{"id":"https://openalex.org/W3164193774","doi":"https://doi.org/10.1021/acs.jcim.0c01226","title":"Automated Generation of Novel Fragments Using Screening Data, a Dual SMILES Autoencoder, Transfer Learning and Syntax Correction","display_name":"Automated Generation of Novel Fragments Using Screening Data, a Dual SMILES Autoencoder, Transfer Learning and Syntax Correction","publication_year":2021,"publication_date":"2021-05-24","ids":{"openalex":"https://openalex.org/W3164193774","doi":"https://doi.org/10.1021/acs.jcim.0c01226","mag":"3164193774","pmid":"https://pubmed.ncbi.nlm.nih.gov/34029470"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c01226","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01226","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028781806","display_name":"Alan Bilsland","orcid":"https://orcid.org/0000-0003-0957-3908"},"institutions":[{"id":"https://openalex.org/I4210143228","display_name":"Cancer Research UK Scotland Institute","ror":"https://ror.org/03pv69j64","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210143228"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alan E. Bilsland","raw_affiliation_strings":["Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0957-3908","affiliations":[{"raw_affiliation_string":"Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K","institution_ids":["https://openalex.org/I4210143228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057251114","display_name":"Kirsten McAulay","orcid":"https://orcid.org/0000-0003-1864-7665"},"institutions":[{"id":"https://openalex.org/I4210143228","display_name":"Cancer Research UK Scotland Institute","ror":"https://ror.org/03pv69j64","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210143228"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kirsten McAulay","raw_affiliation_strings":["Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K","institution_ids":["https://openalex.org/I4210143228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102186003","display_name":"Ryan West","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143228","display_name":"Cancer Research UK Scotland Institute","ror":"https://ror.org/03pv69j64","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210143228"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ryan West","raw_affiliation_strings":["Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K","institution_ids":["https://openalex.org/I4210143228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091631038","display_name":"Angelo Pugliese","orcid":"https://orcid.org/0000-0002-9472-7440"},"institutions":[{"id":"https://openalex.org/I2801443577","display_name":"NHS Lanarkshire","ror":"https://ror.org/049prb569","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2801443577"]},{"id":"https://openalex.org/I4210143228","display_name":"Cancer Research UK Scotland Institute","ror":"https://ror.org/03pv69j64","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210143228"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Angelo Pugliese","raw_affiliation_strings":["Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K","BioAscent Discovery Ltd., Bo\u2019Ness Road, Newhouse, Lanarkshire ML1 5UH, U.K","BioAscent Discovery Ltd., Bo'Ness Road, Newhouse, Lanarkshire ML1 5UH, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K","institution_ids":["https://openalex.org/I4210143228"]},{"raw_affiliation_string":"BioAscent Discovery Ltd., Bo\u2019Ness Road, Newhouse, Lanarkshire ML1 5UH, U.K","institution_ids":["https://openalex.org/I2801443577"]},{"raw_affiliation_string":"BioAscent Discovery Ltd., Bo'Ness Road, Newhouse, Lanarkshire ML1 5UH, U.K","institution_ids":["https://openalex.org/I2801443577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050835542","display_name":"Justin Bower","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143228","display_name":"Cancer Research UK Scotland Institute","ror":"https://ror.org/03pv69j64","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210143228"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Justin Bower","raw_affiliation_strings":["Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beatson Drug Discovery Unit, Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Bearsden, Glasgow, G61 1BD, U.K","institution_ids":["https://openalex.org/I4210143228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091631038"],"corresponding_institution_ids":["https://openalex.org/I2801443577","https://openalex.org/I4210143228"],"apc_list":null,"apc_paid":null,"fwci":1.3011,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.78110753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"61","issue":"6","first_page":"2547","last_page":"2559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9775000214576721,"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":0.9775000214576721,"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/T10028","display_name":"Topic Modeling","score":0.9623000025749207,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9592999815940857,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.9113003015518188},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6954531669616699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682651042938232},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.629157304763794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6169531941413879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5447895526885986},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5240134000778198},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4133487939834595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3392106294631958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3300573229789734},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3048909306526184},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10179486870765686}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9113003015518188},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6954531669616699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682651042938232},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.629157304763794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169531941413879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5447895526885986},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5240134000778198},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4133487939834595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3392106294631958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3300573229789734},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3048909306526184},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10179486870765686},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.0c01226","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01226","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:34029470","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34029470","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,"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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4816731202","display_name":null,"funder_award_id":"17096","funder_id":"https://openalex.org/F4320319985","funder_display_name":"Cancer