{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T10:25:13Z","timestamp":1768472713425,"version":"3.49.0"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"19","license":[{"start":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T00:00:00Z","timestamp":1593648000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Ministry of Economy and Competitiveness of the Spanish Government","award":["BFU2016-77297-P"],"award-info":[{"award-number":["BFU2016-77297-P"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Short bioactive peptides encoded by small open reading frames (sORFs) play important roles in eukaryotes. Bioinformatics prediction of ORFs is an early step in a genome sequence analysis, but sORFs encoding short peptides, often using non-AUG initiation codons, are not easily discriminated from false ORFs occurring by chance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>AnABlast is a computational tool designed to highlight putative protein-coding regions in genomic DNA sequences. This protein-coding finder is independent of ORF length and reading frame shifts, thus making of AnABlast a potentially useful tool to predict sORFs. Using this algorithm, here, we report the identification of 82 putative new intergenic sORFs in the Caenorhabditis elegans genome. Sequence similarity, motif presence, expression data and RNA interference experiments support that the underlined sORFs likely encode functional peptides, encouraging the use of AnABlast as a new approach for the accurate prediction of intergenic sORFs in annotated eukaryotic genomes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>AnABlast is freely available at http:\/\/www.bioinfocabd.upo.es\/ab\/. The C.elegans genome browser with AnABlast results, annotated genes and all data used in this study is available at http:\/\/www.bioinfocabd.upo.es\/celegans.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa608","type":"journal-article","created":{"date-parts":[[2020,6,23]],"date-time":"2020-06-23T11:44:50Z","timestamp":1592912690000},"page":"4827-4832","source":"Crossref","is-referenced-by-count":9,"title":["Using AnABlast for intergenic sORF prediction in the <i>Caenorhabditis elegans<\/i> genome"],"prefix":"10.1093","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1774-2580","authenticated-orcid":false,"given":"C S","family":"Casimiro-Soriguer","sequence":"first","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M M","family":"Rigual","sequence":"additional","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A M","family":"Brokate-Llanos","sequence":"additional","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M J","family":"Mu\u00f1oz","sequence":"additional","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A","family":"Garz\u00f3n","sequence":"additional","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3343-2822","authenticated-orcid":false,"given":"A J","family":"P\u00e9rez-Pulido","sequence":"additional","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3851-7393","authenticated-orcid":false,"given":"J","family":"Jimenez","sequence":"additional","affiliation":[{"name":"Centro Andaluz de Biolog\u00eda del Desarrollo (CABD, UPO-CSIC), Universidad Pablo de Olavide , 41013 Sevilla, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,7,2]]},"reference":[{"key":"2023062408060345000_btaa608-B1","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/978-1-61779-582-4_6","article-title":"Gene prediction","volume":"855","author":"Alioto","year":"2012","journal-title":"Methods Mol. Biol. (Clifton, N.J.)"},{"key":"2023062408060345000_btaa608-B2","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2023062408060345000_btaa608-B3","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1038\/nrg3520","article-title":"Emerging evidence for functional peptides encoded by short open reading frames","volume":"15","author":"Andrews","year":"2014","journal-title":"Nat. Rev. Genet"},{"key":"2023062408060345000_btaa608-B4","doi-asserted-by":"crossref","first-page":"e03528","DOI":"10.7554\/eLife.03528","article-title":"Extensive translation of small open reading frames revealed by Poly-Ribo-Seq","volume":"3","author":"Aspden","year":"2014","journal-title":"Elife"},{"key":"2023062408060345000_btaa608-B6","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1038\/nmeth.3688","article-title":"Detecting actively translated open reading frames in ribosome profiling data","volume":"13","author":"Calviello","year":"2016","journal-title":"Nat. Methods"},{"key":"2023062408060345000_btaa608-B7","doi-asserted-by":"crossref","first-page":"111973","DOI":"10.1016\/j.yexcr.2020.111973","article-title":"Non-AUG start codons: expanding and regulating the small and alternative ORFeome","volume":"391","author":"Cao","year":"2020","journal-title":"Exp. Cell. Res"},{"key":"2023062408060345000_btaa608-B8","doi-asserted-by":"crossref","first-page":"1700071","DOI":"10.1002\/pmic.201700071","article-title":"Sma3s: a universal tool for easy functional annotation of proteomes and transcriptomes","volume":"17","author":"Casimiro-Soriguer","year":"2017","journal-title":"Proteomics"},{"key":"2023062408060345000_btaa608-B9","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1186\/s12864-020-6632-y","article-title":"Ancient evolutionary signals of protein-coding sequences allow the discovery of new genes in the Drosophila melanogaster genome","volume":"21","author":"Casimiro-Soriguer","year":"2020","journal-title":"BMC Genomics"},{"key":"2023062408060345000_btaa608-B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1021\/acs.jproteome.7b00707","article-title":"Mining for small translated