{"id":"https://openalex.org/W3036931110","doi":"https://doi.org/10.1021/acs.jcim.9b01212","title":"Predicting Binding from Screening Assays with Transformer Network Embeddings","display_name":"Predicting Binding from Screening Assays with Transformer Network Embeddings","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3036931110","doi":"https://doi.org/10.1021/acs.jcim.9b01212","mag":"3036931110","pmid":"https://pubmed.ncbi.nlm.nih.gov/32568539"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.9b01212","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b01212","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/A5040859657","display_name":"Paul Morris","orcid":"https://orcid.org/0000-0003-0139-5262"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul Morris","raw_affiliation_strings":["Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States"],"raw_orcid":"https://orcid.org/0000-0003-0139-5262","affiliations":[{"raw_affiliation_string":"Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024431013","display_name":"Rachel St. Clair","orcid":"https://orcid.org/0000-0001-7590-116X"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel St. Clair","raw_affiliation_strings":["Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003569746","display_name":"William Edward Hahn","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Edward Hahn","raw_affiliation_strings":["Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055719182","display_name":"Elan Barenholtz","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elan Barenholtz","raw_affiliation_strings":["Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complex Systems and Brain Sciences, Florida Atlantic University, Boca Raton, Florida 33431, United States","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040859657"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":null,"apc_paid":null,"fwci":3.9019,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.9468803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"60","issue":"9","first_page":"4191","last_page":"4199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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":0.9952999949455261,"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/cheminformatics","display_name":"Cheminformatics","score":0.8475689888000488},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.8076056241989136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6844944953918457},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.6220327615737915},{"id":"https://openalex.org/keywords/in-silico","display_name":"In silico","score":0.620014488697052},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5982025861740112},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5215159058570862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49029067158699036},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46109142899513245},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.4561547338962555},{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.4537021815776825},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44575053453445435},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4266057014465332},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4159567952156067},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41142144799232483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3594563603401184},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2544329762458801},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2403106689453125},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.161557137966156},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09768256545066833}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8475689888000488},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.8076056241989136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844944953918457},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.6220327615737915},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.620014488697052},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5982025861740112},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5215159058570862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49029067158699036},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46109142899513245},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.4561547338962555},{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.4537021815776825},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44575053453445435},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4266057014465332},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4159567952156067},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41142144799232483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3594563603401184},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2544329762458801},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2403106689453125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.161557137966156},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09768256545066833},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.9b01212","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b01212","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:32568539","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32568539","