{"id":"https://openalex.org/W4409882638","doi":"https://doi.org/10.1109/tai.2025.3564914","title":"ProLLaMA: A Protein Large Language Model for Multitask Protein Language Processing","display_name":"ProLLaMA: A Protein Large Language Model for Multitask Protein Language Processing","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4409882638","doi":"https://doi.org/10.1109/tai.2025.3564914"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3564914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3564914","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5005977834","display_name":"Liuzhenghao Lv","orcid":"https://orcid.org/0000-0001-5604-1678"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liuzhenghao Lv","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5604-1678","affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001960948","display_name":"Zongying Lin","orcid":"https://orcid.org/0009-0005-6707-173X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongying Lin","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348558","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-1752-5167"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373460","display_name":"Yuyang Liu","orcid":"https://orcid.org/0000-0002-7438-7258"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Liu","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070944532","display_name":"Jiaxi Cui","orcid":"https://orcid.org/0000-0002-2550-979X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxi Cui","raw_affiliation_strings":["Pandalla.AI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pandalla.AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078562310","display_name":"Calvin Yu\u2010Chian Chen","orcid":"https://orcid.org/0000-0001-9213-9832"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Calvin Yu-Chian Chen","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9213-9832","affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116493713","display_name":"Li Yuan","orcid":"https://orcid.org/0000-0002-2120-5588"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yuan","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2120-5588","affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2978-5935","affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5005977834"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":11.3817,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98842819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"7","issue":"2","first_page":"642","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9926000237464905,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015587091445923},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5377234816551208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43096572160720825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34483009576797485},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07882001996040344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015587091445923},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5377234816551208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43096572160720825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34483009576797485},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07882001996040344},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3564914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3564914","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1947953275","display_name":null,"funder_award_id":"62425101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5151253548","display_name":null,"funder_award_id":"62332002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8504279988","display_name":null,"funder_award_id":"62202014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1594096205","https://openalex.org/W1974819439","https://openalex.org/W2005382196","https://openalex.org/W2032192940","https://openalex.org/W2047544230","https://openalex.org/W2102461176","https://openalex.org/W2161151688","https://openalex.org/W2171533950","https://openalex.org/W2587741066","https://openalex.org/W2620185010","https://openalex.org/W2791796577","https://openalex.org/W2794004073","https://openalex.org/W2808950571","https://openalex.org/W2938415845","https://openalex.org/W2980789587","https://openalex.org/W3129073614","https://openalex.org/W3146944767","https://openalex.org/W3177323791","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W4205773061","https://openalex.org/W4205953903","https://openalex.org/W4283390570","https://openalex.org/W4288066876","https://openalex.org/W4308616064","https://openalex.org/W4318071656","https://openalex.org/W4327550249","https://openalex.org/W4327811957","https://openalex.org/W4375858802","https://openalex.org/W4379259169","https://openalex.org/W4385245566","https://openalex.org/W4388024559","https://openalex.org/W4388945356","https://openalex.org/W4392669753","https://openalex.org/W4393153123","https://openalex.org/W4402670712"],"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":{"Recent":[0],"advances":[1],"in":[2,15,28,46,142,171],"Protein":[3,30,35,65],"Language":[4,17,31,36],"Models":[5],"(PLMs)":[6],"have":[7],"transformed":[8],"protein":[9,47,58,105,147],"engineering,":[10],"yet":[11],"unlike":[12],"their":[13],"counterparts":[14],"Natural":[16],"Processing":[18],"(NLP),":[19],"current":[20],"PLMs":[21],"exhibit":[22],"a":[23,56,71,94,101,123,131,166],"fundamental":[24],"limitation:":[25],"they":[26],"excel":[27],"either":[29],"Understanding":[32],"(PLU)":[33],"or":[34],"Generation":[37,66],"(PLG),":[38],"but":[39],"rarely":[40],"both.":[41],"This":[42],"fragmentation":[43],"hinders":[44],"progress":[45],"engineering.":[48],"To":[49],"bridge":[50],"this":[51],"gap,":[52],"we":[53],"introduce":[54],"ProLLaMA,":[55,100],"multitask":[57,102],"language":[59,115],"model":[60],"enhanced":[61],"by":[62,185],"the":[63,111,177],"Evolutionary":[64],"Framework":[67],"(EPGF).":[68],"We":[69,92],"construct":[70],"comprehensive":[72],"instruction":[73],"dataset":[74],"containing":[75],"approximately":[76],"13":[77],"million":[78],"samples":[79],"with":[80,104,165],"over":[81],"11,000":[82],"superfamily":[83,172],"annotations":[84],"to":[85,98,156],"facilitate":[86],"better":[87],"modeling":[88,116],"of":[89,180],"sequence-function":[90],"landscapes.":[91],"leverage":[93],"two-stage":[95],"training":[96],"approach":[97],"develop":[99],"LLM":[103],"domain":[106],"expertise.":[107],"Our":[108],"EPGF":[109,174],"addresses":[110],"mismatch":[112],"between":[113],"statistic":[114],"and":[117,130,145,190],"biological":[118,178],"constraints":[119],"through":[120],"three":[121],"innovations:":[122],"multi-dimensional":[124],"interpretable":[125],"scorer,":[126],"hierarchical":[127],"efficient":[128],"decoding,":[129],"probabilistic-biophysical":[132],"joint":[133],"selection":[134],"mechanism.":[135],"Extensive":[136],"experiments":[137],"demonstrate":[138],"that":[139],"ProLLaMA":[140,160],"excels":[141],"both":[143],"unconditional":[144],"controllable":[146],"generation":[148],"tasks,":[149],"achieving":[150],"superior":[151],"structural":[152,191],"quality":[153],"metrics":[154,192],"compared":[155],"existing":[157],"PLMs.":[158],"Additionally,":[159],"demonstrates":[161],"strong":[162],"understanding":[163],"capabilities":[164],"67.1%":[167],"exact":[168],"match":[169],"rate":[170],"prediction.":[173],"significantly":[175],"enhances":[176],"viability":[179],"generated":[181],"sequences,":[182],"as":[183],"evidenced":[184],"improved":[186],"biophysical":[187],"scores":[188],"(+4.3%)":[189],"(+14.5%).":[193]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":2}],"updated_date":"2026-02-04T23:10:29.248076","created_date":"2025-10-10T00:00:00"}