ORFs","volume":"17","author":"Chugunova","year":"2018","journal-title":"J. Proteome Res"},{"key":"2023062408060345000_btaa608-B11","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1038\/448855a","article-title":"RNA interference: hitting the on switch","volume":"448","author":"Check","year":"2007","journal-title":"Nature"},{"key":"2023062408060345000_btaa608-B12","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/nrm.2017.58","article-title":"Classification and function of small open reading frames","volume":"18","author":"Couso","year":"2017","journal-title":"Nat. Rev. Mol. Cell. Biol"},{"key":"2023062408060345000_btaa608-B13","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1186\/1471-2164-14-648","article-title":"Combining in silico prediction and ribosome profiling in a genome-wide search for novel putatively coding sORFs","volume":"14","author":"Crapp\u00e9","year":"2013","journal-title":"BMC Genomics"},{"key":"2023062408060345000_btaa608-B14","doi-asserted-by":"crossref","first-page":"e1000176","DOI":"10.1371\/journal.pcbi.1000176","article-title":"Differentiating protein-coding and noncoding RNA: challenges and ambiguities","volume":"4","author":"Dinger","year":"2008","journal-title":"PLoS Comput. Biol"},{"key":"2023062408060345000_btaa608-B15","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1080\/02763869.2019.1548896","article-title":"WormBase: a model organism database","volume":"38","author":"Dubaj Price","year":"2019","journal-title":"Med. Ref. Serv. Q"},{"key":"2023062408060345000_btaa608-B16","doi-asserted-by":"crossref","first-page":"D427","DOI":"10.1093\/nar\/gky995","article-title":"The Pfam protein families database in 2019","volume":"47","author":"El-Gebali","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023062408060345000_btaa608-B17","doi-asserted-by":"crossref","first-page":"e50609","DOI":"10.1371\/journal.pone.0050609","article-title":"Evaluating high-throughput ab initio gene finders to discover proteins encoded in eukaryotic pathogen genomes missed by laboratory techniques","volume":"7","author":"Goodswen","year":"2012","journal-title":"PLoS One"},{"key":"2023062408060345000_btaa608-B19","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1093\/bioinformatics\/btp688","article-title":"sORF finder: a program package to identify small open reading frames with high coding potential","volume":"26","author":"Hanada","year":"2010","journal-title":"Bioinformatics"},{"key":"2023062408060345000_btaa608-B20","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.tplants.2015.11.005","article-title":"The emerging world of small ORFs","volume":"21","author":"Hellens","year":"2016","journal-title":"Trends Plant Sci"},{"key":"2023062408060345000_btaa608-B22","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.ydbio.2018.11.024","article-title":"Multi-modal regulation of C. elegans hermaphrodite spermatogenesis by the GLD-1-FOG-2 complex","volume":"446","author":"Hu","year":"2019","journal-title":"Dev. Biol"},{"key":"2023062408060345000_btaa608-B23","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1126\/science.1168978","article-title":"Genome-wide analysis in vivo of translation with nucleotide resolution using ribosome profiling","volume":"324","author":"Ingolia","year":"2009","journal-title":"Science"},{"key":"2023062408060345000_btaa608-B24","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1093\/dnares\/dsv025","article-title":"AnABlast: a new in silico strategy for the genome-wide search of novel genes and fossil regions","volume":"22","author":"Jimenez","year":"2015","journal-title":"DNA Res"},{"key":"2023062408060345000_btaa608-B25","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1038\/nature01278","article-title":"Systematic functional analysis of the Caenorhabditis elegans genome using RNAi","volume":"421","author":"Kamath","year":"2003","journal-title":"Nature"},{"key":"2023062408060345000_btaa608-B26","doi-asserted-by":"crossref","first-page":"D574","DOI":"10.1093\/nar\/gkv1209","article-title":"Ensembl genomes 2016: more genomes, more complexity","volume":"44","author":"Kersey","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023062408060345000_btaa608-B27","doi-asserted-by":"crossref","first-page":"4655","DOI":"10.1242\/dev.02650","article-title":"Bchs, a BEACH domain protein, antagonizes Rab11 in synapse morphogenesis and other developmental events","volume":"133","author":"Khodosh","year":"2006","journal-title":"Development"},{"key":"2023062408060345000_btaa608-B28","doi-asserted-by":"crossref","first-page":"Reviews 3002","DOI":"10.1186\/gb-2000-1-5-reviews3002","article-title":"The F-box protein family","volume":"1","author":"Kipreos","year":"2000","journal-title":"Genome Biol"},{"key":"2023062408060345000_btaa608-B29","doi-asserted-by":"crossref","first-page":"1700015","DOI":"10.1002\/bies.201700015","article-title":"A tool for integrating genetic and mass spectrometry-based peptide data: proteogenomics viewer: PV: a genome browser-like tool, which includes MS data visualization and peptide identification parameters","volume":"39","author":"Kroll","year":"2017","journal-title":"Bioessays"},{"key":"2023062408060345000_btaa608-B30","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1093\/bioinformatics\/16.12.1105","article-title":"Saturated BLAST: an automated multiple intermediate sequence search used to detect distant homology","volume":"16","author":"Li","year":"2000","journal-title":"Bioinformatics"},{"key":"2023062408060345000_btaa608-B31","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1534\/genetics.115.180208","article-title":"The transgenic RNAi project at Harvard Medical School: resources and