{"doi":"10.1089/omi.2005.9.91","title":"Large-Scale, Multi-Genome Analysis of Alternate Open Reading Frames in Bacteria and Archaea","abstract":"<jats:p>Analysis of over 300,000 annotated genes in 105 bacterial and archaeal genomes reveals an\nunexpectedly high frequency of large (&gt;300 nucleotides) alternate open reading frames\n(ORFs). Especially notable is the very high frequency of alternate ORFs in frames +3 and\n–1 (where the annotated gene is defined as frame +1). The occurrence of alternate ORFs\nis correlated with genomic G+C content and is strongly influenced by synonymous codon\nusage bias. The frequency of alternate ORFs in frame –1 is also influenced by the occurrence\nof codons encoding leucine and serine in frame +1. Although some alternate ORFs\nhave been shown to encode proteins, many others are probably not expressed because they\nlack appropriate signals for transcription and translation. These latter can be mis-annotated\nby automatic gene finding programs leading to errors in public databases. Especially prone\nto mis-annotation is frame –1, because it exhibits a potential codon usage and theoretical\ncapacity to encode proteins with an amino acid composition most similar to real genes. Some\nalternate ORFs are conserved across bacterial or archaeal species, and can give rise to misannotated\n\"conserved hypothetical\" genes, while others are unique to a genome and are\nmisidentified as \"hypothetical orphan\" genes, contributing significantly to the orphan gene\nparadox.</jats:p>","journal":"OMICS: A Journal of Integrative Biology","year":2005,"id":40294,"datarank":1.8235698224893468,"base_score":3.367295829986474,"endowment":3.367295829986474,"self_citation_contribution":0.5050943744979712,"citation_network_contribution":1.3184754479913756,"self_endowment_contribution":0.5050943744979712,"citer_contribution":1.3184754479913756,"corpus_percentile":null,"corpus_rank":null,"citation_count":28,"citer_count":22,"citers_with_citation_signal":18,"citers_with_endowment":18,"datacite_reuse_total":0,"is_dataset":false,"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":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":196057,"name":"Gonzalo Riadi","orcid":null,"position":1,"is_corresponding":false},{"id":196058,"name":"Daniela Aliaga","orcid":null,"position":2,"is_corresponding":false},{"id":196059,"name":"Ryan Lieph","orcid":null,"position":3,"is_corresponding":false},{"id":196060,"name":"David S. Holmes","orcid":null,"position":4,"is_corresponding":false},{"id":196056,"name":"Felipe Veloso","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":3.367295829986474,"endowment":3.367295829986474,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"15805780","pmcid":null,"openalex_id":"https://openalex.org/W2017335389","authors":[],"funders":[],"total_grants":0,"fwci":0.7584,"citation_percentile":0.68636868,"influential_citations":1,"citation_trend":[{"year":2012,"count":3},{"year":2018,"count":1},{"year":2019,"count":3},{"year":2020,"count":1},{"year":2021,"count":1},{"year":2022,"count":1},{"year":2023,"count":1},{"year":2024,"count":3},{"year":2026,"count":1}],"oa_status":"green","license":"other-oa","oa_locations":[{"url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3265885","host_type":"repository"},{"url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3265885","host_type":"repository"},{"url":"https://journals.sagepub.com/doi/pdf/10.1089/omi.2005.9.91","host_type":"publisher"},{"url":"https://doi.org/10.1089/omi.2005.9.91","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/15805780","host_type":"repository"},{"url":"http://hdl.handle.net/10533/176875","host_type":"repository"}],"fields_of_study":["RNA and protein synthesis mechanisms","Genomics and Phylogenetic Studies","Bacteriophages and microbial interactions","Medicine","Biology","Environmental Science","Algorithms","Base Composition","Codon","Codon, Terminator","Genes, Archaeal","Genes, Bacterial","Genetic Techniques","Genome, Archaeal","Genome, Bacterial","Genomics","Leucine","Models, Genetic","Models, Statistical","Open Reading Frames","Protein Biosynthesis","Sequence Analysis, DNA","Transcription, Genetic"],"mesh_terms":["Algorithms","Base Composition","Codon","Genes, Bacterial","Genetic Techniques","Leucine","Models, Genetic","Transcription, Genetic","Protein Biosynthesis","Models, Statistical","Open Reading Frames","Genome, Bacterial","Sequence Analysis, DNA","Codon, Terminator","Genes, Archaeal","Genome, Archaeal","Genomics"],"keywords":["ORFS","Open reading frame","Biology","Genetics","Gene","Genome","ENCODE","Codon usage bias","Computational biology","Peptide sequence"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Quality Education"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-12T04:17:47.425011Z","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":[]}