{"id":"https://openalex.org/W7225224649","doi":"https://doi.org/10.1002/jcc.70521","title":"LTVAE : Hybrid LSTM \u2013Transformer VAE Architecture for Molecular SMILES Representation","display_name":"LTVAE : Hybrid LSTM \u2013Transformer VAE Architecture for Molecular SMILES Representation","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225224649","doi":"https://doi.org/10.1002/jcc.70521","pmid":"https://pubmed.ncbi.nlm.nih.gov/42977687","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13731161"},"language":"en","primary_location":{"id":"doi:10.1002/jcc.70521","doi":"https://doi.org/10.1002/jcc.70521","is_oa":true,"landing_page_url":"https://doi.org/10.1002/jcc.70521","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/jcc.70521","source":{"id":"https://openalex.org/S21117631","display_name":"Journal of Computational Chemistry","issn_l":"0192-8651","issn":["0192-8651","1096-987X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"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 Computational Chemistry","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/jcc.70521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063054260","display_name":"Md. Halim Mondol","orcid":"https://orcid.org/0000-0002-3385-8789","observed_orcids":["https://orcid.org/0000-0002-3385-8789"]},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Halim Mondol","raw_affiliation_strings":["Electrical and Computer Engineering North Carolina State University  Raleigh North Carolina USA"],"raw_orcid":"https://orcid.org/0000-0002-3385-8789","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering North Carolina State University  Raleigh North Carolina USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072976618","display_name":"Qingshan Wei","orcid":"https://orcid.org/0000-0003-1214-010X","observed_orcids":["https://orcid.org/0000-0003-1214-010X"]},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingshan Wei","raw_affiliation_strings":["Chemical and Biomolecular Engineering North Carolina State University  Raleigh North Carolina USA"],"raw_orcid":"https://orcid.org/0000-0003-1214-010X","affiliations":[{"raw_affiliation_string":"Chemical and Biomolecular Engineering North Carolina State University  Raleigh North Carolina USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024158572","display_name":"Edgar J. Lobaton","orcid":"https://orcid.org/0000-0002-4056-8309","observed_orcids":["https://orcid.org/0000-0002-4056-8309"]},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edgar Lobaton","raw_affiliation_strings":["Electrical and Computer Engineering North Carolina State University  Raleigh North Carolina USA"],"raw_orcid":"https://orcid.org/0000-0002-4056-8309","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering North Carolina State University  Raleigh North Carolina USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5063054260"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":{"value":4520,"currency":"USD","value_usd":4520},"apc_paid":{"value":4520,"currency":"USD","value_usd":4520},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79039756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"47","issue":"29","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.003800000064074993,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/smiles-representation","display_name":"SMILES representation","score":0.6690000295639038},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.8930000066757202},{"id":"https://openalex.org/keywords/latent-representations","display_name":"latent representations","score":0.42899999022483826},{"id":"https://openalex.org/keywords/molecular-reconstruction","display_name":"molecular reconstruction","score":0.7409999966621399},{"id":"https://openalex.org/keywords/chemical-validity","display_name":"chemical validity","score":0.6710000038146973},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.7490000128746033},{"id":"https://openalex.org/keywords/dye-molecules","display_name":"dye molecules","score":0.859000027179718},{"id":"https://openalex.org/keywords/conjugation-length","display_name":"conjugation length","score":0.8140000104904175},{"id":"https://openalex.org/keywords/zinc15","display_name":"ZINC15","score":0.8240000009536743}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9214000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074999809265137},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6985999941825867},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.630299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5898000001907349},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.3538999855518341},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2572999894618988}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/jcc.70521","doi":"https://doi.org/10.1002/jcc.70521","is_oa":true,"landing_page_url":"https://doi.org/10.1002/jcc.70521","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/jcc.70521","source":{"id":"https://openalex.org/S21117631","display_name":"Journal of Computational Chemistry","issn_l":"0192-8651","issn":["0192-8651","1096-987X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"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 Computational Chemistry","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13731161","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13731161/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13731161/pdf/JCC-47-0.