{"id":"https://openalex.org/W4394812769","doi":"https://doi.org/10.1186/s13321-024-00837-w","title":"Mind your prevalence!","display_name":"Mind your prevalence!","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4394812769","doi":"https://doi.org/10.1186/s13321-024-00837-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/38622648"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00837-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00837-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00837-w","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","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"},"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/s13321-024-00837-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086797588","display_name":"S\u00e9bastien Guesn\u00e9","orcid":"https://orcid.org/0009-0007-5127-7842"},"institutions":[{"id":"https://openalex.org/I4210128146","display_name":"Canary Wharf Group (United Kingdom)","ror":"https://ror.org/02hx87760","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210128146"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"S\u00e9bastien J. J. Guesn\u00e9","raw_affiliation_strings":["Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK. sebastien.guesne@lhasalimited.org","Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK. sebastien.guesne@lhasalimited.org","institution_ids":["https://openalex.org/I4210128146"]},{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082247372","display_name":"Thierry Hanser","orcid":"https://orcid.org/0000-0002-0392-6154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thierry Hanser","raw_affiliation_strings":["Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041238648","display_name":"St\u00e9phane Werner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"St\u00e9phane Werner","raw_affiliation_strings":["Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021382480","display_name":"Samuel Boobier","orcid":"https://orcid.org/0000-0002-3166-2782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Boobier","raw_affiliation_strings":["Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113178118","display_name":"Shaylyn Scott","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaylyn Scott","raw_affiliation_strings":["Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5086797588"],"corresponding_institution_ids":["https://openalex.org/I4210128146"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":5.4762,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96446531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"43","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9865000247955322,"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":0.9865000247955322,"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/T13283","display_name":"Mental Health Research Topics","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6806622743606567},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.6490756869316101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6390070915222168},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5724174976348877},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5681099891662598},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.5658699870109558},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5336922407150269},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5177423357963562},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.495430588722229},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47705569863319397},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.47062376141548157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4692528247833252},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.46724843978881836},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.45267605781555176},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4356532096862793},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.4116627871990204},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30353015661239624},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11470308899879456},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09139862656593323}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6806622743606567},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6490756869316101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6390070915222168},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5724174976348877},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5681099891662598},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.5658699870109558},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5336922407150269},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5177423357963562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.495430588722229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47705569863319397},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.47062376141548157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4692528247833252},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.46724843978881836},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.45267605781555176},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4356532096862793},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.4116627871990204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30353015661239624},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11470308899879456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09139862656593323},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00837-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00837-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00837-w","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","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"},{"id":"pmid:38622648","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38622648","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:11017531","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11017531","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11017531/pdf/13321_2024_Article_837.