{"id":"https://openalex.org/W2890013832","doi":"https://doi.org/10.1186/s13321-018-0300-0","title":"Exploring non-linear distance metrics in the structure\u2013activity space: QSAR models for human estrogen receptor","display_name":"Exploring non-linear distance metrics in the structure\u2013activity space: QSAR models for human estrogen receptor","publication_year":2018,"publication_date":"2018-09-18","ids":{"openalex":"https://openalex.org/W2890013832","doi":"https://doi.org/10.1186/s13321-018-0300-0","mag":"2890013832","pmid":"https://pubmed.ncbi.nlm.nih.gov/30229396"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-018-0300-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0300-0","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0300-0","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/track/pdf/10.1186/s13321-018-0300-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027249645","display_name":"Ilya A. Balabin","orcid":"https://orcid.org/0000-0001-6245-3855"},"institutions":[{"id":"https://openalex.org/I114662689","display_name":"Leidos (United States)","ror":"https://ror.org/012cvds63","country_code":"US","type":"company","lineage":["https://openalex.org/I114662689"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ilya A. Balabin","raw_affiliation_strings":["Leidos, Inc., 109 TW Alexander Drive, MD N127-01, Research Triangle Park, NC, 27711, USA. ilya.balabin@gmail.com","Leidos, Inc., 109 TW Alexander Drive, MD N127-01, Research Triangle Park, NC, 27711, USA"],"raw_orcid":"https://orcid.org/0000-0001-6245-3855","affiliations":[{"raw_affiliation_string":"Leidos, Inc., 109 TW Alexander Drive, MD N127-01, Research Triangle Park, NC, 27711, USA. ilya.balabin@gmail.com","institution_ids":["https://openalex.org/I114662689"]},{"raw_affiliation_string":"Leidos, Inc., 109 TW Alexander Drive, MD N127-01, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I114662689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026992703","display_name":"Richard Judson","orcid":"https://orcid.org/0000-0002-2348-9633"},"institutions":[{"id":"https://openalex.org/I1302368450","display_name":"Environmental Protection Agency","ror":"https://ror.org/03tns0030","country_code":"US","type":"government","lineage":["https://openalex.org/I1302368450"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard S. Judson","raw_affiliation_strings":["US EPA, 109 TW Alexander Drive, ORD, NCCT, Research Triangle Park, NC, 27711, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US EPA, 109 TW Alexander Drive, ORD, NCCT, Research Triangle Park, NC, 27711, USA","institution_ids":["https://openalex.org/I1302368450","https://openalex.org/I1309191912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027249645"],"corresponding_institution_ids":["https://openalex.org/I114662689"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.569,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.70200439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":"1","first_page":"47","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9912999868392944,"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":0.9912999868392944,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.00139999995008111,"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/T10756","display_name":"Estrogen and related hormone effects","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8987942934036255},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6221466064453125},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.615123987197876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47122251987457275},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.460541695356369},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"Applicability domain","score":0.4499935209751129},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.44745534658432007},{"id":"https://openalex.org/keywords/estrogen-receptor","display_name":"Estrogen receptor","score":0.42457765340805054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3954562842845917},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.35164952278137207},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.23562240600585938},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14829537272453308}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8987942934036255},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6221466064453125},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.615123987197876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47122251987457275},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.460541695356369},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.4499935209751129},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.44745534658432007},{"id":"https://openalex.org/C84606932","wikidata":"https://www.wikidata.org/wiki/Q416496","display_name":"Estrogen