{"id":"https://openalex.org/W3194282770","doi":"https://doi.org/10.1021/acs.jcim.1c00584","title":"Predicting Antimalarial Activity in Natural Products Using Pretrained Bidirectional Encoder Representations from Transformers","display_name":"Predicting Antimalarial Activity in Natural Products Using Pretrained Bidirectional Encoder Representations from Transformers","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W3194282770","doi":"https://doi.org/10.1021/acs.jcim.1c00584","mag":"3194282770","pmid":"https://pubmed.ncbi.nlm.nih.gov/36373285"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c00584","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00584","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":"review","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/A5078787020","display_name":"Thanh\u2010Hoang Nguyen\u2010Vo","orcid":"https://orcid.org/0000-0003-0006-5245"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Thanh-Hoang Nguyen-Vo","raw_affiliation_strings":["School of Mathematics and Statistics, Victoria University of Wellington, Kelburn Parade, Wellington 6140, New Zealand"],"raw_orcid":"https://orcid.org/0000-0003-0006-5245","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Victoria University of Wellington, Kelburn Parade, Wellington 6140, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001831676","display_name":"Quang H. Trinh","orcid":"https://orcid.org/0000-0001-9724-8405"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I228151691","display_name":"Ho Chi Minh City International University","ror":"https://ror.org/003szmg30","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I228151691"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quang H. Trinh","raw_affiliation_strings":["Computational Biology Center, International University\u2212VNU HCMC, Ho Chi Minh City 700000, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-9724-8405","affiliations":[{"raw_affiliation_string":"Computational Biology Center, International University\u2212VNU HCMC, Ho Chi Minh City 700000, Vietnam","institution_ids":["https://openalex.org/I228151691","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046435","display_name":"Loc Nguyen","orcid":"https://orcid.org/0000-0003-0561-6659"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I228151691","display_name":"Ho Chi Minh City International University","ror":"https://ror.org/003szmg30","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I228151691"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Loc Nguyen","raw_affiliation_strings":["Computational Biology Center, International University\u2212VNU HCMC, Ho Chi Minh City 700000, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-0561-6659","affiliations":[{"raw_affiliation_string":"Computational Biology Center, International University\u2212VNU HCMC, Ho Chi Minh City 700000, Vietnam","institution_ids":["https://openalex.org/I228151691","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048585011","display_name":"T. T. Trang","orcid":"https://orcid.org/0000-0002-1614-4661"},"institutions":[{"id":"https://openalex.org/I138377626","display_name":"Wellington Institute of Technology","ror":"https://ror.org/03ycgmc41","country_code":"NZ","type":"education","lineage":["https://openalex.org/I138377626","https://openalex.org/I4387152882"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Trang T. T. Do","raw_affiliation_strings":["School of Business and Information Technology, Wellington Institute of Technology, 21 Kensington Avenue, Lower Hutt 5012, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-1614-4661","affiliations":[{"raw_affiliation_string":"School of Business and Information Technology, Wellington Institute of Technology, 21 Kensington Avenue, Lower Hutt 5012, New Zealand","institution_ids":["https://openalex.org/I138377626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019412302","display_name":"Matthew Chin Heng Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Matthew Chin Heng Chua","raw_affiliation_strings":["Institute of Systems Science, National University of Singapore, 29 Heng Mui Keng Terrace, Singapore 119620, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5200-5079","affiliations":[{"raw_affiliation_string":"Institute of Systems Science, National University of Singapore, 29 Heng Mui Keng Terrace, Singapore 119620, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091142923","display_name":"Binh P. Nguyen","orcid":"https://orcid.org/0000-0001-6203-6664"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Binh P. Nguyen","raw_affiliation_strings":["School of Mathematics and Statistics, Victoria University of Wellington, Kelburn Parade, Wellington 6140, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-6203-6664","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Victoria University of Wellington, Kelburn Parade, Wellington 6140, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019412302","https://openalex.org/A5091142923"],"corresponding_institution_ids":["https://openalex.org/I165932596","https://openalex.org/I41156924"],"apc_list":null,"apc_paid":null,"fwci":3.044,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92329486,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"62","issue":"21","first_page":"5050","last_page":"5058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9995999932289124,"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":0.9995999932289124,"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/T10091","display_name":"Malaria Research and Control","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9926000237464905,"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":0.7012643218040466},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6199365258216858},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.610954761505127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6018239259719849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5969322919845581},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5826976895332336},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5501313209533691},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5244408249855042},{"id":"https://openalex.org/keywords/extreme-learning-machine","display_name":"Extreme learning