{"id":"https://openalex.org/W4402224813","doi":"https://doi.org/10.1021/acs.jcim.4c01396","title":"Large Language Models as Molecular Design Engines","display_name":"Large Language Models as Molecular Design Engines","publication_year":2024,"publication_date":"2024-09-04","ids":{"openalex":"https://openalex.org/W4402224813","doi":"https://doi.org/10.1021/acs.jcim.4c01396","pmid":"https://pubmed.ncbi.nlm.nih.gov/39231030"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c01396","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01396","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/A5015386412","display_name":"Debjyoti Bhattacharya","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debjyoti Bhattacharya","raw_affiliation_strings":["Materials Science and Engineering, Pennsylvania State University, University Park, Pennsylvania 16802, United States"],"raw_orcid":"https://orcid.org/0000-0003-3707-847X","affiliations":[{"raw_affiliation_string":"Materials Science and Engineering, Pennsylvania State University, University Park, Pennsylvania 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420008","display_name":"Harrison J. Cassady","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harrison J. Cassady","raw_affiliation_strings":["Department of Chemical Engineering and Material Science, Michigan State University, East Lansing, Michigan 48824, United States"],"raw_orcid":"https://orcid.org/0000-0002-6453-1762","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering and Material Science, Michigan State University, East Lansing, Michigan 48824, United States","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052734441","display_name":"Michael A. Hickner","orcid":"https://orcid.org/0000-0002-2252-7626"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A. Hickner","raw_affiliation_strings":["Department of Chemical Engineering and Material Science, Michigan State University, East Lansing, Michigan 48824, United States"],"raw_orcid":"https://orcid.org/0000-0002-2252-7626","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering and Material Science, Michigan State University, East Lansing, Michigan 48824, United States","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035545283","display_name":"Wesley F. Reinhart","orcid":"https://orcid.org/0000-0001-7256-2123"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wesley F. Reinhart","raw_affiliation_strings":["Institute for Computational and Data Sciences, Pennsylvania State University, University Park, Pennsylvania 16802, United States","Materials Science and Engineering, Pennsylvania State University, University Park, Pennsylvania 16802, United States"],"raw_orcid":"https://orcid.org/0000-0001-7256-2123","affiliations":[{"raw_affiliation_string":"Institute for Computational and Data Sciences, Pennsylvania State University, University Park, Pennsylvania 16802, United States","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Materials Science and Engineering, Pennsylvania State University, University Park, Pennsylvania 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035545283"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":3.8947,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96725009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"64","issue":"18","first_page":"7086","last_page":"7096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9983999729156494,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9685999751091003,"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/chemical-space","display_name":"Chemical space","score":0.7131574153900146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6935312747955322},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5352991223335266},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5322140455245972},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4633830785751343},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4477059841156006},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4401078224182129},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4251294732093811},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41474515199661255},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3970590829849243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3925883173942566},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.3260442614555359},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1590164303779602}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.7131574153900146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935312747955322},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5352991223335266},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5322140455245972},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4633830785751343},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4477059841156006},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4401078224