{"id":"https://openalex.org/W4409311222","doi":"https://doi.org/10.1109/tcbbio.2025.3559571","title":"BERTPVP: Identifying and Classifying Phage Virion Proteins Using Bidirectional Encoder Representations-Based Transformers","display_name":"BERTPVP: Identifying and Classifying Phage Virion Proteins Using Bidirectional Encoder Representations-Based Transformers","publication_year":2025,"publication_date":"2025-04-09","ids":{"openalex":"https://openalex.org/W4409311222","doi":"https://doi.org/10.1109/tcbbio.2025.3559571","pmid":"https://pubmed.ncbi.nlm.nih.gov/40811333"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2025.3559571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3559571","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","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/A5103127486","display_name":"Lijia Ma","orcid":"https://orcid.org/0000-0002-1201-8051"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijia Ma","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065479809","display_name":"Wenxiang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiang Zhou","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101854884","display_name":"Yuan Bai","orcid":"https://orcid.org/0000-0002-8468-8118"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuan Bai","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922757","display_name":"Min Fang","orcid":"https://orcid.org/0000-0002-8798-537X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Fang","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen, Shenzhen, China","Harbin Institute of Technology Shenzhen, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen, ShenZhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412749","display_name":"Minfeng Xiao","orcid":"https://orcid.org/0000-0002-0507-7352"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minfeng Xiao","raw_affiliation_strings":["BGI-Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I100135526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393871","display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103127486"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0626483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"1528","last_page":"1541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9855999946594238,"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":0.9855999946594238,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9153000116348267,"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/encoder","display_name":"Encoder","score":0.6318625211715698},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6245039701461792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.509879469871521},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.47313371300697327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.372826486825943},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3040326237678528},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2674640417098999},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15037918090820312},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05602836608886719},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05414938926696777}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6318625211715698},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6245039701461792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.509879469871521},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.47313371300697327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.372826486825943},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3040326237678528},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2674640417098999},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15037918090820312},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05602836608886719},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05414938926696777}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbbio.2025.3559571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3559571","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40811333","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40811333","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":"IEEE transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2215765088","display_name":null,"funder_award_id":"JCYJ20240813141416022","funder_id":"https://openalex.org/F4320316880","funder_display_name":"Natural Science Foundation of Shenzhen City"},{"id":"https://openalex.org/G287458316","display_name":null,"funder_award_id":"82304204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5023856971","display_name":null,"funder_award_id":"62173236","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7279309214","display_name":null,"funder_award_id":"62176164","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8411257915","display_name":null,"funder_award_id":"62203134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316880","display_name":"Natural Science Foundation of Shenzhen City","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W58165530","https://openalex.org/W1924689489","https://openalex.org/W1976978745","https://openalex.org/W1980571326","https://openalex.org/W2015452969","https://openalex.org/W2023026264","https://openalex.org/W2062848325","https://openalex.org/W2076048958","https://openalex.org/W2112796928","https://openalex.org/W2123978130","https://openalex.org/W2131871423","https://openalex.org/W2132083787","https://openalex.org/W2156125289","https://openalex.org/W2157825442","https://openalex.org/W2159277024","https://openalex.org/W2174377965","https://openalex.org/W2194775991","https://openalex.org/W2605018235","https://openalex.org/W2620760558","https://openalex.org/W2767986886","https://openalex.org/W2792246829","https://openalex.org/W2807988699","https://openalex.org/W2888329843","https://openalex.org/W2896457183","https://openalex.org/W2946417913","https://openalex.org/W2949342052","https://openalex.org/W2953008890","https://openalex.org/W2963351448","https://openalex.org/W2972445543","https://openalex.org/W2995514860","https://openalex.org/W3003285614","https://openalex.org/W3003557640","https://openalex.org/W3007661495","https://openalex.org/W3011411500","https://openalex.org/W3031591096","https://openalex.org/W3035978132","https://openalex.org/W3049674210","https://openalex.org/W3096218861","https://openalex.org/W3122809531","https://openalex.org/W3128210660","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3161829609","https://openalex.org/W3177500196","https://openalex.org/W4214544244","https://openalex.org/W4220829598","https://openalex.org/W4224315024","https://openalex.org/W4224997359","https://openalex.org/W4280615604","https://openalex.org/W4293094353","https://openalex.org/W4312505683","https://openalex.org/W4312969792","https://openalex.org/W4324291664","https://openalex.org/W4385212722","https://openalex.org/W4385245566","https://openalex.org/W4385267180","https://openalex.org/W4387447837","https://openalex.org/W4400762160","https://openalex.org/W6631190155","https://openalex.org/W6780226713","https://openalex.org/W6808300544"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W1971568933"],"abstract_inverted_index":{"Phage":[0],"virion":[1],"proteins":[2],"(PVPs),":[3],"which":[4,130],"form":[5],"the":[6,26,46,55,83,102,107,114,117,134,144,148,163,166,170,179,183,186],"structural":[7],"components":[8,140,190],"of":[9,28,45,57,87,93,138,165,185,191],"phages,":[10],"are":[11],"crucial":[12],"for":[13,49,82,153],"maintaining":[14],"phage":[15,127],"structures":[16],"and":[17,60,85,136,156,175,188,196],"infecting":[18],"host":[19],"bacteria.":[20],"Identifying":[21],"PVPs":[22],"can":[23],"lead":[24],"to":[25,32,64,96,122,143],"development":[27],"novel":[29],"therapeutic":[30],"agents":[31],"combat":[33],"bacterial":[34],"infections,":[35],"attracting":[36],"great":[37],"research":[38],"attention":[39],"in":[40,132,141,173,193],"recent":[41],"years.":[42],"However,":[43],"most":[44],"existing":[47],"methods":[48,172],"PVP":[50,154],"identification":[51,84,155],"heavily":[52],"depend":[53],"on":[54],"effectiveness":[56],"feature":[58],"extraction":[59],"have":[61],"no":[62],"ability":[63],"precisely":[65],"classify":[66],"specific":[67],"classes.":[68],"In":[69],"this":[70],"article,":[71],"we":[72],"propose":[73],"a":[74,91],"bidirectional":[75],"encoder":[76],"representations-based":[77],"Transformer":[78],"model":[79,115,150],"called":[80],"BERTPVP":[81,89,168,192],"classification":[86,157],"PVPs.":[88,177],"uses":[90],"stack":[92],"transformer":[94],"encoders":[95],"effectively":[97],"capture":[98],"contextual":[99,124],"information":[100,125],"from":[101,126],"entire":[103,145],"protein":[104,128],"sequence":[105],"through":[106],"multi-head":[108],"self-attention":[109],"mechanism.":[110],"We":[111],"firstly":[112],"pre-train":[113],"using":[116],"masked":[118],"language":[119],"modeling":[120],"task":[121],"learn":[123],"sequences,":[129],"aids":[131],"understanding":[133],"significance":[135],"relevance":[137],"individual":[139],"relation":[142],"sequence.":[146],"Subsequently,":[147],"pre-trained":[149],"is":[151],"fine-tuned":[152],"tasks.":[158],"Our":[159],"experimental":[160],"results":[161],"show":[162],"superiority":[164],"proposed":[167],"over":[169],"state-of-the-art":[171],"identifying":[174],"classifying":[176],"Moreover,":[178],"ablation":[180],"study":[181],"demonstrates":[182],"necessity":[184],"pre-training":[187],"fine-tuning":[189],"accelerating":[194],"convergence":[195],"improving":[197],"prediction":[198],"performance.":[199]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}