{"id":"https://openalex.org/W4406259827","doi":"https://doi.org/10.1109/bibm62325.2024.10822514","title":"FalconProtein: Finetuning Falcon Foundation Model for Protein Engineering","display_name":"FalconProtein: Finetuning Falcon Foundation Model for Protein Engineering","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259827","doi":"https://doi.org/10.1109/bibm62325.2024.10822514"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822514","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":"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/A5101143659","display_name":"Yang Wenjun","orcid":null},"institutions":[{"id":"https://openalex.org/I143923087","display_name":"Sultan Idris Education University","ror":"https://ror.org/005bjd415","country_code":"MY","type":"education","lineage":["https://openalex.org/I143923087"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Wenjun Yang","raw_affiliation_strings":["Universiti Pendidikan Sultan Idris,Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Pendidikan Sultan Idris,Malaysia","institution_ids":["https://openalex.org/I143923087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072622467","display_name":"Yiqing Shen","orcid":"https://orcid.org/0000-0001-7866-3339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiqing Shen","raw_affiliation_strings":["Toursun Synbio,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toursun Synbio,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062423029","display_name":"Zehong Wang","orcid":"https://orcid.org/0000-0002-7670-6777"},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":"CN","type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehong Wang","raw_affiliation_strings":["Changchun University of Technology,Changchun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changchun University of Technology,Changchun,China","institution_ids":["https://openalex.org/I4385474403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024414161","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0003-1597-1961"},"institutions":[{"id":"https://openalex.org/I4210114235","display_name":"Heihe University","ror":"https://ror.org/0221fhj86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210114235"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Heihe University,Heihe,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heihe University,Heihe,China","institution_ids":["https://openalex.org/I4210114235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115839949","display_name":"Qitong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114235","display_name":"Heihe University","ror":"https://ror.org/0221fhj86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210114235"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qitong Lu","raw_affiliation_strings":["Heihe University,Heihe,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heihe University,Heihe,China","institution_ids":["https://openalex.org/I4210114235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051040052","display_name":"Xinsheng Liu","orcid":"https://orcid.org/0000-0002-3348-9493"},"institutions":[{"id":"https://openalex.org/I4210114235","display_name":"Heihe University","ror":"https://ror.org/0221fhj86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210114235"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Liu","raw_affiliation_strings":["Heihe University,Heihe,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heihe University,Heihe,China","institution_ids":["https://openalex.org/I4210114235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009226259","display_name":"Yungeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yungeng Liu","raw_affiliation_strings":["Toursun Synbio,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toursun Synbio,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056145687","display_name":"M\u00e9rouane Debbah","orcid":"https://orcid.org/0000-0001-8941-8080"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Merouane Debbah","raw_affiliation_strings":["Khalifa University,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khalifa University,UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001398658","display_name":"Y Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Guang Wang","raw_affiliation_strings":["Toursun Synbio,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toursun Synbio,Shanghai,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059367213","display_name":"Shir Li Wang","orcid":"https://orcid.org/0000-0003-4417-3213"},"institutions":[{"id":"https://openalex.org/I143923087","display_name":"Sultan Idris Education University","ror":"https://ror.org/005bjd415","country_code":"MY","type":"education","lineage":["https://openalex.org/I143923087"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Shir Li Wang","raw_affiliation_strings":["Universiti