{"id":"https://openalex.org/W7155385127","doi":"https://doi.org/10.48550/arxiv.2604.20782","title":"LAFA: A Framework for Reproducible Longitudinal Assessment of Protein Function Annotation Models","display_name":"LAFA: A Framework for Reproducible Longitudinal Assessment of Protein Function Annotation Models","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155385127","doi":"https://doi.org/10.48550/arxiv.2604.20782"},"language":"en","primary_location":{"id":"pmh:oai:pubmedcentral.nih.gov:13131834","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13131834/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13131834/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134418912","display_name":"An Phan","orcid":"https://orcid.org/0009-0004-0154-076X","observed_orcids":["https://orcid.org/0009-0004-0154-076X"]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phan, An","raw_affiliation_strings":["Department of Veterinary Microbiology and Preventive Medicine , Iowa State University , 50011 , Iowa , United States,","Program in Bioinformatics and Computational Biology , Iowa State University , 50011 , Iowa , United States,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Veterinary Microbiology and Preventive Medicine , Iowa State University , 50011 , Iowa , United States,","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Program in Bioinformatics and Computational Biology , Iowa State University , 50011 , Iowa , United States,","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134383062","display_name":"Yanli Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Yanli","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science , University of Missouri , 65211 , Missouri , United States,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science , University of Missouri , 65211 , Missouri , United States,","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boadu, Frimpong","raw_affiliation_strings":["Microsoft Corporation , 98052 , Washington ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation , 98052 , Washington ,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134405508","display_name":"Jianlin Cheng","orcid":null,"observed_orcids":[]},"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":["Department of Electrical Engineering and Computer Science , University of Missouri , 65211 , Missouri , United States,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science , University of Missouri , 65211 , Missouri , United States,","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051324698","display_name":"Predrag Radivojac A","orcid":"https://orcid.org/0000-0002-6769-0793","observed_orcids":["https://orcid.org/0000-0002-6769-0793"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radivojac, Predrag","raw_affiliation_strings":["Khoury College of Computer Sciences , Northeastern University , 02115 , Massachusetts , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences , Northeastern University , 02115 , Massachusetts , United States","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041597050","display_name":"Iddo Friedberg","orcid":"https://orcid.org/0000-0002-1789-8000","observed_orcids":["https://orcid.org/0000-0002-1789-8000"]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Friedberg, Iddo","raw_affiliation_strings":["Department of Veterinary Microbiology and Preventive Medicine , Iowa State University , 50011 , Iowa , United States,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Veterinary Microbiology and Preventive Medicine , Iowa State University , 50011 , Iowa , United States,","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":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":0.6098999977111816,"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":0.6098999977111816,"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":0.2849000096321106,"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":0.05730000138282776,"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":0.9800000190734863},{"id":"https://openalex.org/keywords/protein-function-annotation","display_name":"protein annotation","score":0.8289999961853027},{"id":"https://openalex.org/keywords/cafa","display_name":"CAFA","score":0.7139999866485596},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.7179999947547913},{"id":"https://openalex.org/keywords/longitudinal-assessment","display_name":"longitudinal assessment","score":0.7300000190734863},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.9570000171661377}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8177000284194946},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.7121000289916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960999965667725},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6427000164985657},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.5407999753952026},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.2989000082015991},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:pubmedcentral.nih.gov:13131834","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13131834/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Text"},{"id":"pmh:oai:arXiv.org:2604.20782","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.20782","pdf_url":"https://arxiv.org/pdf/2604.20782","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.20782","doi":"https://doi.org/10.48550/arxiv.2604.20782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:13131834","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13131834/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3619790786","display_name":"Deep transformers for integrating protein sequence, structure and interaction data to predict function","funder_award_id":"2308699","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7384501959","display_name":null,"funder_award_id":"REI/1/5235-01-01","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155385127.pdf","grobid_xml":"https://content.openalex.org/works/W7155385127.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160215314","https://openalex.org/W7160867976","https://openalex.org/W7172408629","https://openalex.org/W2117486996","https://openalex.org/W6903736452","https://openalex.org/W4319069621","https://openalex.org/W2162813650","https://openalex.org/W2891230876","https://openalex.org/W1872414266","https://openalex.org/W6957923266"],"abstract_inverted_index":{"Motivation:":[0],"Protein":[1,96],"function":[2,39,85,109,119,153],"prediction":[3,40,110,120],"is":[4,23,70,160],"a":[5,24,48,103,114,143],"challenging":[6],"task":[7],"and":[8,55,59,81,124,141,146,156],"an":[9,30],"open":[10],"problem":[11],"in":[12,51,151],"computational":[13,35],"biology.":[14],"The":[15],"Critical":[16],"Assessment":[17,94],"of":[18,34,61,77,95,117,128,149],"protein":[19,38,108,152],"Function":[20,97],"Annotation":[21,98],"(CAFA)":[22],"triennial,":[25],"community-driven":[26],"initiative":[27],"that":[28],"provides":[29,113],"independent,":[31],"large-scale":[32],"evaluation":[33,76,116,165],"methods":[36,80],"for":[37,73,107],"through":[41],"time-delayed":[42],"benchmarking":[43,105],"experiments.":[44],"CAFA":[45,67],"has":[46],"played":[47],"key":[49],"role":[50],"highlighting":[52],"high-performing":[53],"methodologies":[54],"fostering":[56],"detailed":[57],"analysis":[58],"exchange":[60],"ideas.":[62],"However,":[63],"outside":[64],"the":[65,74,92],"periodic":[66],"challenges,":[68],"there":[69],"no":[71],"platform":[72],"continuous":[75,115],"newly":[78],"developed":[79],"tracking":[82],"performance":[83,130],"as":[84,102],"annotations":[86],"accumulate.":[87],"Results:":[88],"Here":[89],"we":[90],"introduce":[91],"Longitudinal":[93],"Models":[99],"server":[100],"(LAFA)":[101],"persistent":[104],"system":[106],"methods.":[111],"LAFA":[112,135,159],"containerized":[118],"methods,":[121],"enabling":[122],"up-to-date":[123],"robust":[125],"comparative":[126],"assessment":[127],"method":[129],"under":[131],"evolving":[132],"ground":[133],"truth.":[134],"accelerates":[136],"methodological":[137],"iteration,":[138],"supports":[139],"reproducibility,":[140],"offers":[142],"more":[144],"dynamic":[145],"fine-grained":[147],"view":[148],"progress":[150],"prediction.":[154],"Code":[155],"Data":[157],"Availability:":[158],"available":[161],"at":[162,170],"https://functionbench.net/.":[163],"Detailed":[164],"results":[166],"can":[167],"be":[168],"found":[169],"https://github.com/anphan0828/CAFA_forever":[171]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-04-24T00:00:00"}