{"id":"https://openalex.org/W4416073782","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1254","title":"STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding","display_name":"STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416073782","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1254"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1254","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1254","pdf_url":"https://aclanthology.org/2026.findings-acl.1254.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1254.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015098008","display_name":"Hongwang Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwang Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619424","display_name":"Wenjun Lin","orcid":"https://orcid.org/0009-0008-7925-6944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330074","display_name":"Xi Chen","orcid":"https://orcid.org/0009-0007-7692-9771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460761","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-3226-8728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437965","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-4081-0687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033598489","display_name":"Jiashan Li","orcid":"https://orcid.org/0000-0001-8439-7516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiashan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101187991","display_name":"Yuancheng Sun","orcid":"https://orcid.org/0009-0003-9901-9296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuancheng Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066338475","display_name":"Sicheng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sicheng Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101234400","display_name":"Boya Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boya Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089028438","display_name":"Qiwei Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiwei Ye","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":43.9643,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98415278,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"25030","last_page":"25049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.3752000033855438,"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":0.3752000033855438,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.10790000110864639,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.10639999806880951,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5557000041007996},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5242000222206116},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.44119998812675476},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.3695000112056732},{"id":"https://openalex.org/keywords/stella","display_name":"STELLA (programming language)","score":0.3677999973297119},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.36640000343322754}],"concepts":[{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5246999859809875},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.44119998812675476},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3695000112056732},{"id":"https://openalex.org/C2776174103","wikidata":"https://www.wikidata.org/wiki/Q25339766","display_name":"STELLA (programming language)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.34040001034736633},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1254","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1254","pdf_url":"https://aclanthology.org/2026.findings-acl.1254.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.03800","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.03800","pdf_url":"https://arxiv.org/pdf/2506.03800","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2506.03800","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.03800","pdf_url":"https://arxiv.org/pdf/2506.03800","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.03800","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.03800","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1254","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1254","pdf_url":"https://aclanthology.org/2026.findings-acl.1254.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416073782.pdf","grobid_xml":"https://content.openalex.org/works/W4416073782.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"the":[1,24,61,69,92],"intricate":[2],"interplay":[3],"among":[4],"sequence,":[5],"structure,":[6],"and":[7,68,106,123,146],"function":[8],"remains":[9],"a":[10,82,133,140],"fundamental":[11],"challenge":[12],"in":[13,116],"proteomics.The":[14],"sequence-structure-function":[15],"paradigm":[16,134],"posits":[17],"that":[18,73,85,129],"biological":[19],"roles":[20],"are":[21],"governed":[22],"by":[23],"tertiary":[25],"geometric":[26],"conformations":[27],"encoded":[28],"within":[29],"primary":[30],"sequences;":[31],"consequently,":[32],"integrating":[33],"these":[34],"multi-modal":[35],"descriptors":[36],"is":[37],"imperative":[38],"for":[39,102,108,143],"accurate":[40],"functional":[41,98],"annotation.While":[42],"protein":[43,75,97,144],"language":[44,110],"models":[45],"(pLMs)":[46],"have":[47],"achieved":[48],"significant":[49],"progress":[50],"via":[51,153],"representation":[52],"learning":[53],"on":[54],"massive":[55],"sequence":[56],"data,":[57],"they":[58],"often":[59],"lack":[60],"capacity":[62],"to":[63,95],"incorporate":[64],"high-resolution":[65],"structural":[66],"information":[67],"rich":[70],"textual":[71,93],"context":[72],"characterizes":[74],"roles.In":[76],"this":[77],"work,":[78],"we":[79],"present":[80],"STELLA,":[81],"multimodal":[83,130],"LLM":[84],"synergistically":[86],"aligns":[87],"bimodal":[88,104],"(sequence-structure)":[89],"representations":[90],"with":[91],"modality":[94],"advance":[96],"annotation.By":[99],"leveraging":[100],"ESM3":[101],"unified":[103],"encoding":[105],"Llama-3.1-8B-Instruct":[107],"natural":[109],"modeling,":[111],"STELLA":[112],"achieves":[113],"state-of-the-art":[114],"performance":[115],"two":[117],"critical":[118],"tasks:":[119],"Functional":[120],"Description":[121],"Prediction":[122],"Enzyme-catalyzed":[124],"Reaction":[125],"Prediction.This":[126],"study":[127],"demonstrates":[128],"LLMs":[131],"represent":[132],"shift":[135],"beyond":[136],"pure":[137],"pLMs,":[138],"offering":[139],"new":[141],"frontier":[142],"biology":[145],"biomedical":[147],"discovery.The":[148],"codes":[149],"can":[150],"be":[151],"accessed":[152],"https:":[154],"//github.com/ocx-lab/STELLA.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}