{"id":"https://openalex.org/W4411855876","doi":"https://doi.org/10.1021/acs.jcim.5c00699","title":"A Machine Learning Approach to Molecular Initiating Event Prediction Using High-Throughput Transcriptomic Chemical Screening Data","display_name":"A Machine Learning Approach to Molecular Initiating Event Prediction Using High-Throughput Transcriptomic Chemical Screening Data","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4411855876","doi":"https://doi.org/10.1021/acs.jcim.5c00699","pmid":"https://pubmed.ncbi.nlm.nih.gov/40592767"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00699","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00699","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/A5058182313","display_name":"Joseph L. Bundy","orcid":"https://orcid.org/0000-0002-7631-6197"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joseph L. Bundy","raw_affiliation_strings":["Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States","institution_ids":["https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015391585","display_name":"Jesse D. Rogers","orcid":"https://orcid.org/0000-0001-6667-2342"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse D. Rogers","raw_affiliation_strings":["Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States","institution_ids":["https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101805304","display_name":"Imran Shah","orcid":"https://orcid.org/0000-0003-0808-0140"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imran Shah","raw_affiliation_strings":["Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States","institution_ids":["https://openalex.org/I1302368450"]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard J. Judson","raw_affiliation_strings":["Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States","institution_ids":["https://openalex.org/I1302368450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018169292","display_name":"Logan J. Everett","orcid":"https://orcid.org/0000-0002-9713-6099"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Logan J. Everett","raw_affiliation_strings":["Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States","institution_ids":["https://openalex.org/I1302368450"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053259827","display_name":"Joshua Harrill","orcid":"https://orcid.org/0000-0003-4317-6391"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua A. Harrill","raw_affiliation_strings":["Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States"],"affiliations":[{"raw_affiliation_string":"Center for Computational Toxicology & Exposure, Office of Research and Development, US Environmental Protection Agency, 109 TW Alexander Dr, Durham, North Carolina 27709, United States","institution_ids":["https://openalex.org/I1302368450"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058182313"],"corresponding_institution_ids":["https://openalex.org/I1302368450"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19384307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":"13","first_page":"6671","last_page":"6684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9596999883651733,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9589999914169312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5645202994346619},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5105558633804321},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5029396414756775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027351379394531},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.49307748675346375},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.4503645896911621},{"id":"https://openalex.org/keywords/chemical-safety","display_name":"Chemical safety","score":0.4113554060459137},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3363719582557678},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.30042779445648193},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2729083299636841},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2362850308418274},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14748609066009521},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.14662891626358032},{"id":"https://openalex.org/keywords/biochemical-engineering","display_name":"Biochemical engineering","score":0.1188599169254303},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1118391752243042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5645202994346619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5105558633804321},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5029396414756775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027351379394531},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.49307748675346375},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.4503645896911621},{"id":"https://openalex.org/C2780465076","wikidata":"https://www.wikidata.org/wiki/Q1069289","display_name":"Chemical safety","level":2,"score":0.4113554060459137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3363719582557678},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.30042779445648193},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2729083299636841},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2362850308418274},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14748609066009521},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.14662891626358032},{"id":"https://openalex.org/C183696295","wikidata":"https://www.wikidata.org/wiki/Q2487696","display_name":"Biochemical