{"id":"https://openalex.org/W3082916415","doi":"https://doi.org/10.1021/acs.jcim.0c00476","title":"Comparison of Scaling Methods to Obtain Calibrated Probabilities of Activity for Protein\u2013Ligand Predictions","display_name":"Comparison of Scaling Methods to Obtain Calibrated Probabilities of Activity for Protein\u2013Ligand Predictions","publication_year":2020,"publication_date":"2020-08-31","ids":{"openalex":"https://openalex.org/W3082916415","doi":"https://doi.org/10.1021/acs.jcim.0c00476","mag":"3082916415","pmid":"https://pubmed.ncbi.nlm.nih.gov/32865408"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c00476","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00476","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088554828","display_name":"Lewis Mervin","orcid":"https://orcid.org/0000-0002-7271-0824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lewis H. Mervin","raw_affiliation_strings":["Hit Discovery, Discovery Sciences, R&D, AstraZeneca, Cambridge CB2 0AA, U.K"],"affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, R&D, AstraZeneca, Cambridge CB2 0AA, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065422795","display_name":"Avid M. Afzal","orcid":"https://orcid.org/0000-0002-6186-6954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avid M. Afzal","raw_affiliation_strings":["Data Sciences & Quantitative Biology, Discovery Sciences, R&D, AstraZeneca, Cambridge CB2 0AA, U.K"],"affiliations":[{"raw_affiliation_string":"Data Sciences & Quantitative Biology, Discovery Sciences, R&D, AstraZeneca, Cambridge CB2 0AA, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076975589","display_name":"Ola Engkvist","orcid":"https://orcid.org/0000-0003-4970-6461"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ola Engkvist","raw_affiliation_strings":["Hit Discovery, Discovery Sciences, R&D, AstraZeneca, M\u00f6lndal SE-431 83, Sweden"],"affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, R&D, AstraZeneca, M\u00f6lndal SE-431 83, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026643759","display_name":"Andreas Bender","orcid":"https://orcid.org/0000-0002-6683-7546"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andreas Bender","raw_affiliation_strings":["Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Cambridge CB2 1TN, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Molecular Informatics, Department of Chemistry, University of Cambridge, Cambridge CB2 1TN, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026643759"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7323,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88228999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"60","issue":"10","first_page":"4546","last_page":"4559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9911999702453613,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9864000082015991,"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/brier-score","display_name":"Brier score","score":0.9091193675994873},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6488295197486877},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5907889008522034},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5295194983482361},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5203404426574707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45852839946746826},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.45101621747016907},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.4318787753582001},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.43067365884780884},{"id":"https://openalex.org/keywords/coverage-probability","display_name":"Coverage probability","score":0.41379380226135254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4127654433250427},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.397245854139328},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.385356605052948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3851199150085449},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.31537532806396484},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.14683735370635986}],"concepts":[{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.9091193675994873},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6488295197486877},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5907889008522034},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5295194983482361},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5203404426574707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45852839946746826},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.45101621747016907},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4318787753582001},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.43067365884780884},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.41379380226135254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4127654433250427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.397245854139328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.385356605052948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3851199150085449},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.31537532806396484},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.14683735370635986},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.0c00476","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00476","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:32865408","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32865408","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G321352993","display_name":"Improved In Silico Methods for Target Deconvolution in Phenotypic