{"id":"https://openalex.org/W4379184641","doi":"https://doi.org/10.1088/2632-2153/acdb30","title":"SELFormer: molecular representation learning via SELFIES language models","display_name":"SELFormer: molecular representation learning via SELFIES language models","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4379184641","doi":"https://doi.org/10.1088/2632-2153/acdb30"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/acdb30","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/acdb30","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/acdb30/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://iopscience.iop.org/article/10.1088/2632-2153/acdb30/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003907697","display_name":"Atakan Y\u00fcksel","orcid":null},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Atakan Y\u00fcksel","raw_affiliation_strings":["Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY"],"affiliations":[{"raw_affiliation_string":"Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY","institution_ids":["https://openalex.org/I66514158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011465628","display_name":"Erva Ulusoy","orcid":"https://orcid.org/0000-0002-2643-0362"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Erva Ulusoy","raw_affiliation_strings":["Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY"],"affiliations":[{"raw_affiliation_string":"Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY","institution_ids":["https://openalex.org/I66514158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071698318","display_name":"Atabey \u00dcnl\u00fc","orcid":"https://orcid.org/0000-0003-0078-6069"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Atabey \u00dcnl\u00fc","raw_affiliation_strings":["Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY"],"affiliations":[{"raw_affiliation_string":"Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY","institution_ids":["https://openalex.org/I66514158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003981652","display_name":"Tunca Do\u011fan","orcid":"https://orcid.org/0000-0002-1298-9763"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Tunca Do\u011fan","raw_affiliation_strings":["Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY"],"affiliations":[{"raw_affiliation_string":"Compter Science and AI Engineering, Hacettepe University, Hacettepe Universitesi Beytepe Yerleskesi, Bilgisayar Muhendisligi Bolumu, kat:2 ofis no: 210, Cankaya, Ankara, -, 06800, TURKEY","institution_ids":["https://openalex.org/I66514158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003981652"],"corresponding_institution_ids":["https://openalex.org/I66514158"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":11.585,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.98884832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"4","issue":"2","first_page":"025035","last_page":"025035"},"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":0.9993000030517578,"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":0.9569000005722046,"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/computer-science","display_name":"Computer science","score":0.7521320581436157},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.716875433921814},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.6053035855293274},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.5425825715065002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5353022217750549},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5258393883705139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.471332311630249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45949438214302063},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.4477449059486389},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44201356172561646},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4274926483631134},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4128160774707794},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38850587606430054},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3524973392486572},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.3124351501464844},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10307952761650085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521320581436157},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.716875433921814},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.6053035855293274},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.5425825715065002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353022217750549},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5258393883705139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.471332311630249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45949438214302063},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.4477449059486389},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44201356172561646},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4274926483631134},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4128160774707794},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38850587606430054},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3524973392486572},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3124351501464844},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10307952761650085},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/acdb30","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/acdb30","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/acdb30/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:637ede00a8164e5e97ed8eb34b854e8c","is_oa":true,"landing_page_url":"https://doaj.org/article/637ede00a8164e5e97ed8eb34b854e8c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 4, Iss 2, p 025035 