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W197427643","https://openalex.org/W1573009101","https://openalex.org/W1665214252","https://openalex.org/W1810943226","https://openalex.org/W1969017960","https://openalex.org/W1983478747","https://openalex.org/W1991392549","https://openalex.org/W2016589492","https://openalex.org/W2033757486","https://openalex.org/W2046589863","https://openalex.org/W2058823343","https://openalex.org/W2064675550","https://openalex.org/W2072566913","https://openalex.org/W2095705004","https://openalex.org/W2123179625","https://openalex.org/W2124136621","https://openalex.org/W2133564696","https://openalex.org/W2138857742","https://openalex.org/W2151697120","https://openalex.org/W2157331557","https://openalex.org/W2171830166","https://openalex.org/W2204695023","https://openalex.org/W2221583060","https://openalex.org/W2234529989","https://openalex.org/W2290847742","https://openalex.org/W2295582178","https://openalex.org/W2479356696","https://openalex.org/W2502949459","https://openalex.org/W2518108298","https://openalex.org/W2526925775","https://openalex.org/W2582187633","https://openalex.org/W2604306554","https://openalex.org/W2610646689","https://openalex.org/W2618574054","https://openalex.org/W2626778328","https://openalex.org/W2714724074","https://openalex.org/W2742835787","https://openalex.org/W2771996273","https://openalex.org/W2775684663","https://openalex.org/W2784055555","https://openalex.org/W2784213390","https://openalex.org/W2793273050","https://openalex.org/W2796108585","https://openalex.org/W2801991413","https://openalex.org/W2886544065","https://openalex.org/W2887280559","https://openalex.org/W2896457183","https://openalex.org/W2899070097","https://openalex.org/W2901476322","https://openalex.org/W2904656109","https://openalex.org/W2906755148","https://openalex.org/W2913930293","https://openalex.org/W2919115771","https://openalex.org/W2935703330","https://openalex.org/W2959938226","https://openalex.org/W2962764460","https://openalex.org/W2963017945","https://openalex.org/W2965556524","https://openalex.org/W2966357564","https://openalex.org/W2969457089","https://openalex.org/W2974531988","https://openalex.org/W2984234582","https://openalex.org/W2996604169","https://openalex.org/W3098189759","https://openalex.org/W3100157108","https://openalex.org/W3100704554","https://openalex.org/W3104636952","https://openalex.org/W3203137202","https://openalex.org/W3211848854","https://openalex.org/W4233613299","https://openalex.org/W6602045790","https://openalex.org/W6610450269","https://openalex.org/W6702248584","https://openalex.org/W6743198006"],"related_works":["https://openalex.org/W3005441379","https://openalex.org/W4382246684","https://openalex.org/W2997728144","https://openalex.org/W2770765812","https://openalex.org/W4207063555","https://openalex.org/W2780675302","https://openalex.org/W4294024451","https://openalex.org/W2072444571","https://openalex.org/W2172072929","https://openalex.org/W2079781933"],"abstract_inverted_index":{"Cheminformatics":[0],"aims":[1],"to":[2,54,68,86,108,126,130,185],"assist":[3],"in":[4,37,56,143],"chemistry":[5],"applications":[6],"that":[7,49,174],"depend":[8],"on":[9,93,145,152],"molecular":[10],"interactions,":[11],"structural":[12,111,170],"characteristics,":[13],"and":[14,22,171,182],"functional":[15,172],"properties.":[16],"The":[17,99,178],"arrival":[18],"of":[19,25,62,71,79,96,101,113,163,169],"deep":[20],"learning":[21,125],"the":[23,94,110,140,153,164],"abundance":[24],"easily":[26],"accessible":[27],"chemical":[28,51],"data":[29],"from":[30],"repositories":[31],"like":[32],"PubChem":[33],"have":[34],"enabled":[35],"advancements":[36],"computer-aided":[38],"drug":[39],"discovery.":[40],"Virtual":[41],"high-throughput":[42],"screening":[43,97],"(vHTS)":[44],"is":[45,65,121],"one":[46],"such":[47],"technique":[48],"integrates":[50],"domain":[52],"knowledge":[53],"perform":[55,87],"silico":[57],"biomolecular":[58],"simulations,":[59],"but":[60],"prediction":[61,91,147],"binding":[63,73,89,128,136,146,176],"affinity":[64,90,129],"restricted":[66],"due":[67],"limited":[69],"availability":[70],"ground-truth":[72],"assay":[74],"results.":[75],"Here,":[76],"text":[77],"representations":[78],"83":[80],"000":[81,82],"molecules":[83],"are":[84,188],"leveraged":[85],"single-target":[88],"directly":[92],"outcome":[95],"assays.":[98],"embedding":[100,155,165],"an":[102,159],"end-to-end":[103],"transformer":[104],"neural":[105],"network,":[106],"trained":[107,151],"encode":[109],"characteristics":[112],"a":[114,117],"molecule":[115],"via":[116],"text-based":[118],"translation":[119,154],"task,":[120],"repurposed":[122],"through":[123],"transfer":[124],"classify":[127],"single":[131],"targets":[132],"with":[133],"few":[134],"known":[135],"compounds.":[137],"We":[138],"quantify":[139],"observed":[141],"increase":[142],"AUC":[144],"tasks":[148],"between":[149],"classifiers":[150],"versus":[156],"those":[157],"using":[158],"untrained":[160],"embedding.":[161],"Visualization":[162],"space":[166],"reveals":[167],"organization":[168],"properties":[173],"aid":[175],"prediction.":[177],"pretrained":[179],"transformer,":[180],"data,":[181],"associated":[183],"software":[184],"extract":[186],"embeddings":[187],"made":[189],"publicly":[190],"available":[191],"at":[192],"https://github.com/mpcrlab/MolecularTransformerEmbeddings.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
