{"id":"https://openalex.org/W7126074475","doi":"https://doi.org/10.1109/bibm66473.2025.11356070","title":"BGC Prediction on Minimizing Generalization Error Upper Bound by Collaborative Belief from Fused Biological Language Representations","display_name":"BGC Prediction on Minimizing Generalization Error Upper Bound by Collaborative Belief from Fused Biological Language Representations","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126074475","doi":"https://doi.org/10.1109/bibm66473.2025.11356070"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356070","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zixuan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Xiao","raw_affiliation_strings":["Xiamen University,Department of Automation,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Automation,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079089558","display_name":"Tingzhi Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingzhi Deng","raw_affiliation_strings":["National Institute for Data Science in Health and Medicine, Xiamen University,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Data Science in Health and Medicine, Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124281722","display_name":"Xiaobing Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I129708740","display_name":"Fujian Medical University","ror":"https://ror.org/050s6ns64","country_code":"CN","type":"education","lineage":["https://openalex.org/I129708740"]},{"id":"https://openalex.org/I4210121761","display_name":"First Affiliated Hospital of Fujian Medical University","ror":"https://ror.org/030e09f60","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210121761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Huang","raw_affiliation_strings":["Fuzhou First Hospital, Affiliated with Fujian Medical University,Department of Medical Oncology,Fuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou First Hospital, Affiliated with Fujian Medical University,Department of Medical Oncology,Fuzhou,China","institution_ids":["https://openalex.org/I4210121761","https://openalex.org/I129708740"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124175625","display_name":"Ying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["National Institute for Data Science in Health and Medicine,State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University,Department of Automation,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Data Science in Health and Medicine,State Key Laboratory of Mariculture Breeding, Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Xiamen University,Department of Automation,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1363","last_page":"1368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.37070000171661377,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.37070000171661377,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.16779999434947968,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.1324000060558319,"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/generalization","display_name":"Generalization","score":0.5864999890327454},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5663999915122986},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5569999814033508},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4625000059604645},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4361000061035156},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.39430001378059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654999852180481},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5864999890327454},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5663999915122986},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5378000140190125},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4625000059604645},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.39430001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3853999972343445},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.352400004863739},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2779396153","wikidata":"https://www.wikidata.org/wiki/Q901227","display_name":"Natural product","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.26840001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356070","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2009257824","https://openalex.org/W2173732482","https://openalex.org/W2229450847","https://openalex.org/W2967688728","https://openalex.org/W2972473680","https://openalex.org/W3011366455","https://openalex.org/W4309305948","https://openalex.org/W4327550249","https://openalex.org/W4368358469","https://openalex.org/W4377861946","https://openalex.org/W4409409776"],"related_works":[],"abstract_inverted_index":{"Biosynthetic":[0],"gene":[1],"clusters":[2],"(BGCs)":[3],"encode":[4],"enzymes":[5],"responsible":[6],"for":[7,31,59,191],"the":[8,86,94,114,121,136,165],"synthesis":[9],"of":[10,20,96,111,144],"microbial":[11],"secondary":[12],"metabolites.":[13],"These":[14],"metabolites":[15],"constitute":[16],"a":[17,53,79,141,188],"major":[18],"source":[19],"clinically":[21],"important":[22],"drugs.":[23],"Accurate":[24],"BGC":[25,61,162],"identification":[26],"and":[27,42,63,72,118,147,157,171,195],"classification":[28,65],"are":[29],"essential":[30],"natural":[32,196],"product":[33,64,197],"discovery.":[34,198],"Existing":[35],"tools":[36],"often":[37],"rely":[38],"on":[39,113,120],"single-level":[40],"features":[41],"show":[43],"limited":[44],"sensitivity":[45],"to":[46,100,131,167],"novel":[47],"cluster":[48],"architectures.":[49],"We":[50],"present":[51],"CoBe-BGC,":[52],"deep":[54],"learning":[55],"framework":[56],"designed":[57],"specifically":[58],"precise":[60],"detection":[62,163],"across":[66,126],"diverse":[67,142,182],"genomes.":[68,179],"It":[69],"integrates":[70],"gene-level":[71],"Pfam":[73],"domain-level":[74],"biological":[75],"language":[76],"representations":[77],"through":[78],"Collaborative":[80],"Belief":[81],"Fusion":[82],"strategy.":[83],"Guided":[84],"by":[85],"Generalization":[87],"Error":[88],"Upper":[89],"Bound,":[90],"CoBe-BGC":[91,107,139],"adaptively":[92],"adjusts":[93],"contribution":[95],"each":[97],"modality":[98],"according":[99],"its":[101],"estimated":[102],"confidence.":[103],"Across":[104],"benchmark":[105],"datasets,":[106],"achieved":[108],"AUROC":[109],"scores":[110],"0.960":[112],"nine":[115],"genome":[116,193],"dataset":[117,123],"0.958":[119],"six-genome":[122],"demonstrating":[124],"reliability":[125],"different":[127],"genomic":[128,183],"contexts.":[129],"Applied":[130],"94":[132],"fungal":[133],"genomes":[134],"from":[135],"phylum":[137],"Chytridiomycota,":[138],"identified":[140],"set":[143],"candidate":[145],"BGCs":[146],"classifies":[148],"them":[149],"into":[150],"known":[151],"biosynthetic":[152],"categories,":[153],"including":[154],"NRPs,":[155],"polyketides":[156],"RiPPs.":[158],"CoBe-BGC's":[159],"capabilities":[160],"in":[161,174],"reveal":[164],"potential":[166],"improve":[168],"prediction":[169],"accuracy":[170],"functional":[172],"resolution":[173],"complex":[175],"or":[176],"poorly":[177],"annotated":[178],"By":[180],"integrating":[181],"features,":[184],"it":[185],"also":[186],"provides":[187],"scalable":[189],"solution":[190],"large-scale":[192],"mining":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-30T00:00:00"}