machine","score":0.4701170027256012},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.45859044790267944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2288486659526825},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10192251205444336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012643218040466},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6199365258216858},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.610954761505127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6018239259719849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5969322919845581},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5826976895332336},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5501313209533691},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5244408249855042},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.4701170027256012},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.45859044790267944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2288486659526825},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10192251205444336},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000962","descriptor_name":"Antimalarials","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D000962","descriptor_name":"Antimalarials","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D000962","descriptor_name":"Antimalarials","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D000962","descriptor_name":"Antimalarials","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000962","descriptor_name":"Antimalarials","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000962","descriptor_name":"Antimalarials","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c00584","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00584","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:36373285","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36373285","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1930624869","https://openalex.org/W1967320885","https://openalex.org/W1988037271","https://openalex.org/W2027482274","https://openalex.org/W2031737517","https://openalex.org/W2031796122","https://openalex.org/W2036537237","https://openalex.org/W2038603712","https://openalex.org/W2057611763","https://openalex.org/W2064855181","https://openalex.org/W2096541451","https://openalex.org/W2127553917","https://openalex.org/W2132043145","https://openalex.org/W2139156287","https://openalex.org/W2148143831","https://openalex.org/W2295598076","https://openalex.org/W2328176404","https://openalex.org/W2492794003","https://openalex.org/W2510354901","https://openalex.org/W2569373158","https://openalex.org/W2590034108","https://openalex.org/W2626778328","https://openalex.org/W2751692355","https://openalex.org/W2766193612","https://openalex.org/W2777416523","https://openalex.org/W2790461033","https://openalex.org/W2893466074","https://openalex.org/W2894559996","https://openalex.org/W2911964244","https://openalex.org/W2920054351","https://openalex.org/W2940180668","https://openalex.org/W2943890584","https://openalex.org/W2945236467","https://openalex.org/W2949746867","https://openalex.org/W2963542333","https://openalex.org/W2973114758","https://openalex.org/W2986338705","https://openalex.org/W2997894756","https://openalex.org/W2997903277","https://openalex.org/W3047705148","https://openalex.org/W3085162807","https://openalex.org/W3087812080","https://openalex.org/W3089107717","https://openalex.org/W3102476541","https://openalex.org/W3164396614","https://openalex.org/W4212883601","https://openalex.org/W4232212282","https://openalex.org/W4238530616","https://openalex.org/W4239510810","https://openalex.org/W4249358576"],"related_works":["https://openalex.org/W2067443264","https://openalex.org/W31566076","https://openalex.org/W4297902562","https://openalex.org/W2741186499","https://openalex.org/W2073883415","https://openalex.org/W1950940422","https://openalex.org/W4283822356","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173"],"abstract_inverted_index":{"Malaria":[0],"is":[1,165,181],"a":[2,12,39,80],"threatening":[3],"disease":[4],"that":[5,134,163],"has":[6,11],"claimed":[7],"many":[8,24],"lives":[9],"and":[10,92,117,146,158],"high":[13],"prevalence":[14],"rate":[15],"annually.":[16],"Through":[17],"the":[18,138,143,170,173],"past":[19],"decade,":[20],"there":[21],"have":[22,44,68],"been":[23,46,69],"studies":[25],"to":[26,31,48,59,121,126,169,184],"uncover":[27],"effective":[28,51,167],"antimalarial":[29,54,61,128],"compounds":[30,43],"combat":[32],"this":[33,76,185],"disease.":[34],"Alongside":[35],"chemically":[36],"synthesized":[37],"chemicals,":[38],"number":[40],"of":[41,175],"natural":[42,64,129],"also":[45],"proven":[47],"be":[49,189],"as":[50],"in":[52,63,177],"their":[53],"properties.":[55],"Besides":[56],"experimental":[57],"approaches":[58],"investigate":[60],"activities":[62],"products,":[65],"computational":[66],"methods":[67,161],"developed":[70],"with":[71,100],"satisfactory":[72],"outcomes":[73],"obtained.":[74],"In":[75],"study,":[77],"we":[78],"propose":[79],"novel":[81],"molecular":[82,155,179],"encoding":[83,96,156],"scheme":[84,157],"based":[85],"on":[86],"Bidirectional":[87],"Encoder":[88],"Representations":[89],"from":[90],"Transformers":[91],"used":[93],"our":[94,153],"pretrained":[95],"model":[97],"called":[98],"NPBERT":[99,164],"four":[101],"machine":[102],"learning":[103],"algorithms,":[104],"including":[105],"k-Nearest":[106],"Neighbors":[107],"(k-NN),":[108],"Support":[109],"Vector":[110],"Machines":[111],"(SVM),":[112],"eXtreme":[113],"Gradient":[114],"Boosting":[115],"(XGB),":[116],"Random":[118],"Forest":[119],"(RF),":[120],"develop":[122],"various":[123],"prediction":[124],"models":[125,136],"identify":[127],"products.":[130],"The":[131],"results":[132],"show":[133],"SVM":[135],"are":[137],"best-performing":[139],"classifiers,":[140],"followed":[141],"by":[142],"XGB,":[144],"k-NN,":[145],"RF":[147],"models.":[148],"Additionally,":[149],"comparative":[150],"analysis":[151],"between":[152],"proposed":[154],"existing":[159],"state-of-the-art":[160],"indicates":[162],"more":[166],"compared":[168],"others.":[171],"Moreover,":[172],"deployment":[174],"transformers":[176],"constructing":[178],"encoders":[180],"not":[182],"limited":[183],"study":[186],"but":[187],"can":[188],"utilized":[190],"for":[191],"other":[192],"biomedical":[193],"applications.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}