{"id":"https://openalex.org/W4416035172","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.369","title":"LM2Protein: A Structure-to-Token Protein Large Language Model","display_name":"LM2Protein: A Structure-to-Token Protein Large Language Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035172","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.369"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.369","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.369","pdf_url":"https://aclanthology.org/2025.findings-emnlp.369.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.369.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102025315","display_name":"Chang Zhou","orcid":"https://orcid.org/0000-0001-9241-702X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639054","display_name":"Shan Ye","orcid":"https://orcid.org/0000-0001-6496-0893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuheng Shan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053263555","display_name":"Pengan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104086196","display_name":"Xiangyu Shi","orcid":"https://orcid.org/0009-0007-3909-7929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056285519","display_name":"Zikang Wang","orcid":"https://orcid.org/0000-0003-1406-1237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zikang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720245","display_name":"Yanting Li","orcid":"https://orcid.org/0000-0003-2973-3016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanting Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038913434","display_name":"Jiyue Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiyue Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7023","last_page":"7029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.29409998655319214,"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":0.29409998655319214,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.12549999356269836,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.06759999692440033,"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/language-model","display_name":"Language model","score":0.33250001072883606},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3122999966144562},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28679999709129333},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.26269999146461487},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.2596000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593500018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4632999897003174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.369","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.369","pdf_url":"https://aclanthology.org/2025.findings-emnlp.369.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.369","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.369","pdf_url":"https://aclanthology.org/2025.findings-emnlp.369.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035172.pdf","grobid_xml":"https://content.openalex.org/works/W4416035172.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Proteins":[0],"are":[1],"critical":[2],"for":[3,79,152],"various":[4],"molecular":[5],"functions,":[6],"relying":[7],"on":[8,41],"their":[9],"precise":[10],"tertiary":[11],"structures.This":[12],"structure-sequence":[13],"relationship":[14],"is":[15,48],"complex":[16,74,118,155],"and":[17,33,82,120,143],"degenerate,":[18],"meaning":[19],"multiple":[20],"sequences":[21,62],"can":[22],"fold":[23],"into":[24,103],"a":[25,87,96,108,122,132],"similar":[26],"structure.The":[27],"challenges":[28],"in":[29,59,140,154],"protein":[30,91],"prediction,":[31],"design,":[32],"modification":[34],"increase":[35],"with":[36],"sequence":[37,97,138],"complexity,":[38],"while":[39],"research":[40],"RNA-protein":[42],"interactions,":[43],"especially":[44],"RNA-binding":[45],"proteins":[46],"(RBPs),":[47],"gaining":[49],"importance.Large-scale":[50],"pre-trained":[51],"language":[52],"models":[53],"(LLMs)":[54],"have":[55],"shown":[56],"promising":[57],"results":[58,148],"handling":[60,113],"biological":[61,156],"by":[63],"treating":[64],"them":[65],"as":[66],"natural":[67],"language,":[68],"though":[69],"integrating":[70],"spatial":[71],"structures":[72],"remains":[73],"due":[75],"to":[76,89],"the":[77,112],"need":[78],"specialized":[80],"visual":[81],"3D":[83,92,101,115],"modeling":[84],"approaches.We":[85],"introduce":[86],"method":[88],"integrate":[90],"structural":[93],"data":[94],"within":[95],"processing":[98,125],"framework,":[99],"converting":[100],"coordinates":[102],"discrete":[104],"structure":[105],"tokens":[106],"using":[107],"VQ-VAE-like":[109],"network.This":[110],"simplifies":[111],"of":[114,134],"data,":[116],"avoiding":[117],"pipelines":[119],"facilitating":[121],"unified":[123],"sequence-to-sequence":[124],"model.Our":[126],"approach":[127],"demonstrates":[128],"strong":[129],"performance":[130],"across":[131],"range":[133],"tasks,":[135],"achieving":[136],"high":[137],"recovery":[139],"inverse":[141],"folding":[142],"protein-conditioned":[144],"RNA":[145],"design.These":[146],"outstanding":[147],"demonstrate":[149],"significant":[150],"potential":[151],"application":[153],"systems":[157],"research.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}