{"doi":"10.1093/nar/gkt1114","title":"RefSeq: an update on mammalian reference sequences","abstract":null,"journal":"Nucleic Acids Research","year":2014,"id":40317,"datarank":10.357963405167855,"base_score":6.923628628138427,"endowment":6.923628628138427,"self_citation_contribution":1.0385442942207643,"citation_network_contribution":9.31941911094709,"self_endowment_contribution":1.0385442942207643,"citer_contribution":9.31941911094709,"corpus_percentile":98.84737371393209,"corpus_rank":150,"citation_count":1015,"citer_count":100,"citers_with_citation_signal":100,"citers_with_endowment":100,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":58.3333,"fair_percentile":68.87417218543047,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":196131,"name":"Garth R. Brown","orcid":null,"position":1,"is_corresponding":false},{"id":196132,"name":"Susan M. Hiatt","orcid":null,"position":2,"is_corresponding":false},{"id":196133,"name":"Françoise Thibaud-Nissen","orcid":null,"position":3,"is_corresponding":false},{"id":196134,"name":"Alexander Astashyn","orcid":null,"position":4,"is_corresponding":false},{"id":166946,"name":"Olga Ermolaeva","orcid":null,"position":5,"is_corresponding":false},{"id":81090,"name":"Catherine M. Farrell","orcid":"0009-0003-3804-8528","position":6,"is_corresponding":false},{"id":81101,"name":"Jennifer Hart","orcid":null,"position":7,"is_corresponding":false},{"id":33149,"name":"Melissa J. Landrum","orcid":null,"position":8,"is_corresponding":false},{"id":166951,"name":"Kelly M. McGarvey","orcid":null,"position":9,"is_corresponding":false},{"id":75506,"name":"Michael R. Murphy","orcid":"0000-0002-0470-5791","position":10,"is_corresponding":false},{"id":107203,"name":"Nuala A. O’Leary","orcid":null,"position":11,"is_corresponding":false},{"id":166943,"name":"Shashikant Pujar","orcid":null,"position":12,"is_corresponding":false},{"id":81103,"name":"Bhanu Rajput","orcid":null,"position":13,"is_corresponding":false},{"id":166952,"name":"Sanjida H. Rangwala","orcid":null,"position":14,"is_corresponding":false},{"id":81104,"name":"Lillian D. Riddick","orcid":null,"position":15,"is_corresponding":false},{"id":196135,"name":"Andrei Shkeda","orcid":null,"position":16,"is_corresponding":false},{"id":196136,"name":"Hanzhen Sun","orcid":null,"position":17,"is_corresponding":false},{"id":196137,"name":"Pamela Tamez","orcid":null,"position":18,"is_corresponding":false},{"id":196138,"name":"Raymond E. Tully","orcid":null,"position":19,"is_corresponding":false},{"id":81088,"name":"Craig Wallin","orcid":null,"position":20,"is_corresponding":false},{"id":81105,"name":"David Webb","orcid":"0000-0003-4243-4002","position":21,"is_corresponding":false},{"id":166939,"name":"Janet Weber","orcid":null,"position":22,"is_corresponding":false},{"id":166940,"name":"Wendy Wu","orcid":null,"position":23,"is_corresponding":false},{"id":17114,"name":"Michael DiCuccio","orcid":"0000-0003-0585-2862","position":24,"is_corresponding":false},{"id":2129,"name":"Paul Kitts","orcid":null,"position":25,"is_corresponding":false},{"id":196139,"name":"Donna R. Maglott","orcid":null,"position":26,"is_corresponding":false},{"id":2099,"name":"Terence D. Murphy","orcid":"0000-0001-9311-9745","position":27,"is_corresponding":false},{"id":96415,"name":"James M. Ostell","orcid":null,"position":28,"is_corresponding":false},{"id":2100,"name":"Kim D. Pruitt","orcid":"0000-0001-7950-1374","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":6.920671504248683,"endowment":6.920671504248683,"datacite_reuse_total":25,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"24259432","pmcid":"PMC3965018","openalex_id":"https://openalex.org/W2136101247","authors":[],"funders":[{"funder_name":"Wellcome Trust","grant_id":"unidentified","title":"unidentified"},{"funder_name":"Wellcome Trust","grant_id":"","title":null},{"funder_name":"Intramural NIH HHS","grant_id":"","title":null},{"funder_name":"Wellcome Trust","grant_id":"","title":null},{"funder_name":"Intramural NIH HHS","grant_id":"","title":null}],"total_grants":5,"fwci":66.7286,"citation_percentile":0.99962318,"influential_citations":93,"citation_trend":[{"year":2013,"count":1},{"year":2014,"count":77},{"year":2015,"count":189},{"year":2016,"count":179},{"year":2017,"count":111},{"year":2018,"count":68},{"year":2019,"count":80},{"year":2020,"count":56},{"year":2021,"count":70},{"year":2022,"count":43},{"year":2023,"count":41},{"year":2024,"count":49},{"year":2025,"count":27},{"year":2026,"count":9}],"oa_status":"gold","license":"other-oa","oa_locations":[{"url":"https://academic.oup.com/nar/article-pdf/42/D1/D756/3584670/gkt1114.pdf","host_type":"journal"},{"url":"https://academic.oup.com/nar/article-pdf/42/D1/D756/3584670/gkt1114.pdf","host_type":"GOLD"},{"url":"https://academic.oup.com/nar/article-pdf/42/D1/D756/3584670/gkt1114.pdf","host_type":"publisher"},{"url":"http://academic.oup.com/nar/article-pdf/42/D1/D756/3584670/gkt1114.pdf","host_type":"publisher"},{"url":"https://doi.org/10.1093/nar/gkt1114","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/24259432","host_type":"repository"},{"url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.774.4466","host_type":""},{"url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.854.7234","host_type":""},{"url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.860.9452","host_type":""},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3965018","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC3965018","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC3965018?pdf=render","host_type":"Europe_PMC"},{"url":"http://dx.doi.org/10.1093/nar/gkt1114","host_type":""},{"url":"https://dx.doi.org/10.1093/nar/gkt1114","host_type":""}],"fields_of_study":["Genomics