{"id":"https://openalex.org/W7224435772","doi":"https://doi.org/10.1186/s13321-026-01316-0","title":"PCAM: proteochemometric assay-aware modeling for robust bioactivity estimation and uncertainty quantification","display_name":"PCAM: proteochemometric assay-aware modeling for robust bioactivity estimation and uncertainty quantification","publication_year":2026,"publication_date":"2026-10-25","ids":{"openalex":"https://openalex.org/W7224435772","doi":"https://doi.org/10.1186/s13321-026-01316-0"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01316-0","doi":"https://doi.org/10.1186/s13321-026-01316-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01316-0","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13321-026-01316-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160096463","display_name":"Bola Khalil","orcid":"https://orcid.org/0000-0002-9137-992X","observed_orcids":["https://orcid.org/0000-0002-9137-992X"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Bola Khalil","raw_affiliation_strings":["Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","In Silico Discovery (ISD), Janssen Research and Development, LLC, a Johnson & Johnson company, Beerse, 2340, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-9137-992X","affiliations":[{"raw_affiliation_string":"Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]},{"raw_affiliation_string":"In Silico Discovery (ISD), Janssen Research and Development, LLC, a Johnson & Johnson company, Beerse, 2340, Belgium","institution_ids":["https://openalex.org/I137982388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090495544","display_name":"David Alencar Araripe","orcid":"https://orcid.org/0000-0002-5104-1959","observed_orcids":["https://orcid.org/0000-0002-5104-1959"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David Alencar Araripe","raw_affiliation_strings":["Department of Human Genetics, Leiden University Medical Centre (LUMC), Leiden, 2300 RC, The Netherlands","Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5104-1959","affiliations":[{"raw_affiliation_string":"Department of Human Genetics, Leiden University Medical Centre (LUMC), Leiden, 2300 RC, The Netherlands","institution_ids":["https://openalex.org/I2800006345"]},{"raw_affiliation_string":"Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001242977","display_name":"Linde Schoenmaker","orcid":"https://orcid.org/0000-0001-9879-1004","observed_orcids":["https://orcid.org/0000-0001-9879-1004"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Linde Schoenmaker","raw_affiliation_strings":["Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-9879-1004","affiliations":[{"raw_affiliation_string":"Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030110742","display_name":"Natalia Dyubankova","orcid":"https://orcid.org/0000-0002-5892-3778","observed_orcids":["https://orcid.org/0000-0002-5892-3778"]},"institutions":[{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Natalia Dyubankova","raw_affiliation_strings":["In Silico Discovery (ISD), Janssen Research and Development, LLC, a Johnson & Johnson company, Beerse, 2340, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-5892-3778","affiliations":[{"raw_affiliation_string":"In Silico Discovery (ISD), Janssen Research and Development, LLC, a Johnson & Johnson company, Beerse, 2340, Belgium","institution_ids":["https://openalex.org/I137982388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015253529","display_name":"Herman van Vlijmen","orcid":"https://orcid.org/0000-0002-1915-3141","observed_orcids":["https://orcid.org/0000-0002-1915-3141"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I137982388","display_name":"Janssen (Belgium)","ror":"https://ror.org/04yzcpd71","country_code":"BE","type":"company","lineage":["https://openalex.org/I1330063522","https://openalex.org/I137982388"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Herman van Vlijmen","raw_affiliation_strings":["Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","In Silico Discovery (ISD), Janssen Research and Development, LLC, a Johnson & Johnson company, Beerse, 2340, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-1915-3141","affiliations":[{"raw_affiliation_string":"Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]},{"raw_affiliation_string":"In Silico Discovery (ISD), Janssen Research and Development, LLC, a Johnson & Johnson company, Beerse, 2340, Belgium","institution_ids":["https://openalex.org/I137982388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088996741","display_name":"Gerard J. P. van Westen","orcid":"https://orcid.org/0000-0003-0717-1817","observed_orcids":["https://orcid.org/0000-0003-0717-1817"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Gerard J. P. van Westen","raw_affiliation_strings":["Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0717-1817","affiliations":[{"raw_affiliation_string":"Division of Medicinal Chemistry, Leiden Academic Centre for Drug Research, Leiden University, Einsteinweg 55, 2300 RA, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088996741"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":{"value":2390,"currency":"USD","value_usd":2390},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85321801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12534","display_name":"Protein Degradation and Inhibitors","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/proteochemometrics","display_name":"proteochemometrics","score":0.9919999837875366},{"id":"https://openalex.org/keywords/bioactivity-prediction","display_name":"bioactivity