receptor","level":4,"score":0.42457765340805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3954562842845917},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.35164952278137207},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.23562240600585938},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14829537272453308},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.0},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-018-0300-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0300-0","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0300-0","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:30229396","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30229396","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:6755572","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6755572","pdf_url":null,"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:d76d6779f2d24a88928e7a3461b1b8ec","is_oa":true,"landing_page_url":"https://doaj.org/article/d76d6779f2d24a88928e7a3461b1b8ec","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 10, Iss 1, Pp 1-11 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-018-0300-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0300-0","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-018-0300-0","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":[{"id":"https://openalex.org/F4320310389","display_name":"Novartis Foundation","ror":"https://ror.org/02f9zrr09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890013832.pdf","grobid_xml":"https://content.openalex.org/works/W2890013832.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1539567219","https://openalex.org/W1970197319","https://openalex.org/W1983478747","https://openalex.org/W1986466512","https://openalex.org/W1991146785","https://openalex.org/W1996327711","https://openalex.org/W2002067669","https://openalex.org/W2005690825","https://openalex.org/W2015558379","https://openalex.org/W2037536829","https://openalex.org/W2039609876","https://openalex.org/W2047709056","https://openalex.org/W2076625865","https://openalex.org/W2080922998","https://openalex.org/W2081320283","https://openalex.org/W2101234009","https://openalex.org/W2121435689","https://openalex.org/W2163751327","https://openalex.org/W2282070576","https://openalex.org/W2329907539","https://openalex.org/W2394108223","https://openalex.org/W2993880730"],"related_works":["https://openalex.org/W2746158299","https://openalex.org/W1969085205","https://openalex.org/W1977382278","https://openalex.org/W2090257471","https://openalex.org/W1970841929","https://openalex.org/W3005120176","https://openalex.org/W2309296013","https://openalex.org/W2985099987","https://openalex.org/W2055287694","https://openalex.org/W2089462264"],"abstract_inverted_index":{"BACKGROUND:":[0],"Quantitative":[1],"structure-activity":[2,62],"relationship":[3],"(QSAR)":[4],"models":[5,22],"are":[6,168],"important":[7],"tools":[8],"used":[9],"in":[10,39,60,80,87,133,144],"discovering":[11],"new":[12],"drug":[13],"candidates":[14],"and":[15,35,50,96,110,137],"identifying":[16],"potentially":[17],"harmful":[18],"environmental":[19],"chemicals.":[20],"These":[21],"often":[23],"face":[24],"two":[25],"fundamental":[26],"challenges:":[27],"limited":[28],"amount":[29],"of":[30,71,125],"available":[31,164],"biological":[32,89,165],"activity":[33,41,90,99,131,135,146,166],"data":[34,42,100,167],"noise":[36],"or":[37],"uncertainty":[38],"the":[40,61,72,81,88,106,118,140,163],"themselves.":[43],"To":[44],"address":[45],"these":[46],"challenges,":[47],"we":[48],"introduce":[49],"explore":[51],"a":[52],"QSAR":[53,159],"model":[54,66,93,115,121,143,160],"based":[55],"on":[56,69,123],"custom":[57],"distance":[58,154],"metrics":[59,155],"space.":[63,91],"METHODS:":[64],"The":[65,92,114],"is":[67,94],"built":[68],"top":[70,124],"k-nearest":[73],"neighbor":[74],"model,":[75],"incorporating":[76,152],"non-linearity":[77],"not":[78],"only":[79],"chemical":[82],"structure":[83],"space,":[84],"but":[85],"also":[86],"tuned":[95],"evaluated":[97],"using":[98],"for":[101],"human":[102,128],"estrogen":[103,129],"receptor":[104,130],"from":[105],"US":[107],"EPA":[108],"ToxCast":[109],"Tox21":[111],"databases.":[112],"RESULTS:":[113],"closely":[116],"trails":[117],"CERAPP":[119,141],"consensus":[120,142],"(built":[122],"48":[126],"individual":[127],"models)":[132],"agonist":[134],"predictions":[136],"consistently":[138],"outperforms":[139],"antagonist":[145],"predictions.":[147],"DISCUSSION:":[148],"We":[149],"suggest":[150],"that":[151],"non-linear":[153],"may":[156],"significantly":[157],"improve":[158],"performance":[161],"when":[162],"limited.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}