{"id":"https://openalex.org/W4406261822","doi":"https://doi.org/10.1109/bibm62325.2024.10821839","title":"Combinative Bio-feature Proteins Generation via Pre-trained Protein Large Language Models","display_name":"Combinative Bio-feature Proteins Generation via Pre-trained Protein Large Language Models","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406261822","doi":"https://doi.org/10.1109/bibm62325.2024.10821839"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10821839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5101204726","display_name":"Xin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Sun","raw_affiliation_strings":["Zhejiang University,Center for Data Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Center for Data Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077798585","display_name":"Yuhao Wu","orcid":"https://orcid.org/0000-0002-9746-1975"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Wu","raw_affiliation_strings":["Zhejiang University,Center for Data Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Center for Data Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101204726"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19114093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9894000291824341,"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":0.9894000291824341,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9868000149726868,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9699000120162964,"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":0.7187601923942566},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.560175359249115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5308785438537598},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3543364107608795},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10306936502456665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7187601923942566},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.560175359249115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5308785438537598},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3543364107608795},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10306936502456665},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10821839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2999840604","https://openalex.org/W3110137169","https://openalex.org/W3132323068","https://openalex.org/W3135130381","https://openalex.org/W3154275519","https://openalex.org/W3177500196","https://openalex.org/W4288066876","https://openalex.org/W4312222866","https://openalex.org/W4327550249","https://openalex.org/W4385373960","https://openalex.org/W6791955017","https://openalex.org/W6798272402","https://openalex.org/W6800796171"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Proteins":[0],"serve":[1],"as":[2,13,65],"the":[3,61,66,113,123,152,157,196,209],"functional":[4],"building":[5],"blocks":[6],"of":[7,32,115,159,198],"life,":[8],"facilitating":[9],"critical":[10],"tasks":[11],"such":[12],"signaling,":[14],"catalysis,":[15],"and":[16,40,69,191,203,222,233],"structural":[17],"support":[18],"in":[19,102,226],"all":[20],"living":[21],"organisms.":[22],"Designing":[23],"proteins":[24,59,78,86,130],"with":[25,60,87,131],"targeted":[26],"biological":[27,63,81,133,164,199,227],"features":[28,134],"or":[29],"domains":[30,82],"is":[31,122,141],"utmost":[33],"importance.":[34],"Traditional":[35],"wet-lab":[36],"experiments":[37],"are":[38],"time-consuming":[39],"resource-intensive,":[41],"which":[42,90,121],"makes":[43],"deep":[44],"learning":[45],"(DL)":[46],"methods":[47,53],"ideal":[48],"alternatives.":[49],"However,":[50],"existing":[51,210],"DL":[52],"predominantly":[54],"focus":[55],"on":[56,195],"generating":[57],"new":[58,176],"same":[62],"domain":[64,165],"training":[67],"data,":[68],"overlook":[70],"some":[71],"scenarios":[72],"where":[73],"designers":[74],"expect":[75],"to":[76,83,127,166,207],"combine":[77],"from":[79,135,151,162],"different":[80,137],"create":[84],"novel":[85,109],"both":[88],"features,":[89],"can":[91],"show":[92],"better":[93,221],"fits":[94],"for":[95],"practical":[96],"purpose.":[97],"To":[98],"fill":[99],"this":[100,103],"gap,":[101],"paper,":[104],"we":[105,174],"present":[106],"ComProtein,":[107],"a":[108,144],"framework":[110],"further":[111],"exploiting":[112],"potential":[114,225],"pre-trained":[116],"protein":[117,160,201],"large":[118],"language":[119],"models,":[120],"first":[124],"work":[125],"aiming":[126],"generate":[128],"innovative":[129],"combinative":[132],"two":[136],"domains.":[138],"This":[139],"process":[140],"performed":[142],"by":[143],"cycle-consistent":[145],"generative":[146],"adversarial":[147],"approach,":[148],"leveraging":[149],"insights":[150],"latent":[153],"space.":[154],"It":[155],"enables":[156],"transformation":[158],"representations":[161],"one":[163],"another,":[167],"while":[168],"preserving":[169],"their":[170],"intrinsic":[171],"features.":[172],"Additionally,":[173],"introduce":[175],"evaluative":[177],"metrics,":[178],"namely":[179],"Shortest":[180],"Target":[181],"Neighbor":[182],"Distance":[183],"(STND),":[184],"Mutual":[185],"Root":[186],"Mean":[187],"Square":[188],"Deviation":[189],"(MRMSD)":[190],"Sequence":[192],"Diversity":[193],"(SD)":[194],"evaluation":[197],"representations,":[200,228],"structure":[202,229],"sequence":[204,234],"quality,":[205],"respectively":[206],"complement":[208],"measures.":[211],"Our":[212],"experimental":[213],"results":[214],"demonstrate":[215],"that":[216],"our":[217],"proposed":[218],"method":[219],"performs":[220],"has":[223],"great":[224],"similarity,":[230],"homology":[231],"relationships,":[232],"quality.":[235]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}