{"id":"https://openalex.org/W7204745425","doi":"https://doi.org/10.5281/zenodo.22137308","title":"[Training Dataset] [FunBind]A unified multimodal model for generalizable zero-shot and supervised protein function prediction","display_name":"[Training Dataset] [FunBind]A unified multimodal model for generalizable zero-shot and supervised protein function prediction","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204745425","doi":"https://doi.org/10.5281/zenodo.22137308"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22137308","doi":"https://doi.org/10.5281/zenodo.22137308","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22137308","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22137308","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053602445","display_name":"Frimpong Boadu","orcid":"https://orcid.org/0000-0002-4464-6191","observed_orcids":["https://orcid.org/0000-0002-4464-6191"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boadu, Frimpong","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4464-6191","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067946378","display_name":"Yanli Wang","orcid":"https://orcid.org/0000-0001-7864-826X","observed_orcids":["https://orcid.org/0000-0001-7864-826X","https://orcid.org/0009-0001-6802-4573"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"wang, yanli","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7864-826X","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044354277","display_name":"Jianlin Jack Cheng","orcid":"https://orcid.org/0000-0003-0305-2853","observed_orcids":["https://orcid.org/0000-0003-0305-2853"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng, Jianlin","raw_affiliation_strings":["University of Missouri"],"raw_orcid":"https://orcid.org/0000-0003-0305-2853","affiliations":[{"raw_affiliation_string":"University of Missouri","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9595000147819519,"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":0.9595000147819519,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.021800000220537186,"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":0.007899999618530273,"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/protein-function-prediction","display_name":"protein function prediction","score":0.9229999780654907},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.7170000076293945},{"id":"https://openalex.org/keywords/multimodal-models","display_name":"multimodal models","score":0.7329999804496765},{"id":"https://openalex.org/keywords/training-data","display_name":"training data","score":0.753000020980835},{"id":"https://openalex.org/keywords/protein-sequences","display_name":"protein sequences","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5697000026702881},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4542999863624573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22137308","doi":"https://doi.org/10.5281/zenodo.22137308","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22137308","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22137309","doi":"https://doi.org/10.5281/zenodo.22137309","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22137309","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22137308","doi":"https://doi.org/10.5281/zenodo.22137308","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22137308","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204604672","https://openalex.org/W4410349126","https://openalex.org/W7106496192","https://openalex.org/W6968297698","https://openalex.org/W6891528381","https://openalex.org/W2884144156","https://openalex.org/W3119766474","https://openalex.org/W4412131028","https://openalex.org/W4415080590","https://openalex.org/W7223177203"],"abstract_inverted_index":{"This":[0],"dataset":[1],"contains":[2],"the":[3],"training":[4],"data":[5],"for":[6,13,26],"FunBind,":[7],"a":[8],"unified":[9],"multimodal":[10],"AI":[11],"model":[12],"generalizable":[14],"zero-shot":[15],"and":[16,29],"supervised":[17],"protein":[18],"function":[19],"prediction.":[20],"FunBind:":[21],"A":[22],"Unified":[23],"Multimodal":[24],"Model":[25],"Generalizable":[27],"Zero-Shot":[28],"Supervised":[30],"Protein":[31],"Function":[32],"Prediction":[33],"GitHub":[34],"Repository:":[35],"FunBind":[36],"Journal":[37],"Publication:":[38],"Bioinformatics":[39],"BioRxiv":[40,42],"Preprint:":[41],"Supplementary":[43,45],"materials:":[44],"Materials":[46]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-01T00:00:00"}