{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T23:25:02Z","timestamp":1783812302342,"version":"3.55.0"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T00:00:00Z","timestamp":1693440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HG010040"],"award-info":[{"award-number":["R01HG010040"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["391397397"],"award-info":[{"award-number":["391397397"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["277249973"],"award-info":[{"award-number":["277249973"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"name":"US National Institute of Health"},{"name":"Government of Mecklenburg-Vorpommern","award":["Project Data Competency"],"award-info":[{"award-number":["Project Data Competency"]}]},{"DOI":"10.13039\/501100018934","name":"Universit\u00e4t Greifswald","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018934","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The Earth Biogenome Project has rapidly increased the number of available eukaryotic genomes, but most released genomes continue to lack annotation of protein-coding genes. In addition, no transcriptome data is available for some genomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Various gene annotation tools have been developed but each has its limitations. Here, we introduce GALBA, a fully automated pipeline that utilizes miniprot, a rapid protein-to-genome aligner, in combination with AUGUSTUS to predict genes with high accuracy. Accuracy results indicate that GALBA is particularly strong in the annotation of large vertebrate genomes. We also present use cases in insects, vertebrates, and a land plant. GALBA is fully open source and available as a docker image for easy execution with Singularity in high-performance computing environments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our pipeline addresses the critical need for accurate gene annotation in newly sequenced genomes, and we believe that GALBA will greatly facilitate genome annotation for diverse organisms.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12859-023-05449-z","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T11:33:48Z","timestamp":1693481628000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":113,"title":["Galba: genome annotation with miniprot and AUGUSTUS"],"prefix":"10.1186","volume":"24","author":[{"given":"Tom\u00e1\u0161","family":"Br\u016fna","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Guhlin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Honsel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffen","family":"Herbold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Stanke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalia","family":"Nenasheva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthis","family":"Ebel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"Gabriel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina J.","family":"Hoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,31]]},"reference":[{"issue":"17","key":"5449_CR1","doi-asserted-by":"publisher","first-page":"4325","DOI":"10.1073\/pnas.1720115115","volume":"115","author":"HA Lewin","year":"2018","unstructured":"Lewin HA, Robinson GE, Kress WJ, Baker WJ, Coddington J, Crandall KA, Durbin R, Edwards SV, Forest F, Gilbert MTP, et al. Earth BioGenome project: sequencing life for the future of life. Proc Natl Acad Sci. 2018;115(17):4325\u201333.","journal-title":"Proc Natl Acad Sci"},{"issue":"11","key":"5449_CR2","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1038\/s41587-021-01108-x","volume":"39","author":"Y Wang","year":"2021","unstructured":"Wang Y, Zhao Y, Bollas A, Wang Y, Au KF. Nanopore sequencing technology, bioinformatics and applications. Nat Biotechnol. 2021;39(11):1348\u201365.","journal-title":"Nat Biotechnol"},{"issue":"4","key":"5449_CR3","doi-asserted-by":"publisher","first-page":"2115639118","DOI":"10.1073\/pnas.2115639118","volume":"119","author":"MK Lawniczak","year":"2022","unstructured":"Lawniczak MK, Durbin R, Flicek P, Lindblad-Toh K, Wei X, Archibald JM, Baker WJ, Belov K, Blaxter ML, Marques Bonet T, et al. Standards recommendations for the Earth BioGenome Project. Proc Natl Acad Sci. 2022;119(4):2115639118.","journal-title":"Proc Natl Acad Sci"},{"key":"5449_CR4","unstructured":"Hope H, Willis S, Markie M, Elliott L. Wellcome Open Research. https:\/\/wellcomeopenresearch.org\/browse\/articles Accessed Accessed 10 April 2023. 