{"id":"https://openalex.org/W4416144347","doi":"https://doi.org/10.1145/3721201.3725512","title":"Identifying SMILES from Molecular Structure Images","display_name":"Identifying SMILES from Molecular Structure Images","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4416144347","doi":"https://doi.org/10.1145/3721201.3725512"},"language":null,"primary_location":{"id":"doi:10.1145/3721201.3725512","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721201.3725512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alexander Dang","orcid":"https://orcid.org/0009-0006-6164-3036"},"institutions":[{"id":"https://openalex.org/I4210162751","display_name":"Newark Academy","ror":"https://ror.org/05d3xvm78","country_code":"US","type":"education","lineage":["https://openalex.org/I4210162751"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Dang","raw_affiliation_strings":["Newark Academy, Livingston, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0006-6164-3036","affiliations":[{"raw_affiliation_string":"Newark Academy, Livingston, NJ, USA","institution_ids":["https://openalex.org/I4210162751"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Emma Liu","orcid":"https://orcid.org/0009-0005-5242-6534"},"institutions":[{"id":"https://openalex.org/I2800565835","display_name":"Princeton Public Schools","ror":"https://ror.org/041m1e551","country_code":"US","type":"education","lineage":["https://openalex.org/I2800565835"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Liu","raw_affiliation_strings":["Princeton High School, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0005-5242-6534","affiliations":[{"raw_affiliation_string":"Princeton High School, Princeton, NJ, USA","institution_ids":["https://openalex.org/I2800565835"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023983709","display_name":"Wei Zhi","orcid":"https://orcid.org/0000-0001-5485-1095"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Wei","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-5485-1095","affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"484","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.45840001106262207,"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":0.45840001106262207,"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":0.4099000096321106,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.027400000020861626,"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":0.9214000105857849},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.46470001339912415},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.43149998784065247},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42879998683929443},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.4284999966621399},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3783999979496002},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.3691999912261963}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.9214000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487999796867371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.38370001316070557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C14314382","wikidata":"https://www.wikidata.org/wiki/Q1943386","display_name":"Molecular Pharmacology","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2989255885","wikidata":"https://www.wikidata.org/wiki/Q500256","display_name":"Molecular conformation","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721201.3725512","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721201.3725512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4282936206","https://openalex.org/W4353112191","https://openalex.org/W4405546127"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"extraction":[1],"of":[2,40,73],"Simplified":[3],"Molecular":[4],"Input":[5],"Line":[6],"Entry":[7],"System":[8],"(SMILES)":[9],"representations":[10,33],"from":[11],"molecular":[12,32,74,97,128],"structure":[13],"images":[14],"is":[15],"crucial":[16],"for":[17,29,65],"computational":[18],"chemistry":[19],"and":[20,58,95,100,108,113],"cheminformatics.":[21],"This":[22],"study":[23],"presents":[24],"a":[25,46,70],"machine":[26],"learning-based":[27],"approach":[28,87],"converting":[30],"graphical":[31],"into":[34],"SMILES":[35,84,121],"notation,":[36],"addressing":[37],"the":[38,76],"challenges":[39],"chemical":[41,89],"image":[42],"recognition.":[43],"We":[44],"developed":[45],"deep":[47],"learning":[48],"model":[49,77],"leveraging":[50],"Tensorflow/Keras":[51],"framework,":[52],"cheminformatics":[53],"tools":[54],"such":[55],"as":[56],"RDKit,":[57],"Long":[59],"Short-":[60],"Term":[61],"Memory":[62],"(LSTM)":[63],"networks":[64],"sequence":[66],"learning.":[67],"Trained":[68],"on":[69],"curated":[71],"dataset":[72,93],"images,":[75],"effectively":[78],"learns":[79],"structure-text":[80],"relationships,":[81],"enabling":[82],"high-accuracy":[83],"predictions.":[85],"Our":[86],"enhances":[88],"data":[90],"digitization,":[91],"improves":[92],"accuracy,":[94],"accelerates":[96],"property":[98],"assessments":[99],"drug":[101],"discovery,":[102],"driving":[103],"progress":[104],"in":[105],"pharmaceutical":[106],"research":[107],"personalized":[109],"medicine.":[110],"By":[111],"training":[112],"testing":[114],"an":[115],"image-captioning":[116],"model,":[117],"we":[118],"ensure":[119],"robust":[120],"generation":[122],"while":[123],"maintaining":[124],"high":[125],"fidelity":[126],"to":[127],"structures.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-12T00:00:00"}