{"id":"https://openalex.org/W4393317648","doi":"https://doi.org/10.1038/s42256-024-00821-x","title":"Invalid SMILES are beneficial rather than detrimental to chemical language models","display_name":"Invalid SMILES are beneficial rather than detrimental to chemical language models","publication_year":2024,"publication_date":"2024-03-29","ids":{"openalex":"https://openalex.org/W4393317648","doi":"https://doi.org/10.1038/s42256-024-00821-x"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-024-00821-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00821-x","pdf_url":"https://www.nature.com/articles/s42256-024-00821-x.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s42256-024-00821-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045701956","display_name":"Michael A. Skinnider","orcid":"https://orcid.org/0000-0002-2168-1621"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210150094","display_name":"Ludwig Cancer Research","ror":"https://ror.org/05qdwtz81","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210150094"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael A. Skinnider","raw_affiliation_strings":["Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ, USA","Ludwig Institute for Cancer Research, Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Ludwig Institute for Cancer Research, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210150094","https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045701956"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210150094"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":{"value":9750,"currency":"EUR","value_usd":11690},"fwci":6.3471,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":{"value":0.9875466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"6","issue":"4","first_page":"437","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9896000027656555,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.909600019454956,"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":0.3813023567199707},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3777424097061157},{"id":"https://openalex.org/keywords/intensive-care-medicine","display_name":"Intensive care medicine","score":0.3474549651145935},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.33515065908432007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3813023567199707},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3777424097061157},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.3474549651145935},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.33515065908432007}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s42256-024-00821-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00821-x","pdf_url":"https://www.nature.com/articles/s42256-024-00821-x.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s42256-024-00821-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00821-x","pdf_url":"https://www.nature.com/articles/s42256-024-00821-x.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311496","display_name":"Ludwig Institute for Cancer Research","ror":"https://ror.org/05qdwtz81"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393317648.pdf"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W1934481644","https://openalex.org/W1980581986","https://openalex.org/W1988037271","https://openalex.org/W1992156271","https://openalex.org/W1998693213","https://openalex.org/W2017254234","https://openalex.org/W2027478081","https://openalex.org/W2033495141","https://openalex.org/W2035753075","https://openalex.org/W2060531713","https://openalex.org/W2061843861","https://openalex.org/W2064963922","https://openalex.org/W2066273100","https://openalex.org/W2070072705","https://openalex.org/W2077488126","https://openalex.org/W2110791536","https://openalex.org/W2153693853","https://openalex.org/W2529996553","https://openalex.org/W2578240541","https://openalex.org/W2604296437","https://openalex.org/W2777416523","https://openalex.org/W2784270883","https://openalex.org/W2786103815","https://openalex.org/W2786565076","https://openalex.org/W2803526748","https://openalex.org/W2887447356","https://openalex.org/W2897337442","https://openalex.org/W2900090807","https://openalex.org/W2900694120","https://openalex.org/W2907470641","https://openalex.org/W2914542247","https://openalex.org/W2925830236","https://openalex.org/W2945551948","https://openalex.org/W2953641781","https://openalex.org/W2963028280","https://openalex.org/W2971690404","https://