2023."},{"key":"5449_CR5","unstructured":"for Biotechnology\u00a0Information NC. NCBI Genomes. https:\/\/www.ncbi.nlm.nih.gov\/genome\/browse#!\/eukaryotes\/ Accessed Accessed 10 April 2023. 2023."},{"key":"5449_CR6","unstructured":"Gabriel L, Hoff KJ, Bruna T, Lomsadze A, Borodovsky M, Stanke M. The BRAKER3 genome annotation pipeline. Plant and Animal Genomes Conference. 2023;30."},{"key":"5449_CR7","doi-asserted-by":"publisher","unstructured":"Bruna T, Lomsadze A, Borodovsky M. GeneMark-ETP: automatic gene finding in eukaryotic genomes in consistence with extrinsic data. bioRxiv. 2023. https:\/\/doi.org\/10.1101\/2023.01.13.524024.","DOI":"10.1101\/2023.01.13.524024"},{"issue":"5","key":"5449_CR8","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1093\/bioinformatics\/btn013","volume":"24","author":"M Stanke","year":"2008","unstructured":"Stanke M, Diekhans M, Baertsch R, Haussler D. Using native and syntenically mapped cDNA alignments to improve de novo gene finding. Bioinformatics. 2008;24(5):637\u201344.","journal-title":"Bioinformatics"},{"issue":"1","key":"5449_CR9","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1002\/cpbi.57","volume":"65","author":"KJ Hoff","year":"2019","unstructured":"Hoff KJ, Stanke M. Predicting genes in single genomes with AUGUSTUS. Curr Protoc Bioinform. 2019;65(1):57.","journal-title":"Curr Protoc Bioinform"},{"issue":"D1","key":"5449_CR10","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1093\/nar\/gkac998","volume":"51","author":"D Kuznetsov","year":"2023","unstructured":"Kuznetsov D, Tegenfeldt F, Manni M, Seppey M, Berkeley M, Kriventseva EV, Zdobnov EM. OrthoDB v11: annotation of orthologs in the widest sampling of organismal diversity. Nucleic Acids Res. 2023;51(D1):445\u201351.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"5449_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-5-59","volume":"5","author":"I Korf","year":"2004","unstructured":"Korf I. Gene finding in novel genomes. BMC Bioinform. 2004;5(1):1\u20139.","journal-title":"BMC Bioinform"},{"issue":"12","key":"5449_CR12","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1101\/gr.081612.108","volume":"18","author":"V Ter-Hovhannisyan","year":"2008","unstructured":"Ter-Hovhannisyan V, Lomsadze A, Chernoff YO, Borodovsky M. Gene prediction in novel fungal genomes using an ab initio algorithm with unsupervised training. Genome Res. 2008;18(12):1979\u201390.","journal-title":"Genome Res"},{"issue":"2","key":"5449_CR13","first-page":"026","volume":"2","author":"T Bruna","year":"2020","unstructured":"Bruna T, Lomsadze A, Borodovsky M. GeneMark-EP+: eukaryotic gene prediction with self-training in the space of genes and proteins. NAR Genom Bioinform. 2020;2(2):026.","journal-title":"NAR Genom Bioinform"},{"issue":"20","key":"5449_CR14","doi-asserted-by":"publisher","first-page":"6494","DOI":"10.1093\/nar\/gki937","volume":"33","author":"A Lomsadze","year":"2005","unstructured":"Lomsadze A, Ter-Hovhannisyan V, Chernoff YO, Borodovsky M. Gene identification in novel eukaryotic genomes by self-training algorithm. Nucleic Acids Res. 2005;33(20):6494\u2013506.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"5449_CR15","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1101\/gr.6743907","volume":"18","author":"BL Cantarel","year":"2008","unstructured":"Cantarel BL, Korf I, Robb SM, Parra G, Ross E, Moore B, Holt C, Alvarado AS, Yandell M. MAKER: an easy-to-use annotation pipeline designed for emerging model organism genomes. Genome Res. 2008;18(1):188\u201396.","journal-title":"Genome Res"},{"issue":"1","key":"5449_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-12-491","volume":"12","author":"C Holt","year":"2011","unstructured":"Holt C, Yandell M. MAKER2: an annotation pipeline and genome-database management tool for second-generation genome projects. BMC Bioinform. 