{"id":"https://openalex.org/W4392093325","doi":"https://doi.org/10.1021/acs.jcim.4c00049","title":"Combining IC <sub>50</sub> or <i>K</i> <sub> <i>i</i> </sub> Values from Different Sources Is a Source of Significant Noise","display_name":"Combining IC <sub>50</sub> or <i>K</i> <sub> <i>i</i> </sub> Values from Different Sources Is a Source of Significant Noise","publication_year":2024,"publication_date":"2024-02-23","ids":{"openalex":"https://openalex.org/W4392093325","doi":"https://doi.org/10.1021/acs.jcim.4c00049","pmid":"https://pubmed.ncbi.nlm.nih.gov/38394344"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00049","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00049","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00049","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00049","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056808182","display_name":"Gregory A. Landrum","orcid":"https://orcid.org/0000-0001-6279-4481"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Gregory A. Landrum","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, 8093 Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-6279-4481","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, 8093 Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019754904","display_name":"Sereina Riniker","orcid":"https://orcid.org/0000-0003-1893-4031"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sereina Riniker","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, 8093 Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-1893-4031","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, Vladimir-Prelog-Weg 2, 8093 Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019754904","https://openalex.org/A5056808182"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":45.0615,"has_fulltext":true,"cited_by_count":143,"citation_normalized_percentile":{"value":0.9991562,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"64","issue":"5","first_page":"1560","last_page":"1567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9918000102043152,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.920199990272522,"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":0.9222403764724731},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7405063509941101},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6055113673210144},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6041086316108704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5505688786506653},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.4948362708091736},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4471193850040436},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.436862975358963},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4287205636501312},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42833825945854187},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4160309433937073},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3255528211593628},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.2300792634487152},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21888667345046997},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19340282678604126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1776115596294403},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15364041924476624},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1338755488395691}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.9222403764724731},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7405063509941101},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6055113673210144},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6041086316108704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5505688786506653},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.4948362708091736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4471193850040436},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.436862975358963},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4287205636501312},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42833825945854187},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4160309433937073},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3255528211593628},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2300792634487152},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21888667345046997},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19340282678604126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1776115596294403},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15364041924476624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1338755488395691},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"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":"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":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.4c00049","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00049","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00049","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:38394344","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38394344","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},{"id":"pmh:oai:pubmedcentral.nih.gov:10934815","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10934815","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10934815/pdf/ci4c00049.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 Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.4c00049","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00049","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00049","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392093325.pdf","grobid_xml":"https://content.openalex.org/works/W4392093325.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1987275960","https://openalex.org/W1990236573","https://openalex.org/W1995134802","https://openalex.org/W2073735425","https://openalex.org/W2088970363","https://openalex.org/W2096541451","https://openalex.org/W2284941582","https://openalex.org/W2329862012","https://openalex.org/W2574428496","https://openalex.org/W2610771738","https://openalex.org/W3172444956","https://openalex.org/W4297200146","https://openalex.org/W4377232456","https://openalex.org/W4388455891"],"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/W2745792676","https://openalex.org/W4206278474"],"abstract_inverted_index":{"High":[0],"Resolution":[1],"Image":[2],"Download":[3],"MS":[4],"PowerPoint":[5],"Slide":[6],"As":[7],"part":[8],"of":[9,84,97,107,151,186,205,230,241,281],"the":[10,73,78,82,105,119,128,152,170,173,187,202,206,228,279,282,301,310],"ongoing":[11],"quest":[12],"to":[13,39,69,197,277,288],"find":[14],"or":[15],"construct":[16],"large":[17,95],"data":[18,44,52,93,99,112,233,245,263,283],"sets":[19,113,264],"for":[20,29,37,118,294,309],"use":[21],"in":[22,110,124,190,195,319],"validating":[23],"new":[24],"machine":[25],"learning":[26],"(ML)":[27],"approaches":[28],"bioactivity":[30,295],"prediction,":[31],"it":[32],"has":[33],"become":[34],"distressingly":[35],"common":[36],"researchers":[38],"combine":[40,198],"literature":[41,98,248],"IC":[42,135],"50":[43,136],"generated":[45],"using":[46,114,139],"different":[47,247,266],"assays":[48,74,85,126,137,200,267],"into":[49],"a":[50,65],"single":[51],"set.":[53],"It":[54],"is":[55,64,180,225],"well-known":[56],"that":[57,134,184,254,270,284,306],"there":[58],"are":[59,75,88,122,285,314],"many":[60],"situations":[61],"where":[62,116],"this":[63],"scientifically":[66],"risky":[67],"thing":[68],"do,":[70],"even":[71,89],"when":[72,91,243,261],"against":[76,127],"exactly":[77],"same":[79,120,129],"target,":[80],"but":[81],"risks":[83],"being":[86,286],"incompatible":[87],"higher":[90],"pulling":[92],"from":[94,246,265],"collections":[96],"like":[100],"ChEMBL.":[101],"Here,":[102],"we":[103,307],"estimate":[104],"amount":[106],"noise":[108,242],"present":[109],"combined":[111],"cases":[115],"measurements":[117],"compound":[121],"reported":[123],"multiple":[125],"target.":[130],"This":[131],"approach":[132,313],"shows":[133,238],"selected":[138],"minimal":[140],"curation":[141,260,273,312],"settings":[142],"have":[143],"poor":[144],"agreement":[145],"with":[146],"each":[147],"other:":[148],"almost":[149],"65%":[150],"points":[153,207],"differ":[154,162,208],"by":[155,163,177,209,216],"more":[156,164,210,217],"than":[157,165,211,218],"0.3":[158,212],"log":[159,167,213,220],"units,":[160,214],"27%":[161],"one":[166,219],"unit,":[168,221],"and":[169,222,268,290,303],"correlation":[171],"between":[172],"assays,":[174],"as":[175,316],"measured":[176],"Kendall\u2019s":[178,223],"\u03c4,":[179],"only":[181],"0.51.":[182],"Requiring":[183],"most":[185],"assay":[188],"metadata":[189],"ChEMBL":[191,304],"matches":[192],"(\u201cmaximal":[193],"curation\u201d)":[194],"order":[196],"two":[199],"improves":[201],"situation":[203],"(48%":[204],"13%":[215],"\u03c4":[224],"0.71)":[226],"at":[227],"expense":[229],"having":[231],"smaller":[232],"sets.":[234],"Surprisingly,":[235],"our":[236,271,320],"analysis":[237],"similar":[239],"amounts":[240],"combining":[244,262],"K":[249],"i":[250],"assays.":[251],"We":[252],"suggest":[253],"good":[255],"scientific":[256],"practice":[257],"requires":[258],"careful":[259],"hope":[269],"maximal":[272,311],"strategy":[274],"will":[275],"help":[276,298],"improve":[278],"quality":[280],"used":[287,308],"build":[289],"validate":[291],"ML":[292],"models":[293],"prediction.":[296],"To":[297],"achieve":[299],"this,":[300],"code":[302],"queries":[305],"available":[315],"open-source":[317],"software":[318],"GitHub":[321],"repository,":[322],"https://github.com/rinikerlab/overlapping_assays":[323],".":[324]},"counts_by_year":[{"year":2026,"cited_by_count":35},{"year":2025,"cited_by_count":70},{"year":2024,"cited_by_count":38}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2024-02-24T00:00:00"}