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/acdb30","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/acdb30","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/acdb30/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4379184641.pdf"},"referenced_works_count":101,"referenced_works":["https://openalex.org/W2008505552","https://openalex.org/W2014858249","https://openalex.org/W2027482274","https://openalex.org/W2060531713","https://openalex.org/W2076498053","https://openalex.org/W2092285329","https://openalex.org/W2142633038","https://openalex.org/W2145578524","https://openalex.org/W2152849720","https://openalex.org/W2163922914","https://openalex.org/W2406943157","https://openalex.org/W2461470610","https://openalex.org/W2558999090","https://openalex.org/W2580386812","https://openalex.org/W2594183968","https://openalex.org/W2606780347","https://openalex.org/W2726670313","https://openalex.org/W2753921001","https://openalex.org/W2766578585","https://openalex.org/W2767887454","https://openalex.org/W2786672974","https://openalex.org/W2792524998","https://openalex.org/W2887905891","https://openalex.org/W2896457183","https://openalex.org/W2900694120","https://openalex.org/W2937307539","https://openalex.org/W2950875922","https://openalex.org/W2962711740","https://openalex.org/W2962810718","https://openalex.org/W2962876364","https://openalex.org/W2965373594","https://openalex.org/W2966357564","https://openalex.org/W2974531988","https://openalex.org/W2980282514","https://openalex.org/W2991220304","https://openalex.org/W3005552578","https://openalex.org/W3009321976","https://openalex.org/W3023204497","https://openalex.org/W3027362665","https://openalex.org/W3034999214","https://openalex.org/W3045928028","https://openalex.org/W3085139254","https://openalex.org/W3093934881","https://openalex.org/W3098189759","https://openalex.org/W3109892317","https://openalex.org/W3114291043","https://openalex.org/W3137038343","https://openalex.org/W3138925288","https://openalex.org/W3155806510","https://openalex.org/W3158331815","https://openalex.org/W3176163250","https://openalex.org/W3197693216","https://openalex.org/W3204651332","https://openalex.org/W3206711231","https://openalex.org/W3207924272","https://openalex.org/W4206615258","https://openalex.org/W4213070269","https://openalex.org/W4213077304","https://openalex.org/W4214868967","https://openalex.org/W4220991280","https://openalex.org/W4226159083","https://openalex.org/W4280597794","https://openalex.org/W4280602833","https://openalex.org/W4282017563","https://openalex.org/W4287025617","https://openalex.org/W4287828570","https://openalex.org/W4297179162","https://openalex.org/W4297632148","https://openalex.org/W4297808394","https://openalex.org/W4300537282","https://openalex.org/W4306179830","https://openalex.org/W4306955484","https://openalex.org/W4307468223","https://openalex.org/W4313485929","https://openalex.org/W4321370919","https://openalex.org/W4362503491","https://openalex.org/W4362664882","https://openalex.org/W4380786758","https://openalex.org/W4385245566","https://openalex.org/W4389888290","https://openalex.org/W6736685754","https://openalex.org/W6739901393","https://openalex.org/W6744596635","https://openalex.org/W6744881317","https://openalex.org/W6748816842","https://openalex.org/W6754929296","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768817161","https://openalex.org/W6769311223","https://openalex.org/W6772452955","https://openalex.org/W6784526300","https://openalex.org/W6786619936","https://openalex.org/W6793987055","https://openalex.org/W6799370299","https://openalex.org/W6803136014","https://openalex.org/W6838492796","https://openalex.org/W6841143912","https://openalex.org/W6843615466","https://openalex.org/W6844194202","https://openalex.org/W6847590285"],"related_works":["https://openalex.org/W4382246684","https://openalex.org/W4387845407","https://openalex.org/W2902857455","https://openalex.org/W4207004502","https://openalex.org/W2907885506","https://openalex.org/W4212982662","https://openalex.org/W4210899196","https://openalex.org/W2160244398","https://openalex.org/W2022444336","https://openalex.org/W2904656109"],"abstract_inverted_index":{"Abstract":[0],"Automated":[1],"computational":[2],"analysis":[3],"of":[4,14,34,41,62,70,190,252,260,274],"the":[5,31,71,84,107,112,116,201,219,250,254,258,270],"vast":[6],"chemical":[7,127,261],"space":[8],"is":[9,58,83,94,153],"critical":[10],"for":[11,44,79,90,162,200,269],"numerous":[12,97],"fields":[13],"research":[15,248],"such":[16],"as":[17,141,232],"drug":[18,194,276],"discovery":[19,273],"and":[20,37,102,137,148,160,183,192,240,264,272],"material":[21],"science.":[22],"Representation":[23],"learning":[24],"techniques":[25],"have":[26],"recently":[27],"been":[28],"employed":[29],"with":[30,96,225,237,278],"primary":[32],"objective":[33],"generating":[35],"compact":[36,136],"informative":[38],"numerical":[39],"expressions":[40],"complex":[42],"data,":[43],"efficient":[45],"usage":[46],"in":[47,115,143,257],"subsequent":[48],"prediction":[49,166],"tasks.":[50,167,203],"One":[51],"approach":[52],"to":[53,100,145],"efficiently":[54],"learn":[55,146],"molecular":[56,150,164,207],"representations":[57,208],"processing":[59,67],"string-based":[60,88],"notations":[61,78,256],"chemicals":[63],"via":[64,212],"natural":[65],"language":[66,128,262],"algorithms.":[68],"Majority":[69],"methods":[72],"proposed":[73],"so":[74],"far":[75],"utilize":[76],"SMILES":[77,93],"this":[80,119],"purpose,":[81],"which":[82,104,215],"most":[85],"extensively":[86],"used":[87],"encoding":[89],"molecules.":[91],"However,":[92],"associated":[95],"problems":[98],"related":[99],"validity":[101],"robustness,":[103],"may":[105],"prevent":[106],"model":[108,129,221],"from":[109],"effectively":[110],"uncovering":[111],"knowledge":[113],"hidden":[114],"data.":[117],"In":[118],"study,":[120],"we":[121],"propose":[122],"SELFormer,":[123],"a":[124,133,233],"transformer":[125],"architecture-based":[126],"(CLM)":[130],"that":[131,217],"utilizes":[132],"100%":[134],"valid,":[135],"expressive":[138],"notation,":[139],"SELFIES,":[140],"input,":[142],"order":[144],"flexible":[147],"high-quality":[149],"representations.":[151],"SELFormer":[152,174,211,231],"pre-trained":[154,220,241],"on":[155,186],"two":[156],"million":[157],"drug-like":[158],"compounds":[159],"fine-tuned":[161],"diverse":[163],"property":[165],"Our":[168],"performance":[169],"evaluation":[170],"has":[171],"revealed":[172],"that,":[173],"outperforms":[175],"all":[176],"competing":[177],"methods,":[178],"including":[179],"graph":[180],"learning-based":[181],"approaches":[182],"SMILES-based":[184],"CLMs,":[185],"predicting":[187],"aqueous":[188],"solubility":[189],"molecules":[191,224],"adverse":[193],"reactions,":[195],"while":[196],"producing":[197],"comparable":[198],"results":[199],"remaining":[202],"We":[204,229],"also":[205],"visualized":[206],"learned":[209],"by":[210],"dimensionality":[213],"reduction,":[214],"indicated":[216],"even":[218],"can":[222],"discriminate":[223],"differing":[226],"structural":[227],"properties.":[228],"shared":[230],"programmatic":[234],"tool,":[235],"together":[236],"its":[238],"datasets":[239],"models":[242],"at":[243],"https://github.com/HUBioDataLab/SELFormer":[244],".":[245],"Overall,":[246],"our":[247],"demonstrates":[249],"benefit":[251],"using":[253],"SELFIES":[255],"context":[259],"modeling":[263],"opens":[265],"up":[266],"new":[267],"possibilities":[268],"design":[271],"novel":[275],"candidates":[277],"desired":[279],"features.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}