLOR":[95,147],"(Extrapolatory":[96],"Pseudo-Label":[97],"Matching":[98],"OOD":[100,152],"Uncertainty-Based":[101],"Rejection),":[102],"framework":[104],"addresses":[106],"both":[107],"challenges":[108],"through":[109],"extrapolatory":[110],"pseudo-labeling":[111],"on":[112],"latent-space":[113],"augmentations,":[114],"requiring":[115],"single":[118],"labeled":[119],"set":[121],"and":[122,187],"no":[123],"access":[124],"unlabeled":[126],"test":[127],"compounds,":[128],"mirroring":[129],"realistic":[131],"conditions":[132],"prospective":[134],"campaigns.":[136],"Through":[137],"multi-headed":[139],"architecture":[140],"with":[141,160],"per-head":[144],"matching":[145],"loss,":[146],"learns":[148],"extrapolate":[150],"chemical":[153,186],"space":[154],"producing":[156],"estimates,":[159],"particularly":[161],"strong":[162],"performance":[163,184],"high-confidence":[165],"regions,":[166],"which":[167],"critical":[169],"top-ranked":[175],"candidates":[176],"advance":[177],"validation.":[180],"demonstrate":[182],"state-of-the-art":[183],"across":[185],"tabular":[188],"benchmarks":[189],"using":[190],"different":[191],"molecular":[192],"embeddings.":[193]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2024-06-08T00:00:00"}
