{"id":"https://openalex.org/W7204603314","doi":"https://doi.org/10.5281/zenodo.22139107","title":"[Dataset] [TransFew] Improving protein function prediction by learning and integrating representations of protein sequences and function labels","display_name":"[Dataset] [TransFew] Improving protein function prediction by learning and integrating representations of protein sequences and function labels","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204603314","doi":"https://doi.org/10.5281/zenodo.22139107"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22139107","doi":"https://doi.org/10.5281/zenodo.22139107","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22139107","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.22139107","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":[{"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":"Boadu, Frimpong","raw_affiliation_strings":["University of Missouri"],"raw_orcid":"https://orcid.org/0000-0002-4464-6191","affiliations":[{"raw_affiliation_string":"University of Missouri","institution_ids":["https://openalex.org/I76835614"]}]},{"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":["https://openalex.org/I76835614"],"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":0.9794999957084656,"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":0.9794999957084656,"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":0.00860000029206276,"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":0.004699999932199717,"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":0.9990000128746033},{"id":"https://openalex.org/keywords/protein-sequences","display_name":"protein sequences","score":0.6679999828338623},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7519999742507935},{"id":"https://openalex.org/keywords/label-representation","display_name":"label representation","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6557999849319458},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.64410001039505},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.6176000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5521000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296000242233276},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.35929998755455017},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.33239999413490295},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27379998564720154},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C2988375501","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein stability","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22139107","doi":"https://doi.org/10.5281/zenodo.22139107","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22139107","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.22139108","doi":"https://doi.org/10.5281/zenodo.22139108","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22139108","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.22139107","doi":"https://doi.org/10.5281/zenodo.22139107","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22139107","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/W4401660139","https://openalex.org/W7204745425","https://openalex.org/W6891528381","https://openalex.org/W7204604672","https://openalex.org/W7106496192","https://openalex.org/W2884144156","https://openalex.org/W4360938460","https://openalex.org/W3119766474","https://openalex.org/W4283588627","https://openalex.org/W1661130597"],"abstract_inverted_index":{"This":[0],"is":[1],"the":[2,5],"dataset":[3],"for":[4],"paper,":[6],"Improving":[7,23],"protein":[8,17,24,33],"function":[9,20,25,36],"prediction":[10,26],"by":[11,27],"learning":[12,28],"and":[13,19,29,35],"integrating":[14,30],"representations":[15,31],"of":[16,32],"sequences":[18,34],"labels.":[21],"TransFew:":[22],"labels":[37],"GitHub":[38],"Repository:":[39],"TransFew":[40],"Journal":[41],"Publication:":[42],"Bioinformatics":[43],"Advances":[44],"BioRxiv":[45,47],"Preprint:":[46],"Supplementary":[48,50],"materials:":[49],"Materials":[51]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-29T00:00:00"}