and Phylogenetic Studies","RNA and protein synthesis mechanisms","Machine Learning in Bioinformatics","Computer Science","Medicine","Biology","0301 basic medicine","0303 health sciences","03 medical and health sciences","Animals","Databases, Genetic","Eukaryota","Exons","Genome","Genomics","Humans","Internet","Mammals","Molecular Sequence Annotation","Proteins","RNA","Reference Standards"],"mesh_terms":["Animals","Exons","Humans","Mammals","Proteins","Reference Standards","RNA","Genome","Internet","Genomics","Databases, Genetic","Eukaryota","Molecular Sequence Annotation"],"keywords":["RefSeq","Annotation","Biology","Ensembl","Pipeline (software)","Computational biology","Genome project","Genome","Gene Annotation","Reference genome","Sequence (biology)","Genetics","Whole genome sequencing","Human genome","Gene","Bioinformatics","Genomics","Computer science","Mammals","Internet","Eukaryota","Proteins","Molecular Sequence Annotation","V. Human genome, model organisms, comparative genomics","Exons","Reference Standards","Databases, Genetic","Animals","Humans","RNA"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Partnerships for the goals"}],"linked_datasets":[{"doi":"10.6084/m9.figshare.12153867.v1","title":"Additional file 1 of DolphinNext: a distributed data processing platform for high throughput genomics","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.12153867","title":"Additional file 1 of DolphinNext: a distributed data processing platform for high throughput genomics","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.13632980.v1","title":"Additional file 1 of MicroExonator enables systematic discovery and quantification of microexons across mouse embryonic development","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.13632980","title":"Additional file 1 of MicroExonator enables systematic discovery and quantification of microexons across mouse embryonic development","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.13633004.v1","title":"Additional file 9 of MicroExonator enables systematic discovery and quantification of microexons across mouse embryonic development","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.13633004","title":"Additional file 9 of MicroExonator enables systematic discovery and quantification of microexons across mouse embryonic development","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14442922.v1","title":"Additional file 10 of Identification of X-chromosomal genes that drive sex differences in embryonic stem cells through a hierarchical CRISPR screening approach","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14442922","title":"Additional file 10 of Identification of X-chromosomal genes that drive sex differences in embryonic stem cells through a hierarchical CRISPR screening approach","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14442925.v1","title":"Additional file 1 of Identification of X-chromosomal genes that drive sex differences in embryonic stem cells through a hierarchical CRISPR screening approach","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14442925","title":"Additional file 1 of Identification of X-chromosomal genes that drive sex differences in embryonic stem cells through a hierarchical CRISPR screening approach","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14456934.v1","title":"Additional file 1 of FINDER: an automated software package to annotate eukaryotic genes from RNA-Seq data and associated protein sequences","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14456934","title":"Additional file 1 of FINDER: an automated software package to annotate eukaryotic genes from RNA-Seq data and associated protein sequences","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14456958.v1","title":"Additional file 9 of FINDER: an automated software package to annotate eukaryotic genes from RNA-Seq data and associated protein sequences","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.14456958","title":"Additional file 9 of FINDER: an automated software package to annotate eukaryotic genes from RNA-Seq data and associated protein sequences","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.19470326.v1","title":"Additional file 1 of Impact of gene annotation choice on the quantification of RNA-seq data","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.19470326","title":"Additional file 1 of Impact of gene annotation choice on the quantification of RNA-seq data","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586477.v1","title":"Additional file 1 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586477","title":"Additional file 1 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586480.v1","title":"Additional file 2 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586480","title":"Additional file 2 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586483.v1","title":"Additional file 3 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586483","title":"Additional file 3 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26614609.v1","title":"Additional file 1 of Gene-based burden scores identify rare variant associations for 28 blood biomarkers","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26614609","title":"Additional file 