{"id":"https://openalex.org/W4290502024","doi":"https://doi.org/10.3390/make4030034","title":"VLA-SMILES: Variable-Length-Array SMILES Descriptors in Neural Network-Based QSAR Modeling","display_name":"VLA-SMILES: Variable-Length-Array SMILES Descriptors in Neural Network-Based QSAR Modeling","publication_year":2022,"publication_date":"2022-08-05","ids":{"openalex":"https://openalex.org/W4290502024","doi":"https://doi.org/10.3390/make4030034"},"language":"en","primary_location":{"id":"doi:10.3390/make4030034","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4030034","pdf_url":"https://www.mdpi.com/2504-4990/4/3/34/pdf?version=1660896052","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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 and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/4/3/34/pdf?version=1660896052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064748174","display_name":"Antonina L. Nazarova","orcid":"https://orcid.org/0000-0002-8480-8861"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Antonina L. Nazarova","raw_affiliation_strings":["Department of Quantitative & Computational Biology, Bridge Institute, USC Michelson Center for Convergent Bioscience, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative & Computational Biology, Bridge Institute, USC Michelson Center for Convergent Bioscience, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087579275","display_name":"Aiichiro Nakano","orcid":"https://orcid.org/0000-0003-3228-3896"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aiichiro Nakano","raw_affiliation_strings":["Collaboratory of Advanced Computing and Simulations, Department of Computer Science, Department of Physics & Astronomy, Department of Quantitative & Computational Biology, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":"https://orcid.org/0000-0003-3228-3896","affiliations":[{"raw_affiliation_string":"Collaboratory of Advanced Computing and Simulations, Department of Computer Science, Department of Physics & Astronomy, Department of Quantitative & Computational Biology, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064748174","https://openalex.org/A5087579275"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1559},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1559},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11154701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"3","first_page":"715","last_page":"737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9649999737739563,"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8907322883605957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.785520076751709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6765274405479431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.656639575958252},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5670042634010315},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5415646433830261},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.49247226119041443},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4845229983329773},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4588582515716553},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.4437786340713501},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.431281715631485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.367147296667099},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.29466015100479126},{"id":"https://openalex.org/keywords/pharmacophore","display_name":"Pharmacophore","score":0.28025245666503906},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.11233001947402954},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10390311479568481}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8907322883605957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.785520076751709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6765274405479431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656639575958252},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5670042634010315},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5415646433830261},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.49247226119041443},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4845229983329773},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4588582515716553},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.4437786340713501},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.431281715631485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.367147296667099},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.29466015100479126},{"id":"https://openalex.org/C56173144","wikidata":"https://www.wikidata.org/wiki/Q1539893","display_name":"Pharmacophore","level":2,"score":0.28025245666503906},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.11233001947402954},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10390311479568481},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/make4030034","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4030034","pdf_url":"https://www.mdpi.com/2504-4990/4/3/34/pdf?version=1660896052","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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 and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0e392cdde6ff472fb19fc33ba1685f73","is_oa":true,"landing_page_url":"https://doaj.org/article/0e392cdde6ff472fb19fc33ba1685f73","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 4, Iss 3, Pp 715-737 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-4990/4/3/34/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/make4030034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction; Volume 4; Issue 3; Pages: 715-737","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/make4030034","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4030034","pdf_url":"https://www.mdpi.com/2504-4990/4/3/34/pdf?version=1660896052","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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 