2011;12(1):1\u201314.","journal-title":"BMC Bioinform"},{"issue":"1","key":"5449_CR17","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1002\/0471250953.bi0411s48","volume":"48","author":"MS Campbell","year":"2014","unstructured":"Campbell MS, Holt C, Moore B, Yandell M. Genome annotation and curation using MAKER and MAKER-P. Curr Protoc Bioinform. 2014;48(1):4\u201311.","journal-title":"Curr Protoc Bioinform"},{"key":"5449_CR18","unstructured":"FunAnnotate. 2023. https:\/\/github.com\/nextgenusfs\/funannotate Accessed Accessed 10 April 2023."},{"issue":"1","key":"5449_CR19","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1038\/s42003-021-02335-3","volume":"4","author":"JM Ranz","year":"2021","unstructured":"Ranz JM, Gonz\u00e1lez PM, Clifton BD, Nazario-Yepiz NO, Hern\u00e1ndez-Cervantes PL, Palma-Mart\u00ednez MJ, Valdivia DI, Jim\u00e9nez-Kaufman A, Lu MM, Markow TA, et al. A de novo transcriptional atlas in danaus plexippus reveals variability in dosage compensation across tissues. Commun Biol. 2021;4(1):791.","journal-title":"Commun Biol"},{"issue":"1","key":"5449_CR20","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1093\/nargab\/lqaa108","volume":"3","author":"T Bruna","year":"2021","unstructured":"Bruna T, Hoff KJ, Lomsadze A, Stanke M, Borodovsky M. BRAKER2: automatic eukaryotic genome annotation with GeneMark-EP+ and AUGUSTUS supported by a protein database. NAR Genom Bioinform. 2021;3(1):108.","journal-title":"NAR Genom Bioinform"},{"issue":"1","key":"5449_CR21","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nmeth.3176","volume":"12","author":"B Buchfink","year":"2015","unstructured":"Buchfink B, Xie C, Huson DH. Fast and sensitive protein alignment using DIAMOND. Nat Methods. 2015;12(1):59\u201360.","journal-title":"Nat Methods"},{"issue":"21","key":"5449_CR22","doi-asserted-by":"publisher","first-page":"2438","DOI":"10.1093\/bioinformatics\/btn460","volume":"24","author":"O Gotoh","year":"2008","unstructured":"Gotoh O. Direct mapping and alignment of protein sequences onto genomic sequence. Bioinformatics. 2008;24(21):2438\u201344.","journal-title":"Bioinformatics"},{"issue":"20","key":"5449_CR23","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1093\/nar\/gks708","volume":"40","author":"H Iwata","year":"2012","unstructured":"Iwata H, Gotoh O. Benchmarking spliced alignment programs including Spaln2, an extended version of Spaln that incorporates additional species-specific features. Nucleic Acids Res. 2012;40(20):161\u2013161.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"5449_CR24","doi-asserted-by":"publisher","first-page":"014","DOI":"10.1093\/bioinformatics\/btad014","volume":"39","author":"H Li","year":"2023","unstructured":"Li H. Protein-to-genome alignment with miniprot. Bioinformatics. 2023;39(1):014.","journal-title":"Bioinformatics"},{"issue":"1","key":"5449_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04482-0","volume":"22","author":"L Gabriel","year":"2021","unstructured":"Gabriel L, Hoff KJ, Bruna T, Borodovsky M, Stanke M. TSEBRA: transcript selector for BRAKER. BMC Bioinform. 2021;22(1):1\u201312.","journal-title":"BMC Bioinform"},{"key":"5449_CR26","unstructured":"Bruna T. miniprothint. https:\/\/github.com\/tomasbruna\/miniprothint.git Accessed Accessed 10 April 2023. 2023."},{"key":"5449_CR27","unstructured":"Gabriel L, Bruna T, Hoff KJ, Lomsadze A, Borodovsky M, Stanke M. BRAKER. https:\/\/github.com\/Gaius-Augustus\/BRAKER. Accessed 10 April 2023. 2023."},{"issue":"5","key":"5449_CR28","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1038\/nrg3174","volume":"13","author":"M Yandell","year":"2012","unstructured":"Yandell M, Ence D. A beginner\u2019s guide to eukaryotic genome annotation. Nat Rev Genet. 2012;13(5):329\u201342.","journal-title":"Nat Rev Genet"},{"key":"5449_CR29","unstructured":"Bruna T. OrthoDB-clades. https:\/\/github.com\/tomasbruna\/orthodb-clades Accessed Accessed 10 April 2023. 2023."},{"issue":"12","key":"5449_CR30","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1002\/cpz1.323","volume":"1","author":"M Manni","year":"2021","unstructured":"Manni M, Berkeley MR, Seppey M, Zdobnov EM. BUSCO: assessing genomic data quality and beyond. Curr Protoc. 