{"id":"https://openalex.org/W3009321976","doi":"https://doi.org/10.1088/2632-2153/aba947","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","display_name":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","publication_year":2020,"publication_date":"2020-07-27","ids":{"openalex":"https://openalex.org/W3009321976","doi":"https://doi.org/10.1088/2632-2153/aba947","mag":"3009321976"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/aba947","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/aba947","pdf_url":null,"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":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/aba947","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mario Krenn","orcid":"https://orcid.org/0000-0003-1620-9207"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mario Krenn","raw_affiliation_strings":["Department of Chemistry, University of Toronto, Toronto, Canada","Department of Computer Science, University of Toronto, Toronto, Canada","Vector Institute for Artificial Intelligence, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1620-9207","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Florian H\u00e4se","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Florian H\u00e4se","raw_affiliation_strings":["Department of Chemistry and Chemical Biology, Harvard University, Cambridge, United States of America","Department of Chemistry, University of Toronto, Toronto, Canada","Department of Computer Science, University of Toronto, Toronto, Canada","Vector Institute for Artificial Intelligence, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Chemical Biology, Harvard University, Cambridge, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Chemistry, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":null,"display_name":"AkshatKumar Nigam","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"AkshatKumar Nigam","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pascal Friederich","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","DE"],"is_corresponding":false,"raw_author_name":"Pascal Friederich","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","Institute of Nanotechnology, Karlsruhe Institute of Technology, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Institute of Nanotechnology, Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alan Aspuru-Guzik","orcid":null},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Alan Aspuru-Guzik","raw_affiliation_strings":["Canadian Institute for Advanced Research (CIFAR) Senior Fellow, Toronto, Canada","Department of Chemistry, University of Toronto, Toronto, Canada","Department of Computer Science, University of Toronto, Toronto, Canada","Vector Institute for Artificial Intelligence, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canadian Institute for Advanced Research (CIFAR) Senior Fellow, Toronto, Canada","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Department of Chemistry, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I109736498","https://openalex.org/I185261750","https://openalex.org/I4210127509"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":19.7101,"has_fulltext":false,"cited_by_count":600,"citation_normalized_percentile":{"value":0.99798365,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"1","issue":"4","first_page":"045024","last_page":"045024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8888000249862671,"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":0.8888000249862671,"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":0.020099999383091927,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5390999913215637},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.3783000111579895},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3716999888420105},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.36719998717308044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370000243186951},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5271000266075134},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4674000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45210000872612},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36719998717308044},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2669000029563904}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1088/2632-2153/aba947","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/aba947","pdf_url":null,"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:arXiv.org:1905.13741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.13741","pdf_url":"https://arxiv.org/pdf/1905.13741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:38aefb59b152494cb40c565569412f4e","is_oa":false,"landing_page_url":"https://doaj.org/article/38aefb59b152494cb40c565569412f4e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 1, Iss 4, p 045024 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/aba947","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/aba947","pdf_url":null,"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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2025948031","https://openalex.org/W2080635178","https://openalex.org/W2110791536","https://openalex.org/W2114704115","https://openalex.org/W2119938189","https://openalex.org/W2244690429","https://openalex.org/W2347129741","https://openalex.org/W2527189750","https://openalex.org/W2529996553","https://openalex.org/W2748190745","https://openalex.org/W2792130717","https://openalex.org/W2883583109","https://openalex.org/W2884775584","https://openalex.org/W2891814056","https://openalex.org/W2906453878","https://openalex.org/W2908837618","https://openalex.org/W2914542247","https://openalex.org/W2945551948","https://openalex.org/W2977595407","https://openalex.org/W6640963894","https://openalex.org/W6738599175","https://openalex.org/W6744627333","https://openalex.org/W6748391871","https://openalex.org/W6752245542","https://openalex.org/W6768561264"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1,48,69],"discovery":[2],"of":[3,14,56,90,117,153,157,174,197,201],"novel":[4,28],"materials":[5],"and":[6,24,44,107,132,195],"functional":[7],"molecules":[8,118,178,188],"can":[9,135,141],"help":[10],"to":[11,26,95,128],"solve":[12,100],"some":[13],"society\u2019s":[15],"most":[16],"urgent":[17],"challenges,":[18],"ranging":[19],"from":[20],"efficient":[21],"energy":[22],"harvesting":[23],"storage":[25],"uncovering":[27],"pharmaceutical":[29],"drug":[30],"candidates.":[31],"Traditionally":[32],"matter":[33],"engineering\u2013generally":[34],"denoted":[35],"as":[36,186],"inverse":[37],"design\u2013was":[38],"based":[39,62],"massively":[40],"on":[41,63],"human":[42],"intuition":[43],"high-throughput":[45],"virtual":[46],"screening.":[47],"last":[49],"few":[50],"years":[51],"have":[52],"seen":[53],"the":[54,75,151,154,158,167,198,202],"emergence":[55],"significant":[57],"interest":[58],"in":[59,84,145],"computer-inspired":[60],"designs":[61],"evolutionary":[64],"or":[65],"deep":[66],"learning":[67,148],"methods.":[68],"major":[70],"challenge":[71],"here":[72],"is":[73,120,162],"that":[74,85],"standard":[76],"strings":[77,91],"molecular":[78],"representation":[79,116],"SMILES":[80],"shows":[81],"substantial":[82],"weaknesses":[83],"task":[86],"because":[87],"large":[88],"fractions":[89],"do":[92],"not":[93],"correspond":[94],"valid":[96,130],"molecules.":[97],"Here,":[98],"we":[99],"this":[101],"problem":[102],"at":[103],"a":[104,114,129,180],"fundamental":[105],"level":[106],"introduce":[108],"S":[109,124,133,139],"ELFIES":[110,125,134,140],"(SELF-referencIng":[111],"Embedded":[112],"Strings),":[113],"string-based":[115],"which":[119],"100%":[121],"robust.":[122],"Every":[123],"string":[126],"corresponds":[127],"molecule,":[131],"represent":[136],"every":[137],"molecule.":[138],"be":[142],"directly":[143],"applied":[144],"arbitrary":[146],"machine":[147],"models":[149],"without":[150],"adaptation":[152],"models;":[155],"each":[156],"generated":[159],"molecule":[160],"candidates":[161],"valid.":[163],"In":[164],"our":[165],"experiments,":[166],"model\u2019s":[168],"internal":[169,199],"memory":[170],"stores":[171],"two":[172],"orders":[173],"magnitude":[175],"more":[176],"diverse":[177],"than":[179],"similar":[181],"test":[182],"with":[183],"SMILES.":[184],"Furthermore,":[185],"all":[187],"are":[189],"valid,":[190],"it":[191],"allows":[192],"for":[193],"explanation":[194],"interpretation":[196],"working":[200],"generative":[203],"models.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":61},{"year":2025,"cited_by_count":145},{"year":2024,"cited_by_count":146},{"year":2023,"cited_by_count":101},{"year":2022,"cited_by_count":79},{"year":2021,"cited_by_count":51},{"year":2020,"cited_by_count":17}],"updated_date":"2026-07-07T14:30:12.667765","created_date":"2020-03-13T00:00:00"}