{"id":"https://openalex.org/W7126071886","doi":"https://doi.org/10.1109/bibm66473.2025.11356265","title":"Cross-Granularity Representations for Biological Sequences: Insights From ESM and BiGCARP","display_name":"Cross-Granularity Representations for Biological Sequences: Insights From ESM and BiGCARP","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126071886","doi":"https://doi.org/10.1109/bibm66473.2025.11356265"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.20825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124156530","display_name":"Hanlin Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hanlin Xiao","raw_affiliation_strings":["Manchester Institute of Biotechnology, The University of Manchester,Manchester,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manchester Institute of Biotechnology, The University of Manchester,Manchester,United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110299768","display_name":"Breitling Rainer","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rainer Breitling","raw_affiliation_strings":["Manchester Institute of Biotechnology, The University of Manchester,Manchester,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manchester Institute of Biotechnology, The University of Manchester,Manchester,United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124182502","display_name":"Eriko Takano","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eriko Takano","raw_affiliation_strings":["Manchester Institute of Biotechnology, The University of Manchester,Manchester,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manchester Institute of Biotechnology, The University of Manchester,Manchester,United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124231046","display_name":"Mauricio A. Alvarez","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mauricio A. Alvarez","raw_affiliation_strings":["The University of Manchester,Department of Computer Science,Manchester,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Manchester,Department of Computer Science,Manchester,United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28407311"],"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":"6936","last_page":"6943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.2685000002384186,"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":0.2685000002384186,"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":0.08470000326633453,"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":0.08349999785423279,"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/interpretability","display_name":"Interpretability","score":0.8427000045776367},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7049000263214111},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6220999956130981},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.589900016784668},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5249999761581421},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4066999852657318},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.4023999869823456}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8427000045776367},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7049000263214111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662999987602234},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6220999956130981},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C10853874","wikidata":"https://www.wikidata.org/wiki/Q180618","display_name":"Genetic code","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.20825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.20825","pdf_url":"https://arxiv.org/pdf/2603.20825","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.20825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.20825","pdf_url":"https://arxiv.org/pdf/2603.20825","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6733390092849731}],"awards":[{"id":"https://openalex.org/G3422603645","display_name":"UKRI AI Centre for Doctoral Training in Decision Making for Complex Systems","funder_award_id":"EP/Y030826/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2114839447","https://openalex.org/W2136280642","https://openalex.org/W2602946330","https://openalex.org/W2919115771","https://openalex.org/W2967688728","https://openalex.org/W3095583226","https://openalex.org/W3096851604","https://openalex.org/W3118485687","https://openalex.org/W4205773061","https://openalex.org/W4309305948","https://openalex.org/W4327550249","https://openalex.org/W4377861946","https://openalex.org/W4382631189","https://openalex.org/W4385737488","https://openalex.org/W4392302569","https://openalex.org/W4393870943","https://openalex.org/W4406440058","https://openalex.org/W4406817136"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,100,139],"general-purpose":[3],"foundation":[4,161],"models":[5,53],"have":[6],"stimulated":[7],"the":[8,47,115,155],"development":[9],"of":[10,49,58,83,114,159],"large":[11],"biological":[12,24,129,160],"sequence":[13],"models.":[14,162],"While":[15],"natural":[16],"language":[17,74],"shows":[18],"symbolic":[19],"granularity":[20,28],"(characters,":[21],"words,":[22],"sentences),":[23],"sequences":[25],"exhibit":[26],"hierarchical":[27],"whose":[29],"levels":[30],"(nucleotides,":[31],"amino":[32,71],"acids,":[33],"protein":[34,73],"domains,":[35],"genes)":[36],"further":[37],"encode":[38,127],"biologically":[39],"functional":[40],"information.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,86,120],"investigate":[46],"integration":[48,147],"crossgranularity":[50,146],"knowledge":[51],"from":[52],"through":[54],"a":[55,60,81,90,108,149],"case":[56],"study":[57],"BiGCARP,":[59,101],"Pfam":[61],"domain-level":[62],"model":[63],"for":[64,152],"biosynthetic":[65],"gene":[66],"clusters,":[67],"and":[68,80,102,111,131,157],"ESM,":[69],"an":[70],"acid-level":[72],"model.":[75],"Using":[76],"representation":[77,113],"analysis":[78],"tools":[79],"set":[82],"probe":[84],"tasks,":[85],"first":[87],"explain":[88],"why":[89],"straightforward":[91],"cross-model":[92],"embedding":[93],"initialization":[94],"fails":[95],"to":[96],"improve":[97],"downstream":[98],"performance":[99,137,156],"show":[103],"that":[104,122,132],"deeper-layer":[105],"embeddings":[106],"capture":[107],"more":[109],"contextual":[110],"faithful":[112],"model's":[116],"learned":[117],"knowledge.":[118],"Furthermore,":[119],"demonstrate":[121],"representations":[123],"at":[124,167],"different":[125],"granularities":[126],"complementary":[128],"knowledge,":[130],"combining":[133],"them":[134],"yields":[135],"measurable":[136],"gains":[138],"intermediate-level":[140],"prediction":[141],"tasks.":[142],"Our":[143,163],"findings":[144],"highlight":[145],"as":[148],"promising":[150],"strategy":[151],"improving":[153],"both":[154],"interpretability":[158],"code":[164],"is":[165],"available":[166],"https://github.com/Nugkta/cgrep.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-30T00:00:00"}