{"id":"https://openalex.org/W4206526645","doi":"https://doi.org/10.1109/bibm52615.2021.9669668","title":"MolBit: De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem","display_name":"MolBit: De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4206526645","doi":"https://doi.org/10.1109/bibm52615.2021.9669668"},"language":"en","primary_location":{"id":"doi:10.1109/bibm52615.2021.9669668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669668","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5064308519","display_name":"Jonghwan Choi","orcid":"https://orcid.org/0000-0002-8429-4135"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonghwan Choi","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Seoul, Republic of Korea","UBLBio Corporation, Suwon, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"UBLBio Corporation, Suwon, Gyeonggi-do, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102777941","display_name":"Sangmin Seo","orcid":"https://orcid.org/0000-0003-4883-3987"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Seo","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Seoul, Republic of Korea","UBLBio Corporation, Suwon, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"UBLBio Corporation, Suwon, Gyeonggi-do, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103061208","display_name":"Jinuk Park","orcid":"https://orcid.org/0000-0003-0424-8225"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinuk Park","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100322270","display_name":"Sanghyun Park","orcid":"https://orcid.org/0000-0002-5196-6193"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyun Park","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24798155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"364","last_page":"367"},"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":0.98089998960495,"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":0.9743000268936157,"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/autoencoder","display_name":"Autoencoder","score":0.7261658310890198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6661999225616455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365177989006042},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4994833469390869},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.44093117117881775},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3575782775878906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3285130262374878},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27367809414863586}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7261658310890198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661999225616455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365177989006042},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4994833469390869},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.44093117117881775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3575782775878906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3285130262374878},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27367809414863586}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm52615.2021.9669668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669668","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1757990252","https://openalex.org/W1959608418","https://openalex.org/W2023818227","https://openalex.org/W2047094503","https://openalex.org/W2529996553","https://openalex.org/W2547875792","https://openalex.org/W2578240541","https://openalex.org/W2786565076","https://openalex.org/W2786722833","https://openalex.org/W2900090807","https://openalex.org/W2910135751","https://openalex.org/W2951670304","https://openalex.org/W2963676163","https://openalex.org/W2966574105","https://openalex.org/W2971690404","https://openalex.org/W3116865743","https://openalex.org/W6640963894","https://openalex.org/W6729448088","https://openalex.org/W6733974131","https://openalex.org/W6747927160","https://openalex.org/W6748188831","https://openalex.org/W6758151150","https://openalex.org/W6763918015","https://openalex.org/W6766364717"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000","https://openalex.org/W3008584592","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Deep":[0],"generative":[1,83],"models":[2,111],"for":[3],"molecular":[4,21,31,74,90],"generation":[5],"have":[6,38],"accelerated":[7],"the":[8,97,101,107],"development":[9],"of":[10,41],"de":[11],"novo":[12],"drug":[13,35,109],"design":[14,36,110],"by":[15],"introducing":[16],"how":[17],"to":[18,54],"generate":[19,55],"novel":[20],"structures":[22],"expressed":[23],"in":[24,67],"simplified":[25],"molecular-input":[26],"line-entry":[27],"system":[28],"(SMILES)":[29],"or":[30],"graph":[32],"formats.":[33],"Numerous":[34],"studies":[37],"proposed":[39,80,98],"combinations":[40],"variational":[42],"autoencoder":[43],"(VAE)":[44],"and":[45,86,105],"autoregressive":[46],"generators":[47],"such":[48],"as":[49],"recurrent":[50],"neural":[51],"networks":[52],"(RNNs)":[53],"SMILES":[56],"strings.":[57],"However,":[58],"RNN-VAE":[59],"has":[60],"one":[61],"notorious":[62],"issue,":[63],"called":[64],"posterior":[65,102],"collapse,":[66],"which":[68],"different":[69],"latent":[70],"vectors":[71],"produce":[72],"indistinguishable":[73],"distributions.":[75],"In":[76],"this":[77],"study,":[78],"we":[79],"a":[81,87],"Gumbel-Softmax-based":[82],"model,":[84],"MolBit,":[85],"genetic":[88],"algorithm-based":[89],"property":[91],"optimization":[92],"method.":[93],"We":[94],"confirmed":[95],"that":[96],"model":[99],"avoided":[100],"collapse":[103],"problem":[104],"outperformed":[106],"existing":[108],"with":[112],"SMILES.":[113]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}