1 of Gene-based burden scores identify rare variant associations for 28 blood biomarkers","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26586486.v1","title":"Additional file 4 of Twist exome capture allows for lower average sequence coverage in clinical exome sequencing","publisher":"figshare","resource_type":"Dataset"}],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"refseq"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-12T04:35:11.321478Z","pmid":"24259432","pmcid":"PMC3965018","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":"gold","license":"other-oa","views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":65.0,"fair_a":72.5,"fair_i":62.5,"fair_r":33.3333,"fair_zscore":0.4373,"fair_rationale":{"fair_score":58.33,"has_llm":true,"dimensions":{"F":{"name":"Findable","score":65.0,"criteria":[{"key":"f_has_doi","label":"Has a persistent DOI","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"DOI present","rationale":null},{"key":"f_repository_presence","label":"Indexed in repositories / literature DBs","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"datacite=25, pmcid=True, pmid=True","rationale":null},{"key":"f_persistent_ids","label":"Resolvable scholarly identifiers (OpenAlex)","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"no OpenAlex id","rationale":null},{"key":"f_metadata_richness","label":"Rich, machine-readable metadata","kind":"llm","weight":1.0,"fraction":0.5,"signal":null,"rationale":"The paper mentions structured comments like 'Evidence Data' and 'RefSeq Attributes' with ECO identifiers, but provides no evidence that the metadata is machine-readable (e.g., in a standard schema like JSON-LD or RDF) or that the paper itself includes rich, structured metadata beyond human-readable text."}]},"A":{"name":"Accessible","score":72.5,"criteria":[{"key":"a_open_access","label":"Open Access / files deposited","kind":"deterministic","weight":1.5,"fraction":0.5,"signal":"files/OA location present but not flagged OA","rationale":null},{"key":"a_retrievable","label":"Free full text retrievable","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"14 OA location(s)","rationale":null},{"key":"a_access_protocol","label":"Clear data/code access protocol","kind":"llm","weight":1.0,"fraction":0.75,"signal":null,"rationale":"The paper clearly describes FTP and web access for RefSeq data, including URLs for downloads and a mail list, but does not explicitly state the license for access (though it mentions 'public domain' for the specific paper, not necessarily for all data) and lacks details on authentication or API endpoints for machine access."}]},"I":{"name":"Interoperable","score":62.5,"criteria":[{"key":"i_linked_data","label":"Linked datasets / DataCite relations","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"linked_datasets=0, datacite=25","rationale":null},{"key":"i_standard_ids","label":"References data via standard accessions","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"accessions=0, trials=0","rationale":null},{"key":"i_standards","label":"Standard formats, vocabularies & identifiers","kind":"llm","weight":1.0,"fraction":0.75,"signal":null,"rationale":"The paper uses standard identifiers (NCBI accessions, ECO IDs, RefSeq prefixes) and mentions community vocabularies, but does not demonstrate use of broad interoperability standards like Dublin Core for metadata or FAIR vocabularies beyond its own domain."}]},"R":{"name":"Reusable","score":33.33,"criteria":[{"key":"r_license","label":"Clear, open reuse license","kind":"deterministic","weight":1.5,"fraction":0.0,"signal":"no license","rationale":null},{"key":"r_downloads","label":"Demonstrated reuse (downloads)","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"downloads=0","rationale":null},{"key":"r_version","label":"Versioned / maintained","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"no version chain","rationale":null},{"key":"r_dataset","label":"Classified as a data resource","kind":"deterministic","weight":0.5,"fraction":1.0,"signal":"is_dataset","rationale":null},{"key":"r_reusability","label":"Data-availability statement, license & reproducibility","kind":"llm","weight":2.0,"fraction":0.5,"signal":null,"rationale":"The paper describes data availability via FTP and web, includes a brief statement about being 'public domain in the US' for the paper, but lacks a formal data-availability statement, explicit license for the data, and sufficient details to fully reproduce the analysis (e.g., exact pipeline version, full configuration)."}]}},"suggestions":["Include a formal data-availability statement with explicit license (e.g., CC0) for the RefSeq data and code.","Provide machine-readable metadata (e.g., DataCite XML or schema.org JSON-LD) and a persistent identifier for the dataset version.","Add a clear protocol for machine access, such as an API endpoint with authentication details and rate limits.","Specify the exact versions and parameters of the annotation pipeline used, to enable full reproducibility.","Use standard vocabulary URIs (e.g., from the Evidence Code Ontology) in a machine-readable format alongside the human-readable text."],"model":"deepseek/deepseek-v4-flash","agent_version":"fair_agent_v2","fulltext_source":"epmc_xml"},"fair_model":"deepseek/deepseek-v4-flash","fair_agent_version":"fair_agent_v2","fair_fulltext_source":"epmc_xml","fair_has_llm":true,"fair_computed_at":"2026-06-18T00:32:20.760680Z","clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}