engineering","level":1,"score":0.1188599169254303},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1118391752243042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":true},{"descriptor_ui":"D061986","descriptor_name":"MCF-7 Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D061986","descriptor_name":"MCF-7 Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c00699","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00699","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:40592767","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40592767","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306107","display_name":"U.S. Environmental Protection Agency","ror":"https://ror.org/03tns0030"},{"id":"https://openalex.org/F4320308963","display_name":"Oak Ridge Associated Universities","ror":"https://ror.org/0526p1y61"},{"id":"https://openalex.org/F4320332382","display_name":"Oak Ridge Institute for Science and Education","ror":"https://ror.org/0526p1y61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1976834739","https://openalex.org/W2000089305","https://openalex.org/W2004429971","https://openalex.org/W2005829575","https://openalex.org/W2025508567","https://openalex.org/W2053131174","https://openalex.org/W2053850724","https://openalex.org/W2087155189","https://openalex.org/W2103017472","https://openalex.org/W2103344195","https://openalex.org/W2116791732","https://openalex.org/W2123879591","https://openalex.org/W2130410032","https://openalex.org/W2136147153","https://openalex.org/W2144062280","https://openalex.org/W2149044745","https://openalex.org/W2179438025","https://openalex.org/W2429101022","https://openalex.org/W2612467560","https://openalex.org/W2619508573","https://openalex.org/W2749613778","https://openalex.org/W2768921712","https://openalex.org/W2905940429","https://openalex.org/W2911968308","https://openalex.org/W2919637418","https://openalex.org/W2957947066","https://openalex.org/W3129067354","https://openalex.org/W3155381855","https://openalex.org/W3184729641","https://openalex.org/W4214884086","https://openalex.org/W4220690839","https://openalex.org/W4294216483","https://openalex.org/W4307407889","https://openalex.org/W4386914500","https://openalex.org/W4389269873","https://openalex.org/W4399579002","https://openalex.org/W4401659129","https://openalex.org/W4401835142","https://openalex.org/W4410362017"],"related_works":["https://openalex.org/W2973074952","https://openalex.org/W4399416193","https://openalex.org/W4320732452","https://openalex.org/W135095951","https://openalex.org/W4286980196","https://openalex.org/W4385588199","https://openalex.org/W3199987505","https://openalex.org/W4385760073","https://openalex.org/W2600435468","https://openalex.org/W2324927567"],"abstract_inverted_index":{"Improved":[0],"scalability":[1],"of":[2,25,130,168,215],"high-throughput":[3],"RNA-sequencing":[4],"technologies":[5],"has":[6],"contributed":[7],"to":[8,38,80,126,177],"their":[9],"proposed":[10],"use":[11],"in":[12,41,100,218],"regulatory":[13],"contexts":[14],"for":[15,34,48,65,114,181,198],"chemical":[16,42,73,98,139,226],"hazard":[17],"identification.":[18],"However,":[19],"the":[20,128,142,213,220],"high":[21],"dimensionality":[22],"and":[23,164,206],"size":[24],"these":[26,36],"transcriptomic":[27,53,72,225],"data":[28,37,54,119,197],"sets":[29,55],"present":[30,62],"a":[31,57,63,108],"formidable":[32],"obstacle":[33],"utilizing":[35],"address":[39],"gaps":[40],"safety":[43],"information.":[44],"New":[45],"bioinformatic":[46],"approaches":[47],"extracting":[49],"mechanistic":[50],"insight":[51],"from":[52,71,97,106,137,193,223],"are":[56],"critical":[58],"need.":[59],"Here,":[60],"we":[61],"framework":[64,77,217],"predicting":[66,219],"molecular":[67,115,195],"initiating":[68],"events":[69],"(MIE)":[70],"bioactivity":[74],"screens.":[75,227],"This":[76],"trains":[78],"models":[79],"predict":[81,127],"<u>MIE</u>":[82],"activation":[83,129,222],"using":[84,134],"<u>M</u>achine":[85],"<u>L</u>earning":[86],"(MIEML).":[87],"Classifiers":[88,123],"were":[89,124,174],"trained":[90,125,155],"by":[91,117],"integrating":[92],"gene":[93],"expression":[94],"profiles,":[95],"derived":[96,136,192],"exposures":[99],"MCF-7":[101],"cells,":[102],"with":[103,190],"chemical-MIE":[104],"annotations":[105],"RefChemDB,":[107],"database":[109],"that":[110,149],"identifies":[111],"reference":[112,138,170],"chemicals":[113],"targets":[116],"aggregating":[118],"across":[120],"multiple":[121],"sources.":[122],"nine":[131,143],"distinct":[132],"MIEs":[133,144,167],"profiles":[135,159],"exposures.":[140],"Of":[141],"modeled,":[145],"three":[146],"yielded":[147],"classifiers":[148,154,173],"performed":[150],"significantly":[151],"better":[152],"than":[153],"on":[156],"randomly":[157],"selected":[158],"(<i>p</i>":[160],"value":[161],"\u2264":[162],"0.1)":[163],"correctly":[165],"predicted":[166],"training-excluded":[169],"chemicals.":[171,184],"These":[172,185,210],"then":[175],"used":[176],"generate":[178],"MIE":[179,221],"predictions":[180,186],"1750":[182],"test":[183],"showed":[187],"significant":[188],"overlap":[189],"those":[191],"targeted":[194],"bioassay":[196],"estrogen":[199],"receptor":[200,204,208],"agonism,":[201,205],"aryl":[202],"hydrocarbon":[203],"glucocorticoid":[207],"agonism.":[209],"results":[211],"demonstrate":[212],"utility":[214],"this":[216],"large":[224]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}