{"doi":"10.1101/473488","title":"Hayai-Annotation Plants: an ultra-fast and comprehensive gene annotation system in plants","abstract":"<jats:title>Summary</jats:title>\n                <jats:p>\n                  Hayai-Annotation Plants is a browser-based interface for an ultra-fast and accurate gene annotation system for plant species using R. The pipeline combines the sequence-similarity searches, using USEARCH against UniProtKB (taxonomy Embryophyta), with a functional annotation step. Hayai-Annotation Plants provides five layers of annotation: 1) gene name; 2) gene ontology terms consisting of its three main domains (Biological Process, Molecular Function, and Cellular Component); 3) enzyme commission number; 4) protein existence level; 5) and evidence type. In regard to speed and accuracy, Hayai-Annotation Plants annotated\n                  <jats:italic>Arabidopsis thaliana</jats:italic>\n                  (Araport11, representative peptide sequences) within five minutes with an accuracy of 96.4 %.\n                </jats:p>\n                <jats:sec>\n                  <jats:title>Availability and Implementation</jats:title>\n                  <jats:p>\n                    The software is implemented in R and runs on Macintosh and Linux systems. It is freely available at\n                    <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" ext-link-type=\"uri\" xlink:href=\"https://github.com/kdri-genomics/Hayai-Annotation-Plants\">https://github.com/kdri-genomics/Hayai-Annotation-Plants</jats:ext-link>\n                    under the GPLv3 license.\n                  </jats:p>\n                </jats:sec>","journal":null,"year":null,"id":16005,"datarank":0.26876392038420827,"base_score":1.791759469228055,"endowment":1.791759469228055,"self_citation_contribution":0.26876392038420827,"citation_network_contribution":0.0,"self_endowment_contribution":0.26876392038420827,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":5,"citer_count":1,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":119794,"name":"Kenta Shirasawa","orcid":"0000-0001-7880-6221","position":1,"is_corresponding":false},{"id":119795,"name":"Hideki Hirakawa","orcid":null,"position":2,"is_corresponding":false},{"id":119796,"name":"Sachiko Isobe","orcid":"0000-0002-9555-5054","position":3,"is_corresponding":false},{"id":119793,"name":"Andrea Ghelfi","orcid":"0000-0001-9617-3309","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":1.791759469228055,"endowment":1.791759469228055,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"21071399","pmcid":null,"openalex_id":"https://openalex.org/W2901823680","authors":[],"funders":[],"total_grants":0,"fwci":null,"citation_percentile":null,"influential_citations":1,"citation_trend":[{"year":2019,"count":2},{"year":2023,"count":1},{"year":2024,"count":2}],"oa_status":"green","license":"cc-by-nc","oa_locations":[{"url":"https://www.biorxiv.org/content/biorxiv/early/2018/11/20/473488.full.pdf","host_type":"repository"},{"url":"https://www.biorxiv.org/content/biorxiv/early/2018/11/20/473488.full.pdf","host_type":"GREEN"},{"url":"https://www.biorxiv.org/content/biorxiv/early/2018/11/20/473488.full.pdf","host_type":"repository"},{"url":"https://syndication.highwire.org/content/doi/10.1101/473488","host_type":"publisher"},{"url":"https://doi.org/10.1101/473488","host_type":"repository"}],"fields_of_study":["Genomics and Phylogenetic Studies","Gene expression and cancer classification","Plant-Microbe Interactions and Immunity","Biology","Computer Science","Environmental Science"],"mesh_terms":[],"keywords":["Annotation","UniProt","Gene Annotation","Computer science","Pipeline (software)","Computational biology","Arabidopsis","Genomics","Biology","Gene","Information retrieval","Genome","Artificial intelligence","Genetics","Programming language"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-01T19:53:31.694805Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}