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:d0673062d6b34d8ba9dfa37669f04284","is_oa":true,"landing_page_url":"https://doaj.org/article/d0673062d6b34d8ba9dfa37669f04284","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 16, Iss 1, Pp 1-13 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00837-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00837-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00837-w","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","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394812769.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W166169566","https://openalex.org/W2046596584","https://openalex.org/W2068258779","https://openalex.org/W2077676861","https://openalex.org/W2152575748","https://openalex.org/W2220892016","https://openalex.org/W2896686089","https://openalex.org/W2918408501","https://openalex.org/W2971616138","https://openalex.org/W2978750824","https://openalex.org/W3037824585","https://openalex.org/W3101083045","https://openalex.org/W4292721946"],"related_works":["https://openalex.org/W3124102327","https://openalex.org/W2100523380","https://openalex.org/W4236800443","https://openalex.org/W2141738404","https://openalex.org/W3121296535","https://openalex.org/W1907816360","https://openalex.org/W2019678805","https://openalex.org/W2134888474","https://openalex.org/W2080355854","https://openalex.org/W2388825802"],"abstract_inverted_index":{"Multiple":[0],"metrics":[1,172,219,287,389,408],"are":[2],"used":[3,58,69,416],"when":[4],"assessing":[5],"and":[6,162,206,208,279,316,367,395,413],"validating":[7],"the":[8,17,29,45,49,53,72,79,97,100,107,114,118,123,131,178,187,193,214,231,260,267,271,283,311,326,383,404],"performance":[9,31,90,218,232,277,302,417],"of":[10,19,32,48,74,99,117,125,170,180,216,244,252,285,310,314,321,328,331,392,406],"quantitative":[11],"structure-activity":[12],"relationship":[13],"(QSAR)":[14],"models.":[15,34],"In":[16,35,376],"case":[18],"binary":[20],"classification,":[21],"balanced":[22,39,66,108,171,174,228,247,253,298,301,332,361,365,407],"accuracy":[23,40,67,175,229,234,254],"is":[24,57,68,92,128,230],"a":[25,61,202,237,241,308,319,348],"metric":[26,233,278,303,362],"to":[27,37,59,70,95,106,149,165,177,236,259,274,282,378,387,409],"assess":[28],"global":[30,89],"such":[33],"contrast":[36,105,377],"accuracy,":[38,109,299,366],"does":[41],"not":[42,183],"depend":[43],"on":[44,78,113,130,266],"respective":[46,115],"prevalence":[47,116,243,354,396,423],"two":[50,322],"categories":[51],"in":[52,104,186,356],"test":[54,76,101,156,238,248],"set":[55,239],"that":[56,227],"validate":[60],"QSAR":[62],"classifier.":[63],"As":[64],"such,":[65],"overcome":[71],"effect":[73],"imbalanced":[75],"sets":[77,157],"model's":[80],"perceived":[81],"accuracy.":[82],"Matthews'":[83,410],"correlation":[84,411],"coefficient":[85,412],"(MCC),":[86],"an":[87],"alternative":[88],"metric,":[91],"also":[93],"known":[94],"mitigate":[96],"imbalance":[98],"set.":[102],"However,":[103],"MCC":[110,135,261,333,335],"remains":[111],"dependent":[112],"predicted":[119],"categories.":[120],"For":[121],"simplicity,":[122],"rest":[124],"this":[126,196,329],"work":[127,346],"based":[129],"positive":[132,145,160,242,268],"prevalence.":[133,146,222,269],"The":[134,168,401],"value":[136],"may":[137,163,304],"be":[138,257,290,305],"underestimated":[139],"at":[140],"high":[141],"or":[142],"extremely":[143],"low":[144],"It":[147],"contributes":[148],"more":[150],"challenging":[151],"comparisons":[152,421],"between":[153],"experiments":[154],"using":[155,340],"with":[158,211,240,336],"different":[159],"prevalences":[161],"lead":[164],"incorrect":[166],"interpretations.":[167],"concept":[169,251,273,284,330,405],"beyond":[173,364],"is,":[176],"best":[179],"our":[181],"knowledge,":[182],"yet":[184],"described":[185],"cheminformatic":[188],"literature.":[189],"Therefore,":[190],"after":[191,262],"describing":[192],"relevant":[194],"literature,":[195,380],"manuscript":[197,402],"will":[198,225,255,288,294,324],"first":[199],"formally":[200],"define":[201],"confusion":[203,385],"matrix,":[204],"sensitivity":[205,315],"specificity":[207,394],"then":[209,256,289],"present,":[210],"synthetic":[212,341],"data,":[213],"danger":[215],"comparing":[217],"under":[220,422],"nonconstant":[221],"Second,":[223],"it":[224,281,381],"demonstrate":[226],"calibrated":[235,286],"50%":[245],"(i.e.,":[246],"set).":[249],"This":[250,345],"extended":[258],"showing":[263],"its":[264],"dependency":[265],"Applying":[270],"same":[272],"any":[275,300],"other":[276,414],"widening":[280],"briefly":[291],"discussed.":[292],"We":[293],"show":[295],"that,":[296],"like":[297],"expressed":[306],"as":[307,390],"function":[309],"well-known":[312],"values":[313],"specificity.":[317],"Finally,":[318],"tale":[320],"MCCs":[323],"exemplify":[325],"use":[327,338,374],"versus":[334],"four":[337],"cases":[339],"data.":[342],"SCIENTIFIC":[343],"CONTRIBUTION:":[344],"provides":[347],"formal,":[349],"unified":[350],"framework":[351],"for":[352,372],"understanding":[353],"dependence":[355],"model":[357],"validation":[358],"metrics,":[359],"deriving":[360],"expressions":[363],"demonstrating":[368],"their":[369],"practical":[370],"utility":[371],"common":[373],"cases.":[375],"prior":[379],"introduces":[382],"derived":[384],"matrix":[386],"express":[388],"functions":[391],"sensitivity,":[393],"without":[397],"needing":[398],"additional":[399],"coefficients.":[400],"extends":[403],"widely":[415],"indicators,":[418],"enabling":[419],"robust":[420],"shifts.":[424]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}