182129},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4251294732093811},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41474515199661255},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3970590829849243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3925883173942566},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3260442614555359},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1590164303779602},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c01396","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01396","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:39231030","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39231030","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":[{"id":"https://openalex.org/G8479233696","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338420","funder_display_name":"Energy Frontier Research Centers"}],"funders":[{"id":"https://openalex.org/F4320338420","display_name":"Energy Frontier Research Centers","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2032084435","https://openalex.org/W2601081289","https://openalex.org/W2804431384","https://openalex.org/W2889326414","https://openalex.org/W2900694120","https://openalex.org/W3111676828","https://openalex.org/W3116865743","https://openalex.org/W3165171933","https://openalex.org/W3201230437","https://openalex.org/W3209056694","https://openalex.org/W3217546525","https://openalex.org/W4212774754","https://openalex.org/W4213070269","https://openalex.org/W4220798957","https://openalex.org/W4221067726","https://openalex.org/W4319996831","https://openalex.org/W4320857994","https://openalex.org/W4324026004","https://openalex.org/W4324102210","https://openalex.org/W4381059804","https://openalex.org/W4382182163","https://openalex.org/W4382239609","https://openalex.org/W4383216745","https://openalex.org/W4385671288","https://openalex.org/W4386250621","https://openalex.org/W4387114475","https://openalex.org/W4390789080","https://openalex.org/W4392202731","https://openalex.org/W4396723768","https://openalex.org/W4399884514","https://openalex.org/W4403363609","https://openalex.org/W4403547237","https://openalex.org/W6600424091","https://openalex.org/W6601141708","https://openalex.org/W6602670149"],"related_works":["https://openalex.org/W2973074952","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4283395020","https://openalex.org/W4320732452","https://openalex.org/W135095951","https://openalex.org/W4286980196","https://openalex.org/W4385588199","https://openalex.org/W3199987505","https://openalex.org/W4385760073"],"abstract_inverted_index":{"The":[0],"design":[1,21,192],"of":[2,97,174,185],"small":[3],"molecules":[4,101,127,175],"is":[5,59,160],"crucial":[6],"for":[7,53,88],"technological":[8],"applications":[9],"ranging":[10],"from":[11],"drug":[12],"discovery":[13],"to":[14,18,24,33,40,69,94,129,162,169],"energy":[15],"storage.":[16],"Due":[17],"the":[19,28,117,150,158,171,183],"vast":[20],"space":[22],"available":[23],"modern":[25],"synthetic":[26],"chemistry,":[27],"community":[29],"has":[30],"increasingly":[31],"sought":[32],"use":[34,58],"data-driven":[35],"and":[36,65,72,99,125,135,189],"machine":[37,46],"learning":[38,47],"approaches":[39],"navigate":[41],"this":[42,76,112],"space.":[43],"Although":[44],"generative":[45],"methods":[48],"have":[49,83],"recently":[50],"shown":[51],"potential":[52,86,184],"computational":[54],"molecular":[55,89,165,191],"design,":[56,90],"their":[57],"hindered":[60],"by":[61],"complex":[62],"training":[63],"procedures,":[64],"they":[66,92],"often":[67],"fail":[68],"generate":[70],"valid":[71,134],"unique":[73,136],"molecules.":[74,137],"In":[75,111],"context,":[77],"pretrained":[78],"Large":[79],"Language":[80],"Models":[81],"(LLMs)":[82],"emerged":[84],"as":[85,91,187],"tools":[87],"appear":[93],"be":[95],"capable":[96],"creating":[98],"modifying":[100],"based":[102],"on":[103],"simple":[104],"instructions":[105],"provided":[106],"through":[107],"natural":[108],"language":[109],"prompts.":[110,179],"work,":[113],"we":[114,147],"show":[115],"that":[116],"Claude":[118],"3":[119],"Opus":[120],"LLM":[121],"can":[122],"read,":[123],"write,":[124],"modify":[126],"according":[128],"prompts,":[130],"with":[131],"impressive":[132],"97%":[133],"By":[138],"quantifying":[139],"these":[140],"modifications":[141],"in":[142],"a":[143],"low-dimensional":[144],"latent":[145],"space,":[146],"systematically":[148],"evaluate":[149],"model's":[151],"behavior":[152],"under":[153],"different":[154],"prompting":[155],"conditions.":[156],"Notably,":[157],"model":[159],"able":[161],"perform":[163],"guided":[164],"generation":[166],"when":[167],"asked":[168],"manipulate":[170],"electronic":[172],"structure":[173],"using":[176],"simple,":[177],"natural-language":[178],"Our":[180],"findings":[181],"highlight":[182],"LLMs":[186],"powerful":[188],"versatile":[190],"engines.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}