{"id":"https://openalex.org/W4406619380","doi":"https://doi.org/10.1186/s13321-025-00956-y","title":"Matched pairs demonstrate robustness against inter-assay variability","display_name":"Matched pairs demonstrate robustness against inter-assay variability","publication_year":2025,"publication_date":"2025-01-20","ids":{"openalex":"https://openalex.org/W4406619380","doi":"https://doi.org/10.1186/s13321-025-00956-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/39833966"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-00956-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-00956-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-00956-y","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,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-00956-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003651044","display_name":"Jochem Nelen","orcid":"https://orcid.org/0000-0002-9970-4950"},"institutions":[{"id":"https://openalex.org/I68763199","display_name":"Universidad Cat\u00f3lica de Murcia","ror":"https://ror.org/05b1rsv17","country_code":"ES","type":"education","lineage":["https://openalex.org/I68763199"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jochem Nelen","raw_affiliation_strings":["Health Sciences PhD Program, Universidad Cat\u00f3lica de Murcia UCAM, 30107, Murcia, Spain","Structural Bioinformatics and High Performance Computing Research Group (BIO-HPC), HiTech Innovation Hub, UCAM Universidad Cat\u00f3lica de Murcia, 30107, Murcia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Sciences PhD Program, Universidad Cat\u00f3lica de Murcia UCAM, 30107, Murcia, Spain","institution_ids":["https://openalex.org/I68763199"]},{"raw_affiliation_string":"Structural Bioinformatics and High Performance Computing Research Group (BIO-HPC), HiTech Innovation Hub, UCAM Universidad Cat\u00f3lica de Murcia, 30107, Murcia, Spain","institution_ids":["https://openalex.org/I68763199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037673215","display_name":"Horacio P\u00e9rez\u2010S\u00e1nchez","orcid":"https://orcid.org/0000-0003-4468-7898"},"institutions":[{"id":"https://openalex.org/I68763199","display_name":"Universidad Cat\u00f3lica de Murcia","ror":"https://ror.org/05b1rsv17","country_code":"ES","type":"education","lineage":["https://openalex.org/I68763199"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Horacio P\u00e9rez-S\u00e1nchez","raw_affiliation_strings":["Structural Bioinformatics and High Performance Computing Research Group (BIO-HPC), HiTech Innovation Hub, UCAM Universidad Cat\u00f3lica de Murcia, 30107, Murcia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Structural Bioinformatics and High Performance Computing Research Group (BIO-HPC), HiTech Innovation Hub, UCAM Universidad Cat\u00f3lica de Murcia, 30107, Murcia, Spain","institution_ids":["https://openalex.org/I68763199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048522237","display_name":"Hans De Winter","orcid":"https://orcid.org/0000-0002-4450-7677"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Hans De Winter","raw_affiliation_strings":["Department of Pharmaceutical Sciences, Faculty of Pharmaceutical, Biomedical and Veterinary Sciences, University of Antwerp, Universiteitsplein 1A, 2610, Wilrijk, Belgium. hans.dewinter@uantwerpen.be","Department of Pharmaceutical Sciences, Faculty of Pharmaceutical, Biomedical and Veterinary Sciences, University of Antwerp, Universiteitsplein 1A, 2610, Wilrijk, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Sciences, Faculty of Pharmaceutical, Biomedical and Veterinary Sciences, University of Antwerp, Universiteitsplein 1A, 2610, Wilrijk, Belgium. hans.dewinter@uantwerpen.be","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"Department of Pharmaceutical Sciences, Faculty of Pharmaceutical, Biomedical and Veterinary Sciences, University of Antwerp, Universiteitsplein 1A, 2610, Wilrijk, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056917728","display_name":"Dries Van Rompaey","orcid":"https://orcid.org/0000-0003-0823-8235"},"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":"Dries Van Rompaey","raw_affiliation_strings":["Drug Discovery Data Sciences, Janssen Pharmaceutica NV, Turnhoutseweg 30, 2340, Beerse, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drug Discovery Data Sciences, Janssen Pharmaceutica NV, Turnhoutseweg 30, 2340, Beerse, Belgium","institution_ids":["https://openalex.org/I137982388"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048522237"],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":1.4953,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81671517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"8","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.8531492948532104},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7838053703308105},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.7375124096870422},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6365354061126709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6283419132232666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.506925642490387},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45167604088783264},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3685031235218048},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.363716185092926},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.35162103176116943},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