{"id":"https://openalex.org/W3121462455","doi":"https://doi.org/10.1109/bibm49941.2020.9313317","title":"Generating Novel Compounds Targeting SARS-CoV-2 Main Protease Based on Imbalanced Dataset","display_name":"Generating Novel Compounds Targeting SARS-CoV-2 Main Protease Based on Imbalanced Dataset","publication_year":2020,"publication_date":"2020-12-16","ids":{"openalex":"https://openalex.org/W3121462455","doi":"https://doi.org/10.1109/bibm49941.2020.9313317","mag":"3121462455"},"language":"en","primary_location":{"id":"doi:10.1109/bibm49941.2020.9313317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101704998","display_name":"Fan Hu","orcid":"https://orcid.org/0000-0003-0191-1300"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Hu","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086386273","display_name":"Dongqi Wang","orcid":"https://orcid.org/0000-0001-9415-1173"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqi Wang","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027243959","display_name":"Yishen Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yishen Hu","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","University of Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437174","display_name":"Jiaxin Jiang","orcid":"https://orcid.org/0000-0002-4065-7627"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Jiang","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080862674","display_name":"Peng Yin","orcid":"https://orcid.org/0000-0003-2407-4074"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yin","raw_affiliation_strings":["Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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":0.9994999766349792,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9944999814033508,"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/chemical-space","display_name":"Chemical space","score":0.8356324434280396},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.6103876829147339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6017078161239624},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4821314811706543},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.471581369638443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45027536153793335},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4492255747318268},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4376446604728699},{"id":"https://openalex.org/keywords/protease","display_name":"Protease","score":0.4225926101207733},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.26405227184295654},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.23833370208740234},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2171967625617981},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.1216173768043518},{"id":"https://openalex.org/keywords/enzyme","display_name":"Enzyme","score":0.09818261861801147}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.8356324434280396},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.6103876829147339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017078161239624},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4821314811706543},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.471581369638443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45027536153793335},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4492255747318268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4376446604728699},{"id":"https://openalex.org/C2776714187","wikidata":"https://www.wikidata.org/wiki/Q212410","display_name":"Protease","level":3,"score":0.4225926101207733},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.26405227184295654},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.23833370208740234},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2171967625617981},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.1216173768043518},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.09818261861801147},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm49941.2020.9313317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G3504427552","display_name":null,"funder_award_id":"11801542","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2034549041","https://openalex.org/W2066273100","https://openalex.org/W2160592148","https://openalex.org/W2578240541","https://openalex.org/W2618625858","https://openalex.org/W2900090807","https://openalex.org/W2963403868","https://openalex.org/W2971690404","https://openalex.org/W3009609618","https://openalex.org/W3012379316","https://openalex.org/W3018023298","https://openalex.org/W3037682562","https://openalex.org/W3098269892","https://openalex.org/W4230556746","https://openalex.org/W4241677786","https://openalex.org/W4281570112","https://openalex.org/W4289237578","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2973074952","https://openalex.org/W2594328795","https://openalex.org/W3183930479","https://openalex.org/W4320732452","https://openalex.org/W135095951","https://openalex.org/W3199987505","https://openalex.org/W4385760073","https://openalex.org/W4286980196","https://openalex.org/W2600435468","https://openalex.org/W2324927567"],"abstract_inverted_index":{"The":[0],"de":[1],"novo":[2],"drug":[3,11],"design":[4,27],"plays":[5],"an":[6,88],"important":[7],"role":[8],"in":[9,118,183],"the":[10,26,42,60,64,72,100,104,114,157,160],"discovery.":[12],"Recently":[13],"deep":[14],"learning":[15],"based":[16],"method":[17],"has":[18],"been":[19,181],"popular":[20],"as":[21,169,171],"a":[22,129],"promising":[23],"approach":[24],"for":[25,145,156],"of":[28,53,66,77,124,131,148,175],"novel":[29,93,132],"drugs":[30],"with":[31,164],"desirable":[32,165],"properties.":[33,139],"However,":[34],"conventional":[35],"target-specific":[36],"generative":[37,78],"models":[38],"mainly":[39],"concentrate":[40],"on":[41,99,113],"known":[43,54],"inhibitors":[44,55,177],"and":[45,69,103,135],"thus":[46],"produce":[47],"similar":[48],"molecules.":[49],"And":[50],"these":[51],"derivatives":[52],"are":[56,167],"probably":[57],"negative":[58],"against":[59],"same":[61],"target.":[62],"Considering":[63],"cost":[65],"chemical":[67,154],"synthesis":[68],"experimental":[70],"validation,":[71],"low":[73],"false":[74],"positive":[75,123,149,162],"rate":[76],"molecules":[79,150],"is":[80],"very":[81],"important.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,127,141],"propose":[87],"efficient":[89],"pipeline":[90],"to":[91,151],"generate":[92],"SARS-CoV-2":[94],"3C-like":[95],"protease":[96],"inhibitors.":[97],"Based":[98],"GPT2":[101],"generator":[102],"well":[105,170],"performing":[106],"multi-task":[107],"predictor":[108],"which":[109,178],"achieves":[110],"high":[111],"precision":[112],"highly":[115],"imbalanced":[116],"3CL":[117,176],"vitro":[119],"screening":[120],"dataset":[121],"(650":[122],"297,467":[125],"molecules),":[126],"acquired":[128],"number":[130],"3CL-target":[133],"compounds":[134,163],"analyzed":[136],"their":[137,172],"molecular":[138],"Moreover,":[140],"applied":[142],"randomized":[143],"SMILES":[144],"data":[146],"augmentation":[147],"create":[152],"larger":[153],"space":[155],"generator.":[158],"Finally,":[159],"selected":[161],"properties":[166],"exhibited,":[168],"nearest":[173],"neighbors":[174],"have":[179],"already":[180],"verified":[182],"vitro.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}