prediction","score":0.8539999723434448},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9739999771118164},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.6660000085830688},{"id":"https://openalex.org/keywords/g-protein-coupled-receptors","display_name":"G protein-coupled receptors","score":0.8309999704360962},{"id":"https://openalex.org/keywords/chembl","display_name":"ChEMBL","score":0.6819999814033508},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.5770000219345093},{"id":"https://openalex.org/keywords/biobert","display_name":"BioBERT","score":0.718999981880188},{"id":"https://openalex.org/keywords/probabilistic-neural-network","display_name":"probabilistic neural network","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121000289916992},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6711999773979187},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.6341000199317932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.557699978351593},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45910000801086426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120999872684479},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39089998602867126},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13321-026-01316-0","doi":"https://doi.org/10.1186/s13321-026-01316-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01316-0","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01316-0","doi":"https://doi.org/10.1186/s13321-026-01316-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01316-0","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.428600013256073}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338438","display_name":"HORIZON EUROPE Marie Sklodowska-Curie Actions","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411804077","https://openalex.org/W1590033661","https://openalex.org/W4213281141","https://openalex.org/W4413942118","https://openalex.org/W2186889113","https://openalex.org/W2268071782","https://openalex.org/W7100177657","https://openalex.org/W2129434099","https://openalex.org/W2144377773","https://openalex.org/W1725133249"],"abstract_inverted_index":{"Public":[0],"bioactivity":[1],"databases":[2],"aggregate":[3],"measurements":[4,183],"from":[5,77,197],"heterogeneous":[6,212],"experimental":[7],"assays,":[8,59],"introducing":[9],"systematic":[10],"variability":[11],"that":[12,31,63,250],"can":[13,193,204],"degrade":[14],"model":[15,218],"performance":[16],"and":[17,37,57,92,95,100,126,138,255,269],"distort":[18],"uncertainty":[19],"estimates.":[20],"We":[21,80,243,262],"present":[22],"proteochemometric":[23],"assay-aware":[24,246],"modeling":[25],"(PCAM),":[26],"an":[27,245],"extension":[28,247],"of":[29,86,248],"proteochemometrics":[30,249],"integrates":[32],"assay":[33,42,65,72,78,120,129,145,152,191,202,253,266,272,279],"descriptors":[34,130],"alongside":[35],"compound":[36],"protein":[38],"features":[39],"to":[40,67,142,168,219,277],"capture":[41],"context.":[43,146],"Using":[44],"a":[45,159,185],"curated":[46],"ChEMBL-derived":[47],"benchmark":[48],"spanning":[49],"167":[50],"G":[51],"protein-coupled":[52],"receptor":[53],"targets,":[54],"77,081":[55],"compounds,":[56],"5,161":[58],"we":[60,225],"compare":[61],"models":[62,68,143,252],"omit":[64],"information":[66],"using":[69,236],"either":[70],"categorical":[71,128],"identifiers":[73,121,267],"or":[74,175,180],"text-derived":[75,156,271],"embeddings":[76,157,238],"descriptions.":[79],"evaluate":[81,256],"generalization":[82],"under":[83,239,258],"three":[84],"regimes":[85],"increasing":[87,259],"distribution":[88,117,260],"shift":[89],"(random,":[90],"scaffold-based,":[91],"assay-held-out":[93,112,148],"splits)":[94],"assess":[96],"both":[97],"point":[98],"accuracy":[99,137],"probabilistic":[101,139,233],"quality.":[102],"Overall":[103],"difficulty":[104],"is":[105],"dominated":[106],"by":[107,215],"the":[108,115,132,217,240],"split":[109],"strategy,":[110],"with":[111],"evaluation":[113],"inducing":[114],"strongest":[116],"shift.":[118,261],"When":[119],"are":[122],"shared":[123],"between":[124,151],"training":[125],"evaluation,":[127,149],"provide":[131],"most":[133],"consistent":[134,160],"gains":[135],"in":[136,211],"scoring":[140],"relative":[141],"without":[144],"Under":[147],"differences":[150],"representations":[153,203,273],"contract,":[154],"while":[155,281],"show":[158],"but":[161],"typically":[162],"small":[163],"advantage.":[164],"This":[165],"regime":[166],"corresponds":[167],"practical":[169],"assay-transfer":[170],"scenarios,":[171],"such":[172],"as":[173],"protocol":[174],"vendor":[176],"changes,":[177],"new":[178],"readouts,":[179],"sparse":[181],"early":[182],"for":[184,229],"newly":[186],"introduced":[187],"assay,":[188],"where":[189],"leveraging":[190],"text/metadata":[192],"help":[194],"transfer":[195,276],"signal":[196],"related":[198],"assays.":[199],"In":[200],"addition,":[201],"reduce":[205],"reliance":[206],"on":[207],"brittle":[208],"cross-assay":[209],"normalization":[210],"public":[213],"datasets":[214],"allowing":[216],"learn":[220],"assay-dependent":[221],"shifts":[222],"directly;":[223],"however,":[224],"observed":[226],"optimization":[227],"instability":[228],"one":[230],"configuration":[231],"(a":[232],"neural":[234],"network":[235],"BioBERT":[237],"random":[241],"split).":[242],"introduce":[244],"explicitly":[251],"context":[254],"it":[257],"clarify":[263],"when":[264,270],"simple":[265],"suffice":[268],"better":[274],"support":[275],"unseen":[278],"protocols":[280],"maintaining":[282],"uncertainty-aware":[283],"evaluation.":[284]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}