validation","volume":"201","author":"Lizabeth","year":"2015","journal-title":"Genetics"},{"key":"2023062408060345000_btaa608-B32","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/978-1-4939-9173-0_8","article-title":"Multi-genome annotation with AUGUSTUS","volume":"1962","author":"Nachtweide","year":"2019","journal-title":"Methods Mol. Biol"},{"key":"2023062408060345000_btaa608-B33","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1038\/nmeth.3144","article-title":"Proteogenomics: concepts, applications and computational strategies","volume":"11","author":"Nesvizhskii","year":"2014","journal-title":"Nat. Methods"},{"key":"2023062408060345000_btaa608-B34","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.mrfmmm.2015.06.006","article-title":"The BAH domain of BAF180 is required for PCNA ubiquitination","volume":"779","author":"Niimi","year":"2015","journal-title":"Mutat. Res"},{"key":"2023062408060345000_btaa608-B35","doi-asserted-by":"crossref","first-page":"D497","DOI":"10.1093\/nar\/gkx1130","article-title":"An update on sORFs.org: a repository of small ORFs identified by ribosome profiling","volume":"46","author":"Olexiouk","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023062408060345000_btaa608-B36","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1093\/nar\/gkz734","article-title":"Alternative ORFs and small ORFs: shedding light on the dark proteome","volume":"48","author":"Orr","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023062408060345000_btaa608-B37","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1093\/bioinformatics\/btg414","article-title":"AnaGram: protein function assignment","volume":"20","author":"P\u00e9rez","year":"2004","journal-title":"Bioinformatics"},{"key":"2023062408060345000_btaa608-B38","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1016\/j.tibs.2016.05.003","article-title":"New peptides under the s(ORF)ace of the genome","volume":"41","author":"Pueyo","year":"2016","journal-title":"Trends Biochem. Sci"},{"key":"2023062408060345000_btaa608-B39","first-page":"5, e13328","article-title":"Thousands of novel translated open reading frames in humans inferred by ribosome footprint profiling","author":"Raj","year":"2016","journal-title":"Elife"},{"key":"2023062408060345000_btaa608-B40","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/978-1-4939-9173-0_12","article-title":"AnABlast: re-searching for protein-coding sequences in genomic regions","volume":"1962","author":"Rubio","year":"2019","journal-title":"Methods Mol. Biol"},{"key":"2023062408060345000_btaa608-B41","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.tig.2018.12.003","article-title":"Translation of small open reading frames: roles in regulation and evolutionary innovation","volume":"35","author":"Ruiz-Orera","year":"2019","journal-title":"Trends Genet"},{"key":"2023062408060345000_btaa608-B43","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1093\/bioinformatics\/btr275","article-title":"Identification of prokaryotic small proteins using a comparative genomic approach","volume":"27","author":"Samayoa","year":"2011","journal-title":"Bioinformatics"},{"key":"2023062408060345000_btaa608-B44","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nchembio.1120","article-title":"Peptidomic discovery of short open reading frame-encoded peptides in human cells","volume":"9","author":"Slavoff","year":"2013","journal-title":"Nat. Chem. Biol"},{"key":"2023062408060345000_btaa608-B46","first-page":"1","article-title":"Maintenance of C. elegans","volume":"11","author":"Stiernagle","year":"2006","journal-title":"WormBook"},{"key":"2023062408060345000_btaa608-B47","doi-asserted-by":"crossref","first-page":"D158","DOI":"10.1093\/nar\/gkw1099","article-title":"UniProt: the universal protein knowledgebase","volume":"45","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023062408060345000_btaa608-B48","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1007\/BF02198848","article-title":"Search for ancient patterns in protein sequences","volume":"42","author":"Thode","year":"1996","journal-title":"J. Mol. Evol"},{"key":"2023062408060345000_btaa608-B50","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.omtn.2019.06.008","article-title":"Gene amplification-driven long noncoding RNA SNHG17 regulates cell proliferation and migration in human non-small-cell lung cancer","volume":"17","author":"Xu","year":"2019","journal-title":"Mol. Ther. Nucleic Acids"},{"key":"2023062408060345000_btaa608-B51","doi-asserted-by":"crossref","first-page":"211","DOI":"10.3109\/10409238.2012.742035","article-title":"Structure and function of the BAH domain in chromatin biology","volume":"48","author":"Yang","year":"2013","journal-title":"Crit. Rev. Biochem. Mol. Biol"},{"key":"2023062408060345000_btaa608-B52","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1101\/gr.244830.118","article-title":"Recompleting the Caenorhabditis elegans genoma","volume":"29","author":"Yoshimura","year":"2019","journal-title":"Genome Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa608\/33646448\/btaa608.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/19\/4827\/50692523\/btaa608.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/19\/4827\/50692523\/btaa608.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T23:25:58Z","timestamp":1687649158000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/19\/4827\/5866540"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,7,2]]},"references-count":46,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2020,12,8]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa608","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,10,1]]},"published":{"date-parts":[[2020,7,2]]}}}