Pendidikan Sultan Idris,Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Pendidikan Sultan Idris,Malaysia","institution_ids":["https://openalex.org/I143923087"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5409","last_page":"5417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.8756999969482422,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.8756999969482422,"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":0.6626105904579163},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4702564477920532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6626105904579163},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4702564477920532},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822514","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":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2103425480","https://openalex.org/W2107158607","https://openalex.org/W2620998958","https://openalex.org/W2757254843","https://openalex.org/W2901496107","https://openalex.org/W2913820882","https://openalex.org/W2917858269","https://openalex.org/W2980170459","https://openalex.org/W3015964336","https://openalex.org/W3095583226","https://openalex.org/W3105895642","https://openalex.org/W3107527779","https://openalex.org/W3209545809","https://openalex.org/W3211795435","https://openalex.org/W4205773061","https://openalex.org/W4221142212","https://openalex.org/W4307370003","https://openalex.org/W4308616064","https://openalex.org/W4309161067","https://openalex.org/W4309908854","https://openalex.org/W4310951880","https://openalex.org/W4390690464","https://openalex.org/W4391940656","https://openalex.org/W4400978157","https://openalex.org/W4401715368","https://openalex.org/W4406238010","https://openalex.org/W4406259721","https://openalex.org/W4406260665","https://openalex.org/W4406261070","https://openalex.org/W4406261472","https://openalex.org/W6739901393","https://openalex.org/W6809646742","https://openalex.org/W6851775633","https://openalex.org/W6854720692","https://openalex.org/W6857464309","https://openalex.org/W6861316932","https://openalex.org/W6862837114","https://openalex.org/W6869164663","https://openalex.org/W6871553294","https://openalex.org/W6873294336","https://openalex.org/W6873607958","https://openalex.org/W6873689019","https://openalex.org/W6875672671"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"zero-shot":[6],"generalization":[7],"capabilities":[8],"in":[9,144],"analyzing":[10],"and":[11,36,56,77,105,130],"predicting":[12],"protein":[13,49,90,128],"properties":[14],"through":[15],"natural":[16],"language":[17],"interactions.":[18,131],"However,":[19],"existing":[20],"protein-focused":[21],"datasets":[22],"for":[23,34,39,83],"LLM":[24],"fine-tuning,":[25,40],"such":[26],"as":[27],"ProteinLMDataset":[28],"with":[29],"its":[30],"17.46":[31],"billion":[32],"tokens":[33,82],"pre-training":[35],"893,000":[37],"instructions":[38],"face":[41],"limitations.":[42],"Specifically,":[43],"they":[44],"include":[45],"insufficient":[46],"coverage":[47],"of":[48,59,136],"functional":[50],"properties,":[51],"inadequate":[52],"protein-protein":[53],"interaction":[54],"data,":[55],"limited":[57],"integration":[58],"contextual":[60,125],"information":[61,126],"from":[62,75,160],"biomedical":[63,120],"literature.":[64],"To":[65,132],"overcome":[66],"these":[67],"challenges,":[68],"we":[69,109,139,147],"present":[70],"ProteinPFAIDataset,":[71],"which":[72],"integrates":[73],"data":[74],"UniProt":[76],"PubMed,":[78],"comprising":[79],"72.8":[80],"million":[81],"Supervised":[84],"Fine-Tuning":[85],"(SFT).":[86],"ProteinPFAIDataset":[87],"encompasses":[88],"important":[89],"characteristics":[91],"including":[92],"enzyme":[93],"activities,":[94],"molecular":[95],"functions,":[96],"pH":[97],"dependence,":[98],"tissue":[99],"specificity,":[100],"temperature":[101],"sensitivity,":[102],"subunit":[103],"structure,":[104],"disease":[106],"associations.":[107],"Additionally,":[108],"propose":[110],"a":[111,145],"novel":[112],"knowledge":[113],"graph-based":[114],"approach":[115],"that":[116],"incorporates":[117],"over":[118],"300,000":[119],"literature":[121],"entries,":[122],"providing":[123],"rich":[124],"about":[127],"functions":[129],"validate":[133],"the":[134],"effectiveness":[135],"our":[137],"dataset,":[138],"fine-tuned":[140,151,171],"Falcon2-11B":[141],"LLM,":[142],"resulting":[143],"model":[146,152,172],"call":[148],"Falcon2-11B-PFAI.":[149],"The":[150,164,170],"achieved":[153],"state-of-the-art":[154],"performance":[155],"on":[156],"ProteinLMBench,":[157],"improving":[158],"accuracy":[159],"47.10%":[161],"to":[162],"58.37%.":[163],"dataset":[165],"is":[166,173],"available":[167,174],"at":[168,175],"https://huggingface.co/datasets/xiaorui1/PFAI.":[169],"https://huggingface.co/xiaorui1/PFAI/tree/main.":[176]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