openalex.org/W2989615256","https://openalex.org/W2994678679","https://openalex.org/W3009321976","https://openalex.org/W3011286504","https://openalex.org/W3036527662","https://openalex.org/W3043461363","https://openalex.org/W3045928028","https://openalex.org/W3094686696","https://openalex.org/W3099414221","https://openalex.org/W3111676828","https://openalex.org/W3113447514","https://openalex.org/W3116865743","https://openalex.org/W3118695441","https://openalex.org/W3127493072","https://openalex.org/W3147983081","https://openalex.org/W3158331815","https://openalex.org/W3164193774","https://openalex.org/W3164743754","https://openalex.org/W3167734706","https://openalex.org/W3174777205","https://openalex.org/W3181468767","https://openalex.org/W3185391990","https://openalex.org/W3194841450","https://openalex.org/W3199356076","https://openalex.org/W3200806939","https://openalex.org/W3209056694","https://openalex.org/W4220798957","https://openalex.org/W4221145170","https://openalex.org/W4225876201","https://openalex.org/W4229590462","https://openalex.org/W4280562526","https://openalex.org/W4281619372","https://openalex.org/W4281658583","https://openalex.org/W4283270512","https://openalex.org/W4289549256","https://openalex.org/W4294285719","https://openalex.org/W4297951436","https://openalex.org/W4300961340","https://openalex.org/W4306986298","https://openalex.org/W4309047034","https://openalex.org/W4313703391","https://openalex.org/W4320728073","https://openalex.org/W4361989906","https://openalex.org/W4362503491","https://openalex.org/W4362589790","https://openalex.org/W4362664882","https://openalex.org/W4365442601","https://openalex.org/W4378802816","https://openalex.org/W4382808681","https://openalex.org/W4385245566","https://openalex.org/W4385406507","https://openalex.org/W4387169268","https://openalex.org/W4393592097","https://openalex.org/W6911306409"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3031052312","https://openalex.org/W4389568370","https://openalex.org/W3032375762","https://openalex.org/W1995515455","https://openalex.org/W2080531066","https://openalex.org/W3108674512","https://openalex.org/W1506200166","https://openalex.org/W1489783725","https://openalex.org/W2148612803"],"abstract_inverted_index":{"Abstract":[0],"Generative":[1],"machine":[2],"learning":[3,162],"models":[4,25,50,186],"have":[5,34,44,51],"attracted":[6],"intense":[7],"interest":[8],"for":[9],"their":[10],"ability":[11,112],"to":[12,37,55,77,93,113,124,166],"sample":[13],"novel":[14],"molecules":[15],"with":[16],"desired":[17],"chemical":[18,79,125,168,184],"or":[19,100],"biological":[20],"properties.":[21],"Among":[22],"these,":[23],"language":[24,126,146,185],"trained":[26],"on":[27],"SMILES":[28,64,99,179],"(Simplified":[29],"Molecular-Input":[30],"Line-Entry":[31],"System)":[32],"representations":[33],"been":[35,45],"subject":[36],"the":[38,63,95,111,131,145,157,174],"most":[39],"extensive":[40],"experimental":[41],"validation":[42],"and":[43,163,187],"widely":[46],"adopted.":[47],"However,":[48],"these":[49,171],"what":[52],"is":[53,117,121],"perceived":[54,82],"be":[56,75],"a":[57,78,86,137,181,191,194],"major":[58],"limitation:":[59],"some":[60],"fraction":[61],"of":[62,90,97,133,183],"strings":[65],"that":[66,72,110,130,140,177],"they":[67,73],"generate":[68],"are":[69,180],"invalid,":[70],"meaning":[71],"cannot":[74],"decoded":[76],"structure.":[80],"This":[81],"shortcoming":[83,182],"has":[84],"motivated":[85],"remarkably":[87],"broad":[88],"spectrum":[89],"work":[91],"designed":[92],"mitigate":[94],"generation":[96,132],"invalid":[98,115,134,178],"correct":[101],"them":[102,189],"post":[103],"hoc.":[104],"Here":[105],"I":[106,128],"provide":[107],"causal":[108],"evidence":[109],"produce":[114],"outputs":[116,135,152],"not":[118,193],"harmful":[119],"but":[120],"instead":[122],"beneficial":[123],"models.":[127],"show":[129],"provides":[136],"self-corrective":[138],"mechanism":[139],"filters":[141],"low-likelihood":[142],"samples":[143],"from":[144],"model":[147],"output.":[148],"Conversely,":[149],"enforcing":[150],"valid":[151],"produces":[153],"structural":[154],"biases":[155],"in":[156],"generated":[158],"molecules,":[159],"impairing":[160],"distribution":[161],"limiting":[164],"generalization":[165],"unseen":[167],"space.":[169],"Together,":[170],"results":[172],"refute":[173],"prevailing":[175],"assumption":[176],"reframe":[188],"as":[190],"feature,":[192],"bug.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}