Screenings","funder_award_id":"BB/K011804/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G8130841648","display_name":null,"funder_award_id":"RG75821","funder_id":"https://openalex.org/F4320307770","funder_display_name":"AstraZeneca"}],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W2360098","https://openalex.org/W108037669","https://openalex.org/W349770100","https://openalex.org/W1487831638","https://openalex.org/W1502611875","https://openalex.org/W1601495365","https://openalex.org/W1618905105","https://openalex.org/W1821464114","https://openalex.org/W1869829652","https://openalex.org/W1971606559","https://openalex.org/W1973026729","https://openalex.org/W1975875968","https://openalex.org/W1983393839","https://openalex.org/W1994249991","https://openalex.org/W2009842403","https://openalex.org/W2011006316","https://openalex.org/W2012942264","https://openalex.org/W2016511206","https://openalex.org/W2040369353","https://openalex.org/W2044834685","https://openalex.org/W2046842230","https://openalex.org/W2057549164","https://openalex.org/W2059847559","https://openalex.org/W2060956720","https://openalex.org/W2061789405","https://openalex.org/W2070408245","https://openalex.org/W2076018790","https://openalex.org/W2081123119","https://openalex.org/W2082252201","https://openalex.org/W2092053124","https://openalex.org/W2098824882","https://openalex.org/W2099536767","https://openalex.org/W2101234009","https://openalex.org/W2113846323","https://openalex.org/W2118374803","https://openalex.org/W2118938609","https://openalex.org/W2122629583","https://openalex.org/W2127553917","https://openalex.org/W2134177842","https://openalex.org/W2145784250","https://openalex.org/W2155894387","https://openalex.org/W2166229467","https://openalex.org/W2171830166","https://openalex.org/W2176009755","https://openalex.org/W2189911347","https://openalex.org/W2220358814","https://openalex.org/W2232432533","https://openalex.org/W2267190997","https://openalex.org/W2338757337","https://openalex.org/W2504742770","https://openalex.org/W2513906959","https://openalex.org/W2532619499","https://openalex.org/W2541711215","https://openalex.org/W2541855169","https://openalex.org/W2548695521","https://openalex.org/W2556014018","https://openalex.org/W2559145072","https://openalex.org/W2592742128","https://openalex.org/W2605274794","https://openalex.org/W2605583996","https://openalex.org/W2626967530","https://openalex.org/W2726158680","https://openalex.org/W2729788619","https://openalex.org/W2730075900","https://openalex.org/W2731929837","https://openalex.org/W2740946158","https://openalex.org/W2744167442","https://openalex.org/W2749475934","https://openalex.org/W2773235741","https://openalex.org/W2806547269","https://openalex.org/W2808243645","https://openalex.org/W2886438927","https://openalex.org/W2902800472","https://openalex.org/W2905261310","https://openalex.org/W2911964244","https://openalex.org/W2912842679","https://openalex.org/W2946412700","https://openalex.org/W2949447082","https://openalex.org/W2949983735","https://openalex.org/W2950238754","https://openalex.org/W2972499938","https://openalex.org/W2986234153","https://openalex.org/W2993923158","https://openalex.org/W2996480032","https://openalex.org/W3003729103","https://openalex.org/W3082081167","https://openalex.org/W4230784961","https://openalex.org/W4256669726"],"related_works":["https://openalex.org/W4293426625","https://openalex.org/W1774890144","https://openalex.org/W2728311169","https://openalex.org/W3121128755","https://openalex.org/W2051201630","https://openalex.org/W2082471284","https://openalex.org/W2043644439","https://openalex.org/W2953079191","https://openalex.org/W73929513","https://openalex.org/W2117286806"],"abstract_inverted_index":{"In":[0,34,153],"the":[1,6,39,65,115,131,141,150,155,163,169,190,197,223,259],"context":[2],"of":[3,8,23,41,108,295],"bioactivity":[4,81],"prediction,":[5],"question":[7],"how":[9],"to":[10,25,146,180,188,203,206,212,220,242,258,267,287,301],"calibrate":[11,222],"a":[12,16,21,26,147,178],"score":[13,135,193],"produced":[14],"by":[15],"machine":[17,121],"learning":[18,122],"method":[19,179],"into":[20],"probability":[22,143,165,224,237,303],"binding":[24],"protein":[27],"target":[28,280,296],"is":[29,299,310],"not":[30],"yet":[31],"satisfactorily":[32],"addressed.":[33],"this":[35,290],"study,":[36],"we":[37,284],"compared":[38],"performance":[40,97],"three":[42],"such":[43],"methods,":[44],"namely,":[45],"Platt":[46],"scaling":[47,294],"(PS),":[48],"isotonic":[49],"regression":[50],"(IR),":[51],"and":[52,71,96,105,124,129,149,157,173,235,309],"Venn-ABERS":[53],"predictors":[54],"(VA),":[55],"in":[56,214,289,305],"calibrating":[57],"prediction":[58,63,281,297],"scores":[59],"obtained":[60],"from":[61],"ligand-target":[62],"comprising":[64],"Na\u00efve":[66],"Bayes,":[67],"support":[68],"vector":[69],"machines,":[70],"random":[72],"forest":[73],"(RF)":[74],"algorithms.":[75],"Calibration":[76],"quality":[77],"was":[78,98,186,210,218],"assessed":[79,99],"on":[80],"data":[82,89],"available":[83],"at":[84],"AstraZeneca":[85],"for":[86,168,171,200,226,246,279,314],"40":[87],"million":[88],"points":[90],"(compound-target":[91],"pairs)":[92],"across":[93,119],"2112":[94],"targets":[95],"using":[100],"stratified":[101],"shuffle":[102],"split":[103],"(SSS)":[104],"leave":[106],"20%":[107],"scaffolds":[109],"out":[110],"(L20SO)":[111],"validation.":[112],"VA":[113,217,293],"achieved":[114],"best":[116],"calibration":[117,229],"performances":[118],"all":[120,306],"algorithms":[123],"cross":[125],"validation":[126],"methods":[127,159],"tested":[128],"also":[130],"lowest":[132],"(best)":[133],"Brier":[134,192],"loss":[136,194],"(mean":[137],"squared":[138],"difference":[139],"between":[140],"outputted":[142],"estimates":[144,225,304],"assigned":[145,164],"compound":[148],"actual":[151],"outcome).":[152],"comparison,":[154],"PS":[156],"IR":[158],"can":[160,273],"actually":[161],"degrade":[162],"estimates,":[166],"particularly":[167],"RF":[170],"SSS":[172],"during":[174],"L20SO.":[175],"Sphere":[176],"exclusion,":[177],"sample":[181],"additional":[182],"(putative)":[183],"inactive":[184,201],"compounds,":[185,208],"shown":[187,211,241],"inflate":[189],"overall":[191],"performance,":[195],"through":[196],"artificial":[198],"requirement":[199],"molecules":[202,249],"be":[204,274],"dissimilar":[205,257],"active":[207,260],"but":[209],"result":[213],"overconfident":[215],"estimators.":[216],"able":[219,286,300],"successfully":[221],"even":[227],"small":[228],"sets.":[230],"The":[231],"multiprobability":[232,271],"values":[233],"(lower":[234],"upper":[236],"boundary":[238],"intervals)":[239],"were":[240,264,285],"produce":[243],"large":[244],"discordance":[245,272],"test":[247],"set":[248],"that":[250,270,292],"are":[251],"neither":[252],"very":[253,256],"similar":[254],"nor":[255],"training":[261],"set,":[262],"which":[263],"hence":[265],"difficult":[266],"predict,":[268],"suggesting":[269],"used":[275],"as":[276],"an":[277],"estimate":[278],"uncertainty.":[282],"Overall,":[283],"show":[288],"work":[291],"models":[298],"improve":[302],"testing":[307],"instances":[308],"currently":[311],"being":[312],"applied":[313],"in-house":[315],"approaches.":[316]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}