{"id":"https://openalex.org/W7214955708","doi":"https://doi.org/10.64898/2026.09.28.755017","title":"Fusion2AI: functional re-annotation of the bacterial transparent matter proteins","display_name":"Fusion2AI: functional re-annotation of the bacterial transparent matter proteins","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214955708","doi":"https://doi.org/10.64898/2026.09.28.755017"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.28.755017","doi":"https://doi.org/10.64898/2026.09.28.755017","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755017","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.28.755017.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.28.755017.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040332292","display_name":"Aiden Maloney-Bertelli","orcid":"https://orcid.org/0000-0002-9958-4119","observed_orcids":["https://orcid.org/0000-0002-9958-4119"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aiden Maloney-Bertelli","raw_affiliation_strings":["Department of Biology, Emory University, 1510 Clifton Road NE, Atlanta, GA, 30322, USA","Department of Computer Science, Emory University, 400 Dowman Drive, Atlanta, GA, 30322, USA"],"raw_orcid":"https://orcid.org/0000-0002-9958-4119","affiliations":[{"raw_affiliation_string":"Department of Biology, Emory University, 1510 Clifton Road NE, Atlanta, GA, 30322, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Department of Computer Science, Emory University, 400 Dowman Drive, Atlanta, GA, 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089912529","display_name":"Yana Bromberg","orcid":"https://orcid.org/0000-0002-8351-0844","observed_orcids":["https://orcid.org/0000-0002-8351-0844"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yana Bromberg","raw_affiliation_strings":["Department of Biology, Emory University, 1510 Clifton Road NE, Atlanta, GA, 30322, USA","Department of Computer Science, Emory University, 400 Dowman Drive, Atlanta, GA, 30322, USA"],"raw_orcid":"https://orcid.org/0000-0002-8351-0844","affiliations":[{"raw_affiliation_string":"Department of Biology, Emory University, 1510 Clifton Road NE, Atlanta, GA, 30322, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"Department of Computer Science, Emory University, 400 Dowman Drive, Atlanta, GA, 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089912529"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9814000129699707,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9814000129699707,"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":0.006300000008195639,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.006000000052154064,"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/bacterial-proteins","display_name":"bacterial proteins","score":0.7229999899864197},{"id":"https://openalex.org/keywords/protein-function-annotation","display_name":"protein annotation","score":0.7440000176429749},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7170000076293945},{"id":"https://openalex.org/keywords/gene-ontology-terms","display_name":"Gene Ontology terms","score":0.7099999785423279},{"id":"https://openalex.org/keywords/enzyme-commission-numbers","display_name":"enzyme commission numbers","score":0.9409999847412109},{"id":"https://openalex.org/keywords/metagenome-annotation","display_name":"metagenome annotation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/microbiome-analysis","display_name":"microbiome analysis","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6840000152587891},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.65420001745224},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.5927000045776367},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5335999727249146},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5210999846458435},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C123894998","wikidata":"https://www.wikidata.org/wiki/Q425158","display_name":"Fusion protein","level":4,"score":0.4894999861717224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43880000710487366},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.427700012922287},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.41200000047683716},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.40689998865127563},{"id":"https://openalex.org/C2993175405","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Bacterial protein","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.35929998755455017},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3098999857902527},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.28630000352859497},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.2840000092983246},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.274399995803833},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.27070000767707825},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2911029443","wikidata":"https://www.wikidata.org/wiki/Q21296145","display_name":"Human proteins","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.2572000026702881},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.25049999356269836},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.28.755017","doi":"https://doi.org/10.64898/2026.09.28.755017","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755017","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.28.755017.