and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4290502024.pdf"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1571439140","https://openalex.org/W1973395347","https://openalex.org/W1975147762","https://openalex.org/W1981622697","https://openalex.org/W1984471054","https://openalex.org/W1988195734","https://openalex.org/W1992419399","https://openalex.org/W1996851544","https://openalex.org/W2000977257","https://openalex.org/W2007281089","https://openalex.org/W2014059083","https://openalex.org/W2014751046","https://openalex.org/W2017422910","https://openalex.org/W2019282798","https://openalex.org/W2030214786","https://openalex.org/W2033757486","https://openalex.org/W2034978228","https://openalex.org/W2081808304","https://openalex.org/W2087661061","https://openalex.org/W2087836750","https://openalex.org/W2091589454","https://openalex.org/W2143908786","https://openalex.org/W2144342206","https://openalex.org/W2155478691","https://openalex.org/W2172216479","https://openalex.org/W2294467502","https://openalex.org/W2314731117","https://openalex.org/W2500151196","https://openalex.org/W2578240541","https://openalex.org/W2589639338","https://openalex.org/W2766232747","https://openalex.org/W2789816271","https://openalex.org/W2793405960","https://openalex.org/W2895473117","https://openalex.org/W2900090807","https://openalex.org/W2901476322","https://openalex.org/W2914568473","https://openalex.org/W2920724574","https://openalex.org/W2937307539","https://openalex.org/W2940242941","https://openalex.org/W2952510283","https://openalex.org/W2963386266","https://openalex.org/W2987438138","https://openalex.org/W2988203096","https://openalex.org/W2999044305","https://openalex.org/W2999197824","https://openalex.org/W3009044824","https://openalex.org/W3009321976","https://openalex.org/W3013657235","https://openalex.org/W3022458398","https://openalex.org/W3023042104","https://openalex.org/W3043486744","https://openalex.org/W3045928028","https://openalex.org/W3049158333","https://openalex.org/W3087318293","https://openalex.org/W3090506617","https://openalex.org/W3092524006","https://openalex.org/W3093687066","https://openalex.org/W3095028680","https://openalex.org/W3106717751","https://openalex.org/W3113291402","https://openalex.org/W3120428435","https://openalex.org/W3131057326","https://openalex.org/W3138781613","https://openalex.org/W3153418077","https://openalex.org/W3156276249","https://openalex.org/W3165163721","https://openalex.org/W3176845041","https://openalex.org/W4229590462","https://openalex.org/W4232173398","https://openalex.org/W4233231723","https://openalex.org/W4244471710","https://openalex.org/W6643860709","https://openalex.org/W6750223540","https://openalex.org/W6781851075"],"related_works":["https://openalex.org/W4362464865","https://openalex.org/W2098840560","https://openalex.org/W4302604134","https://openalex.org/W2768880727","https://openalex.org/W2113146994","https://openalex.org/W2073081213","https://openalex.org/W2033669961","https://openalex.org/W2552368679","https://openalex.org/W2083497194","https://openalex.org/W1983510392"],"abstract_inverted_index":{"Machine":[0],"learning":[1,80,114,157],"represents":[2],"a":[3],"milestone":[4],"in":[5,57,152],"data-driven":[6],"research,":[7],"including":[8],"material":[9],"informatics,":[10],"robotics,":[11],"and":[12,21,27,111,147,199,235,268],"computer-aided":[13],"drug":[14],"discovery.":[15],"With":[16],"the":[17,64,75,94,122,126,134,138,155,161,167,177,180,191,200,212,221,224,230,240,255,258,279,285],"continuously":[18],"growing":[19],"virtual":[20],"synthetically":[22],"available":[23],"chemical":[24],"space,":[25],"efficient":[26],"robust":[28],"quantitative":[29,280],"structure\u2013activity":[30],"relationship":[31],"(QSAR)":[32],"methods":[33],"are":[34],"required":[35],"to":[36,73,91,274],"uncover":[37],"molecules":[38],"with":[39,83,104,154,160,179,289],"desired":[40],"properties.":[41],"Herein,":[42],"we":[43],"propose":[44],"variable-length-array":[45],"SMILES-based":[46],"(VLA-SMILES)":[47],"structural":[48,61,168],"descriptors":[49,54,88,142],"that":[50],"expand":[51],"conventional":[52],"SMILES":[53,130,141],"widely":[55],"used":[56,244,277],"machine":[58],"learning.":[59],"This":[60],"representation":[62,131],"extends":[63],"family":[65],"of":[66,77,96,150,194,203,214,223,229,257,263,282,284],"numerically":[67],"coded":[68],"SMILES,":[69,72],"particularly":[70],"binary":[71,129],"expedite":[74],"discovery":[76],"new":[78],"deep":[79],"QSAR":[81,97,215,264,287],"models":[82,98,205,288],"high":[84],"predictive":[85,123,145,201],"ability.":[86],"VLA-SMILES":[87,195,208,249,290],"were":[89,209,272],"shown":[90],"speed":[92],"up":[93],"training":[95,151],"based":[99,165,184,206,238],"on":[100,166,185,207,239],"multilayer":[101],"perceptron":[102],"(MLP)":[103],"optimized":[105],"backpropagation":[106],"(ATransformedBP),":[107],"resilient":[108],"propagation":[109],"(iRPROP\u2012),":[110],"Adam":[112],"optimization":[113],"algorithms":[115],"featuring":[116],"rational":[117],"train\u2013test":[118,163],"splitting,":[119],"while":[120],"improving":[121],"ability":[124,146,202],"toward":[125],"more":[127,174],"compute-intensive":[128],"format.":[132],"All":[133],"tested":[135],"MLPs":[136],"under":[137],"same":[139],"length-array-based":[140],"showed":[143],"similar":[144],"convergence":[148],"rate":[149],"combination":[153],"considered":[156],"procedures.":[158],"Validation":[159],"Kennard\u2013Stone":[162],"splitting":[164],"descriptor":[169],"similarity":[170],"metrics":[171,189],"was":[172,243],"found":[173,273],"effective":[175],"than":[176],"partitioning":[178],"ranking":[181],"by":[182],"activity":[183,187],"biological":[186],"values":[188],"for":[190,245,278],"entire":[192],"set":[193],"featured":[196,250],"QSAR.":[197],"Robustness":[198],"MLP":[204],"assessed":[210],"via":[211],"method":[213,222],"parametric":[216,265],"model":[217,266],"validation.":[218],"In":[219],"addition,":[220],"statistical":[225,269],"H0":[226],"hypothesis":[227,270],"testing":[228,259,271],"linear":[231],"regression":[232],"between":[233],"real":[234],"observed":[236],"activities":[237],"F2,n\u22122":[241],"-criteria":[242],"predictability":[246],"estimation":[247],"among":[248],"QSAR-MLPs":[251],"(with":[252],"n":[253],"being":[254],"volume":[256],"set).":[260],"Both":[261],"approaches":[262],"validation":[267],"correlate":[275],"when":[276],"evaluation":[281],"predictabilities":[283],"designed":[286],"descriptors.":[291]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}