.33337563276290894},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2338601052761078},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19792577624320984},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.08861497044563293}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.8531492948532104},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7838053703308105},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.7375124096870422},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6365354061126709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283419132232666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.506925642490387},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45167604088783264},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3685031235218048},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.363716185092926},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.35162103176116943},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.33337563276290894},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2338601052761078},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19792577624320984},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.08861497044563293},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-00956-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-00956-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-00956-y","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,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:39833966","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39833966","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11748845","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11748845","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11748845/pdf/13321_2025_Article_956.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:aafb622c6d904906a388da1a4337bd31","is_oa":true,"landing_page_url":"https://doaj.org/article/aafb622c6d904906a388da1a4337bd31","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 17, Iss 1, Pp 1-8 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-00956-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-00956-y","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-00956-y","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,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406619380.pdf","grobid_xml":"https://content.openalex.org/works/W4406619380.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1987275960","https://openalex.org/W2014813466","https://openalex.org/W2096725584","https://openalex.org/W2330838234","https://openalex.org/W2332135472","https://openalex.org/W2900090807","https://openalex.org/W4387966128","https://openalex.org/W4392093325","https://openalex.org/W4399242117"],"related_works":["https://openalex.org/W2800402488","https://openalex.org/W2155478691","https://openalex.org/W3005441379","https://openalex.org/W1552948952","https://openalex.org/W4388455891","https://openalex.org/W959778778","https://openalex.org/W4310102410","https://openalex.org/W2082577974","https://openalex.org/W4385760073","https://openalex.org/W4321254242"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"models":[2],"for":[3,126,166,181],"chemistry":[4],"require":[5],"large":[6],"datasets,":[7],"often":[8,41],"compiled":[9],"by":[10,51],"combining":[11,17],"data":[12,18,173,182],"from":[13,29,152,174],"multiple":[14],"assays.":[15],"However,":[16],"without":[19],"careful":[20],"curation":[21,68,99],"can":[22],"introduce":[23],"significant":[24],"noise.":[25],"While":[26],"absolute":[27],"values":[28,132],"different":[30],"assays":[31,60],"are":[32,40],"rarely":[33],"comparable,":[34],"trends":[35],"or":[36],"differences":[37,54,76,90,146],"between":[38,55,77],"compounds":[39],"assumed":[42],"to":[43,123,136,154,156],"be":[44,124],"consistent.":[45],"This":[46],"study":[47],"evaluates":[48],"that":[49,74],"assumption":[50],"analyzing":[52],"potency":[53,75],"matched":[56,78,170],"compound":[57,85,114],"pairs":[58,79,144],"across":[59],"and":[61,129],"assessing":[62],"the":[63,106,141,175],"impact":[64],"of":[65,108,143],"assay":[66,89],"metadata":[67],"on":[69],"error":[70],"reduction.":[71],"We":[72],"find":[73],"exhibit":[80],"less":[81],"variability":[82],"than":[83],"individual":[84],"measurements,":[86],"suggesting":[87],"systematic":[88],"may":[91],"partially":[92],"cancel":[93],"out":[94],"in":[95,169],"paired":[96],"data.":[97],"Metadata":[98],"further":[100],"improves":[101],"inter-assay":[102],"agreement,":[103],"albeit":[104],"at":[105],"cost":[107],"dataset":[109],"size.":[110],"For":[111],"minimally":[112],"curated":[113],"pairs,":[115],"agreement":[116],"within":[117],"0.3":[118],"pChEMBL":[119,149],"units":[120],"was":[121],"found":[122],"44\u201346%":[125],"K":[127],"i":[128],"IC":[130],"50":[131],"respectively,":[133],"which":[134],"improved":[135],"66\u201379%":[137],"after":[138],"curation.":[139,160],"Similarly,":[140],"percentage":[142],"with":[145,158],"exceeding":[147],"1":[148],"unit":[150],"dropped":[151],"12":[153],"15%":[155],"6\u20138%":[157],"extensive":[159],"These":[161],"results":[162],"establish":[163],"a":[164],"benchmark":[165],"expected":[167],"noise":[168],"molecular":[171],"pair":[172],"ChEMBL":[176],"database,":[177],"offering":[178],"practical":[179],"metrics":[180],"quality":[183],"assessment.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