Research UK"},{"id":"https://openalex.org/G8367758090","display_name":null,"funder_award_id":"A17096","funder_id":"https://openalex.org/F4320319985","funder_display_name":"Cancer Research UK"},{"id":"https://openalex.org/G8488597180","display_name":null,"funder_award_id":"A17196","funder_id":"https://openalex.org/F4320319985","funder_display_name":"Cancer Research UK"}],"funders":[{"id":"https://openalex.org/F4320319985","display_name":"Cancer Research UK","ror":"https://ror.org/054225q67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1944091105","https://openalex.org/W1975147762","https://openalex.org/W1982393730","https://openalex.org/W1991198394","https://openalex.org/W2008525757","https://openalex.org/W2017254234","https://openalex.org/W2042126044","https://openalex.org/W2043919191","https://openalex.org/W2060531713","https://openalex.org/W2064675550","https://openalex.org/W2074274985","https://openalex.org/W2089656772","https://openalex.org/W2101234009","https://openalex.org/W2110485445","https://openalex.org/W2114704115","https://openalex.org/W2127073449","https://openalex.org/W2146674790","https://openalex.org/W2152195021","https://openalex.org/W2157844372","https://openalex.org/W2160592148","https://openalex.org/W2166478947","https://openalex.org/W2169303530","https://openalex.org/W2172216479","https://openalex.org/W2172242534","https://openalex.org/W2197008132","https://openalex.org/W2201502411","https://openalex.org/W2393800793","https://openalex.org/W2595840341","https://openalex.org/W2599307500","https://openalex.org/W2604850519","https://openalex.org/W2610148085","https://openalex.org/W2622206241","https://openalex.org/W2773987374","https://openalex.org/W2885195348","https://openalex.org/W2886791556","https://openalex.org/W2896646425","https://openalex.org/W2900694120","https://openalex.org/W2916045588","https://openalex.org/W2922290491","https://openalex.org/W2925830236","https://openalex.org/W2945551948","https://openalex.org/W2949986955","https://openalex.org/W2953128081","https://openalex.org/W2956961449","https://openalex.org/W2971690404","https://openalex.org/W2989615256","https://openalex.org/W2990739655","https://openalex.org/W2992586577","https://openalex.org/W2994715302","https://openalex.org/W3003906593","https://openalex.org/W3030068589","https://openalex.org/W3042595256","https://openalex.org/W3100751385"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Fragment-based":[0],"hit":[1],"identification":[2],"(FBHI)":[3],"allows":[4],"proportionately":[5],"greater":[6],"coverage":[7],"of":[8,87,109,122,195,217,250,279],"chemical":[9,33,152],"space":[10,108],"using":[11,130,139,174],"fewer":[12],"molecules":[13,115],"than":[14],"traditional":[15],"high-throughput":[16],"screening":[17,182],"approaches.":[18],"However,":[19],"effectively":[20],"exploiting":[21],"this":[22,196],"advantage":[23],"is":[24,101,245],"highly":[25],"dependent":[26],"on":[27],"the":[28,107,166,193,266,272],"library":[29,79,278],"design.":[30,80],"Solubility,":[31],"stability,":[32],"complexity,":[34],"chemical/shape":[35],"diversity,":[36],"and":[37,47,56,72,89,95,151,228,260],"synthetic":[38,226],"tractability":[39],"for":[40,54,77,120],"fragment":[41,78,159,231],"elaboration":[42],"are":[43,83,263],"all":[44],"critical":[45],"aspects,":[46],"molecule":[48],"design":[49,70],"remains":[50],"a":[51,131,172,185,215,229,251,277],"time-consuming":[52],"task":[53],"computational":[55],"medicinal":[57],"chemists.":[58],"Artificial":[59],"neural":[60,84,133],"networks":[61,85],"have":[62],"attracted":[63],"considerable":[64],"attention":[65],"in":[66,158,257],"automated":[67],"de":[68],"novo":[69],"applications":[71],"could":[73],"also":[74],"prove":[75],"useful":[76],"Chemical":[81],"autoencoders":[82],"consisting":[86],"encoder":[88],"decoder":[90,100,168],"parts,":[91],"which":[92,136,258],"respectively":[93],"compress":[94],"decompress":[96],"molecular":[97],"representations.":[98],"The":[99,205],"applied":[102,162],"to":[103,112,146,165,170,199,275],"samples":[104],"drawn":[105],"from":[106,143,180],"compressed":[110],"representations":[111],"generate":[113,276],"novel":[114,280],"that":[116,242],"can":[117],"be":[118],"scored":[119],"properties":[121,218],"interest.":[123],"Here,":[124],"we":[125,161,191,234,240,270],"report":[126],"an":[127,200],"autoencoder":[128],"model":[129,198,207,274],"recurrent":[132],"network":[134],"architecture,":[135],"was":[137],"trained":[138],"486,565":[140],"fragments":[141,178],"curated":[142],"commercial":[144],"sources,":[145],"simultaneously":[147],"reconstruct":[148],"both":[149],"SMILES":[150,203,210,262],"fingerprints.":[153],"To":[154],"explore":[155],"its":[156],"utility":[157],"design,":[160],"transfer":[163],"learning":[164],"fingerprint":[167],"layers":[169],"train":[171],"classifier":[173],"66":[175],"frequent":[176],"hitter":[177],"identified":[179],"our":[181],"campaigns.":[183],"Using":[184],"particle":[186],"swarm":[187],"optimization":[188],"sampling":[189],"approach,":[190],"compare":[192],"performance":[194,244],"\u201cdual\u201d":[197],"architecture":[201],"encoding":[202],"only.":[204],"dual":[206],"produced":[208],"valid":[209],"with":[211],"improved":[212],"features,":[213],"considering":[214],"range":[216],"including":[219],"aromatic":[220],"ring":[221],"counts,":[222],"heavy":[223],"atom":[224],"count,":[225],"accessibility,":[227],"new":[230],"complexity":[232],"score":[233],"term":[235],"Feature":[236],"Complexity":[237],"(FeCo).":[238],"Additionally,":[239],"demonstrate":[241],"generative":[243],"further":[246],"enhanced":[247],"by":[248],"use":[249],"simple":[252],"syntax-correction":[253],"procedure":[254],"during":[255],"training,":[256],"invalid":[259],"undesirable":[261],"spiked":[264],"into":[265],"training":[267],"set.":[268],"Finally,":[269],"used":[271],"syntax-corrected":[273],"candidate":[281],"privileged":[282],"fragments.":[283]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}