{"id":"https://openalex.org/W4360604754","doi":"https://doi.org/10.1109/icaiic57133.2023.10067040","title":"Learning the Protein Language Model of SARS-CoV-2 Spike Proteins","display_name":"Learning the Protein Language Model of SARS-CoV-2 Spike Proteins","publication_year":2023,"publication_date":"2023-02-20","ids":{"openalex":"https://openalex.org/W4360604754","doi":"https://doi.org/10.1109/icaiic57133.2023.10067040"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic57133.2023.10067040","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icaiic57133.2023.10067040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5075978428","display_name":"Paul Vincent Llanes","orcid":null},"institutions":[{"id":"https://openalex.org/I5791819","display_name":"University of the Philippines Manila","ror":"https://ror.org/01rrczv41","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I5791819"]}],"countries":["PH"],"is_corresponding":true,"raw_author_name":"Paul Vincent Llanes","raw_affiliation_strings":["University of the Philippines Manila,Department of Physical Sciences and Mathematics,Manila,Philippines","Department of Physical Sciences and Mathematics, University of the Philippines Manila, Manila, Philippines"],"affiliations":[{"raw_affiliation_string":"University of the Philippines Manila,Department of Physical Sciences and Mathematics,Manila,Philippines","institution_ids":["https://openalex.org/I5791819"]},{"raw_affiliation_string":"Department of Physical Sciences and Mathematics, University of the Philippines Manila, Manila, Philippines","institution_ids":["https://openalex.org/I5791819"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086938101","display_name":"Geoffrey A. Solano","orcid":"https://orcid.org/0000-0002-4223-1355"},"institutions":[{"id":"https://openalex.org/I5791819","display_name":"University of the Philippines Manila","ror":"https://ror.org/01rrczv41","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I5791819"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Geoffrey Solano","raw_affiliation_strings":["University of the Philippines Manila,Department of Physical Sciences and Mathematics,Manila,Philippines","Department of Physical Sciences and Mathematics, University of the Philippines Manila, Manila, Philippines"],"affiliations":[{"raw_affiliation_string":"University of the Philippines Manila,Department of Physical Sciences and Mathematics,Manila,Philippines","institution_ids":["https://openalex.org/I5791819"]},{"raw_affiliation_string":"Department of Physical Sciences and Mathematics, University of the Philippines Manila, Manila, Philippines","institution_ids":["https://openalex.org/I5791819"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086119076","display_name":"Marc Jermaine Pontiveros","orcid":"https://orcid.org/0000-0002-0986-6236"},"institutions":[{"id":"https://openalex.org/I87074743","display_name":"University of the Philippines Diliman","ror":"https://ror.org/03tbh6y23","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934","https://openalex.org/I87074743"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Marc Jermaine Pontiveros","raw_affiliation_strings":["University of the Philippines Diliman,Department of Computer Science,Quezon City,Philippines","Department of Computer Science, University of the Philippines Diliman, Quezon City, Philippines"],"affiliations":[{"raw_affiliation_string":"University of the Philippines Diliman,Department of Computer Science,Quezon City,Philippines","institution_ids":["https://openalex.org/I87074743"]},{"raw_affiliation_string":"Department of Computer Science, University of the Philippines Diliman, Quezon City, Philippines","institution_ids":["https://openalex.org/I87074743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075978428"],"corresponding_institution_ids":["https://openalex.org/I5791819"],"apc_list":null,"apc_paid":null,"fwci":0.3185,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62355045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9990000128746033,"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/T10118","display_name":"SARS-CoV-2 and COVID-19 Research","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9886000156402588,"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/spike","display_name":"Spike (software development)","score":0.7316553592681885},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5545660853385925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5488220453262329},{"id":"https://openalex.org/keywords/spike-protein","display_name":"Spike