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.28.755017","doi":"https://doi.org/10.64898/2026.09.28.755017","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755017","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.28.755017.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6836682750","display_name":"Collaborative Research: IIS: III: MEDIUM: Learning Protein-ish: Foundational Insight on Protein Language Models for Better Understanding, Democratized Access, and Discovery","funder_award_id":"2310114","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7260913911","display_name":"Cross-Arc Geochemical Variations in the Southern Washington Cascades","funder_award_id":"0003612","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9000375756","display_name":null,"funder_award_id":"DE-FOA-0003612","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309381","display_name":"Emory University","ror":"https://ror.org/03czfpz43"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214955708.pdf","grobid_xml":"https://content.openalex.org/works/W7214955708.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1692744135","https://openalex.org/W2060797027","https://openalex.org/W2111973517","https://openalex.org/W2768186657","https://openalex.org/W2808291890","https://openalex.org/W2950954328","https://openalex.org/W2989608901","https://openalex.org/W3112600195","https://openalex.org/W4292089575","https://openalex.org/W4386947433","https://openalex.org/W4387541035"],"related_works":["https://openalex.org/W4386947433","https://openalex.org/W7128131831","https://openalex.org/W1975589113","https://openalex.org/W4417411274","https://openalex.org/W4386306370","https://openalex.org/W7147160086","https://openalex.org/W3024062607","https://openalex.org/W4402336735","https://openalex.org/W7155067547","https://openalex.org/W4398200498"],"abstract_inverted_index":{"Abstract":[0],"Determining":[1],"the":[2,23,159,181],"biological":[3],"function":[4,51,62,206],"of":[5,25,27,38,71,86,88,102,183],"bacterial":[6,30],"proteins":[7,31,90,150],"remains":[8],"a":[9,18,100,215],"central":[10],"challenge":[11],"in":[12,143,191],"microbiology.":[13],"We":[14,120],"previously":[15],"developed":[16],"Fusion,":[17],"reference-free":[19],"scheme":[20],"that":[21,194],"clustered":[22],"tens":[24],"millions":[26],"known,":[28],"unique,":[29],"into":[32,91,200],"about":[33],"four":[34],"hundred":[35],"thousand":[36],"groups":[37],"functionally":[39],"similar":[40],"proteins,":[41,49],"i.e.":[42,99,187],"functions":[43,67,87,188],".":[44,222],"For":[45,141,156,170],"any":[46],"newly":[47],"identified":[48],"Fusion":[50,66,104,205],"assignment":[52],"could":[53],"be":[54],"performed":[55],"using":[56],"function-aware":[57],"sequence":[58],"alignment":[59,152],"to":[60,81,153],"each":[61],"\u2019s":[63],"representatives.":[64],"However,":[65],"lack":[68],"human-readable":[69],"descriptions":[70,94],"their":[72],"functionality.":[73],"Here,":[74],"we":[75,109,145],"leverage":[76],"large":[77],"language":[78],"models":[79],"(LLMs)":[80],"synthesize":[82],"scattered,":[83],"partial":[84],"annotations":[85,124,129],"individual":[89],"coherent":[92],"English-language":[93],"for":[95,134,167,218],"\u223c":[96],"100,000":[97],"clusters,":[98],"quarter":[101],"all":[103],"functions.":[105],"From":[106],"these":[107,122],"descriptions,":[108],"extract":[110],"Gene":[111],"Ontology":[112],"(GO)":[113],"terms":[114],"and":[115,137,213],"Enzyme":[116],"Commission":[117],"(EC)":[118],"numbers.":[119],"validate":[121],"against":[123],"inferred":[125],"from":[126],"UniProtKB/Swiss-Prot.":[127],"These":[128],"immediately":[130],"expand":[131],"functional":[132],"coverage":[133,173],"both":[135],"genome":[136],"microbiome":[138],"-level":[139],"analyses.":[140],"organisms":[142],"FusionDB,":[144],"annotate":[146],"\u2265":[147],"50%":[148],"more":[149],"than":[151],"Swiss-Prot":[154],"alone.":[155],"other":[157],"bacteria,":[158],"gain":[160],"is":[161,208],"smaller":[162],"but":[163],"still":[164],"reaches":[165],"30%":[166],"some":[168],"organisms.":[169],"microbiomes,":[171],"annotation":[172,220],"increases":[174],"nearly":[175],"ten-fold.":[176],"Our":[177,203],"work":[178],"thus":[179],"enables":[180],"analysis":[182],"microbial":[184],"\u201ctransparent":[185],"matter,\u201d":[186],"already":[189],"described":[190],"earlier":[192],"research":[193],"have":[195],"not":[196],"yet":[197],"made":[198],"it":[199],"usable":[201],"annotations.":[202],"annotated":[204],"database":[207],"freely":[209],"available":[210],"at":[211],"https://services.bromberglab.org/fusion2ai":[212],"as":[214],"reference":[216],"DB":[217],"metagenome":[219],"https://services.bromberglab.org/mifaser":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-01T00:00:00"}