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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Comput Chem","raw_type":"Text"},{"id":"pmid:42977687","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42977687","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,"listed_in":[],"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 computational chemistry","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1002/jcc.70521","doi":"https://doi.org/10.1002/jcc.70521","is_oa":true,"landing_page_url":"https://doi.org/10.1002/jcc.70521","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/jcc.70521","source":{"id":"https://openalex.org/S21117631","display_name":"Journal of Computational Chemistry","issn_l":"0192-8651","issn":["0192-8651","1096-987X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"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 Computational Chemistry","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225224649.pdf","grobid_xml":"https://content.openalex.org/works/W7225224649.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2027482274","https://openalex.org/W2529996553","https://openalex.org/W2777416523","https://openalex.org/W2965654782","https://openalex.org/W2982596783","https://openalex.org/W2986232138","https://openalex.org/W2991736596","https://openalex.org/W3006149642","https://openalex.org/W3023204497","https://openalex.org/W3045522182","https://openalex.org/W3093926611","https://openalex.org/W3116727726","https://openalex.org/W3185087522","https://openalex.org/W4213070269","https://openalex.org/W4220798957","https://openalex.org/W4382182163","https://openalex.org/W4382239609","https://openalex.org/W4391987935","https://openalex.org/W4403256806","https://openalex.org/W4404480687","https://openalex.org/W4406999737","https://openalex.org/W4408131429","https://openalex.org/W4414464658"],"related_works":["https://openalex.org/W2946928580","https://openalex.org/W2996945591","https://openalex.org/W7164921359","https://openalex.org/W7202207339","https://openalex.org/W4392270476","https://openalex.org/W4404920654","https://openalex.org/W4231556613","https://openalex.org/W7204252119","https://openalex.org/W4393159848","https://openalex.org/W2886791556"],"abstract_inverted_index":{"ABSTRACT":[0],"A":[1],"hybrid":[2],"LSTM\u2013Transformer":[3],"Variational":[4],"Autoencoder":[5],"(LTVAE)":[6],"framework":[7,81],"is":[8,62,116],"introduced":[9],"in":[10,49,69,166],"this":[11],"paper":[12],"for":[13],"learning":[14],"compact":[15],"and":[16,32,36,46,98,128,145,152,172,180],"chemically":[17,173],"meaningful":[18],"latent":[19,108,135,168,185],"representations":[20],"from":[21],"SMILES":[22],"strings,":[23],"providing":[24,158],"a":[25,55,59,76,93,106,119],"SMILES\u2010to\u2010latent\u2010to\u2010SMILES":[26],"representation":[27],"model":[28],"trained":[29,74],"on":[30,34,75,118,161],"ZINC15":[31,35,78],"evaluated":[33,71,117],"an":[37,99,112],"out\u2010of\u2010distribution":[38,113],"dye":[39,122],"dataset.":[40],"In":[41],"the":[42,70,80,167,178,183],"proposed":[43],"model,":[44],"sequential":[45],"structural":[47,147,175],"dependencies":[48],"molecular":[50,67,143,162],"strings":[51],"are":[52,131],"encoded":[53],"using":[54,105],"bidirectional":[56],"LSTM,":[57],"while":[58],"Transformer\u2010based":[60],"decoder":[61],"employed":[63],"to":[64],"reconstruct":[65],"valid":[66],"structures":[68],"settings.":[72],"When":[73],"curated":[77],"dataset,":[79,123],"achieves":[82],"reasonable":[83],"reconstruction":[84],"performance,":[85],"with":[86,140,156],"98.58%":[87],"token\u2010level":[88,126],"accuracy,":[89,92],"92.19%":[90],"string\u2010level":[91],"99.30%":[94],"chemical":[95],"validity":[96,130],"ratio,":[97],"average":[100],"Levenshtein":[101],"distance":[102],"of":[103,182],"0.29":[104],"64\u2010dimensional":[107],"space.":[109],"Reconstruction":[110],"under":[111],"evaluation":[114],"setting":[115],"structurally":[120],"distinct":[121],"where":[124],"95.56%":[125],"accuracy":[127],"85.30%":[129],"achieved.":[132],"The":[133],"learned":[134,184],"space":[136,169],"preserves":[137],"trends":[138],"aligned":[139],"both":[141],"general":[142],"descriptors":[144],"dye\u2010relevant":[146],"descriptors,":[148],"particularly":[149],"conjugation":[150],"length":[151],"aromatic":[153],"surface":[154],"fraction,":[155],"Fsp":[157],"complementary":[159],"information":[160],"saturation.":[163],"Controlled":[164],"perturbations":[165],"suggest":[170],"smooth":[171],"consistent":[174],"variations,":[176],"illustrating":[177],"continuity":[179],"interpretability":[181],"manifold.":[186]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-05T00:00:00"}