Protein","score":0.5301086902618408},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4995079040527344},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.4665405750274658},{"id":"https://openalex.org/keywords/severe-acute-respiratory-syndrome-coronavirus-2","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","score":0.456829309463501},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.43167099356651306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.424618661403656},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.34645578265190125},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34295353293418884},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.28058308362960815},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.23718386888504028},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.22758349776268005},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.12395912408828735}],"concepts":[{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.7316553592681885},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5545660853385925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5488220453262329},{"id":"https://openalex.org/C2909509916","wikidata":"https://www.wikidata.org/wiki/Q22329850","display_name":"Spike Protein","level":5,"score":0.5301086902618408},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4995079040527344},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.4665405750274658},{"id":"https://openalex.org/C3007834351","wikidata":"https://www.wikidata.org/wiki/Q82069695","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","level":5,"score":0.456829309463501},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.43167099356651306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424618661403656},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.34645578265190125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34295353293418884},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28058308362960815},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.23718386888504028},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.22758349776268005},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.12395912408828735},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic57133.2023.10067040","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icaiic57133.2023.10067040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2897249806","https://openalex.org/W2995514860","https://openalex.org/W3010387158","https://openalex.org/W3037888463","https://openalex.org/W3104722250","https://openalex.org/W3106188259","https://openalex.org/W3121000782","https://openalex.org/W3144701084","https://openalex.org/W3179206042","https://openalex.org/W3198971816","https://openalex.org/W4225494479","https://openalex.org/W4287724045"],"related_works":["https://openalex.org/W3135501652","https://openalex.org/W3207585454","https://openalex.org/W4243078506","https://openalex.org/W4372292428","https://openalex.org/W3017562527","https://openalex.org/W4205815969","https://openalex.org/W3023726384","https://openalex.org/W3214817298","https://openalex.org/W4249069515","https://openalex.org/W4376630253"],"abstract_inverted_index":{"Ahstract-SARS-CoV-2":[0],"virus":[1,75],"has":[2,94],"long":[3],"been":[4,64],"evolving":[5],"posing":[6],"an":[7],"increased":[8,42],"risk":[9],"in":[10,20,44,51,147],"terms":[11,148],"of":[12,26,35,73,103,149,161,171,199,202],"infectivity":[13],"and":[14,55,71,139,152],"transmissibility":[15],"which":[16],"causes":[17],"greater":[18],"impact":[19],"communities":[21],"worldwide.":[22],"With":[23],"the":[24,36,45,68,74,95,99,124,128,135,156,159,200,203],"surge":[25],"collected":[27],"SARS-CoV-2":[28,104],"sequences,":[29],"studies":[30,179],"found":[31],"out":[32],"that":[33,93,185],"most":[34,77],"emerging":[37],"variants":[38,146],"are":[39,78,132,189],"linked":[40],"to":[41,66,84,97,142,191],"mutations":[43,169,175],"spike":[46,105,187],"(S)":[47],"protein":[48,100],"as":[49],"observed":[50,130],"Alpha,":[52],"Beta,":[53],"Gamma,":[54],"Delta":[56],"variants.":[57],"Multiple":[58],"approaches":[59],"on":[60,81,108,180],"genomic":[61],"surveillance":[62],"have":[63],"performed":[65],"monitor":[67,143],"mutational":[69],"status":[70],"spread":[72],"however":[76],"heavily":[79],"dependent":[80],"labels":[82],"attributed":[83],"these":[85],"sequences.":[86],"Hence,":[87],"this":[88],"study":[89],"features":[90],"a":[91,109,162],"system":[92,157],"capability":[96],"learn":[98,192],"language":[101],"model":[102],"proteins,":[106],"based":[107],"bidirectional":[110],"long-short":[111],"term":[112],"memory":[113],"(BiLSTM)":[114],"recurrent":[115],"neural":[116],"network,":[117],"using":[118,134],"sequence":[119,125,165,168],"data":[120],"alone.":[121],"Upon":[122],"obtaining":[123],"embedding":[126],"from":[127],"model,":[129],"clusters":[131],"generated":[133],"Leiden":[136],"clustering":[137],"algorithm":[138],"is":[140],"visualized":[141],"similarities":[144],"between":[145],"grammatical":[150],"probability":[151],"semantic":[153,183],"change.":[154],"Additionally,":[155],"measures":[158],"validity":[160],"user-generated":[163],"next-generation":[164],"capturing":[166],"potential":[167],"indicative":[170],"viral":[172,196],"escape,":[173],"particularly":[174],"by":[176],"substitutions.":[177],"Further":[178],"methods":[181],"uncovering":[182],"rules":[184],"govern":[186],"proteins":[188],"recommended":[190],"more":[193],"about":[194],"other":[195],"characteristics":[197],"conclusive":[198],"future":[201],"COVID-19":[204],"pandemic.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