2021;1(12):323.","journal-title":"Curr Protoc"},{"issue":"10","key":"5449_CR31","doi-asserted-by":"publisher","first-page":"3479","DOI":"10.1534\/g3.120.401579","volume":"10","author":"TW Harrop","year":"2020","unstructured":"Harrop TW, Guhlin J, McLaughlin GM, Permina E, Stockwell P, Gilligan J, Le Lec MF, Gruber MA, Quinn O, Lovegrove M, et al. High-quality assemblies for three invasive social wasps from the Vespula genus. G3: Genes Genom Genet. 2020;10(10):3479\u201388.","journal-title":"G3: Genes Genom Genet"},{"issue":"8","key":"5449_CR32","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1111\/mec.13578","volume":"25","author":"DS Standage","year":"2016","unstructured":"Standage DS, Berens AJ, Glastad KM, Severin AJ, Brendel VP, Toth AL. Genome, transcriptome and methylome sequencing of a primitively eusocial wasp reveal a greatly reduced dna methylation system in a social insect. Mol Ecol. 2016;25(8):1769\u201384.","journal-title":"Mol Ecol"},{"key":"5449_CR33","unstructured":"Uniprot. The universal protein knowledgebase in 2023. Nucleic Acids Res. 2023;51(D1):523\u201331."},{"issue":"D1","key":"5449_CR34","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1093\/nar\/gkv1189","volume":"44","author":"NA O\u2019Leary","year":"2016","unstructured":"O\u2019Leary NA, Wright MW, Brister JR, Ciufo S, Haddad D, McVeigh R, Rajput B, Robbertse B, Smith-White B, Ako-Adjei D, et al. Reference sequence (refseq) database at ncbi: current status, taxonomic expansion, and functional annotation. Nucleic Acids Res. 2016;44(D1):733\u201345.","journal-title":"Nucleic Acids Res"},{"key":"5449_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12864-019-5642-0","volume":"20","author":"A Wallberg","year":"2019","unstructured":"Wallberg A, Bunikis I, Pettersson OV, Mosbech M-B, Childers AK, Evans JD, Mikheyev AS, Robertson HM, Robinson GE, Webster MT. A hybrid de novo genome assembly of the honeybee, apis mellifera, with chromosome-length scaffolds. BMC Genom. 2019;20:1\u201319.","journal-title":"BMC Genom"},{"issue":"45","key":"5449_CR36","doi-asserted-by":"publisher","first-page":"13970","DOI":"10.1073\/pnas.1515937112","volume":"112","author":"S Patalano","year":"2015","unstructured":"Patalano S, Vlasova A, Wyatt C, Ewels P, Camara F, Ferreira PG, Asher CL, Jurkowski TP, Segonds-Pichon A, Bachman M, et al. Molecular signatures of plastic phenotypes in two eusocial insect species with simple societies. Proc Natl Acad Sci. 2015;112(45):13970\u20135.","journal-title":"Proc Natl Acad Sci"},{"issue":"10","key":"5449_CR37","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1093\/bioinformatics\/btw015","volume":"32","author":"M-A Dr\u0103gan","year":"2016","unstructured":"Dr\u0103gan M-A, Moghul I, Priyam A, Bustos C, Wurm Y. GeneValidator: identify problems with protein-coding gene predictions. Bioinformatics. 2016;32(10):1559\u201361.","journal-title":"Bioinformatics"},{"key":"5449_CR38","doi-asserted-by":"crossref","unstructured":"A comparative genomics multitool for scientific discovery and conservation. Nature. 2020;587(7833):240\u2013245.","DOI":"10.1038\/s41586-020-2876-6"},{"issue":"D1","key":"5449_CR39","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1093\/nar\/gkab1053","volume":"50","author":"K Katz","year":"2022","unstructured":"Katz K, Shutov O, Lapoint R, Kimelman M, Brister JR, O\u2019Sullivan C. The sequence read archive: a decade more of explosive growth. Nucleic Acids Res. 2022;50(D1):387\u201390.","journal-title":"Nucleic Acids Res"},{"key":"5449_CR40","doi-asserted-by":"crossref","unstructured":"Nevers Y, Rossier V, Train C, Altenhoff AM, Dessimoz C, Glover N. Multifaceted quality assessment of gene repertoire annotation with OMArk. bioRxiv, 2022;2022\u201311.","DOI":"10.1101\/2022.11.25.517970"},{"issue":"2","key":"5449_CR41","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.molp.2019.11.008","volume":"13","author":"C Guo","year":"2020","unstructured":"Guo C, Wang Y, Yang A, He J, Xiao C, Lv S, Han F, Yuan Y, Yuan Y, Dong X, et al. The coix genome provides insights into panicoideae evolution and papery hull domestication. Mol Plant. 2020;13(2):309\u201320.","journal-title":"Mol Plant"},{"key":"5449_CR42","doi-asserted-by":"publisher","unstructured":"Vuruputoor VS, Monyak D, Fetter KC, Webster C, Bhattarai A, Shrestha B, Zaman S, Bennett J, McEvoy SL, Caballero M, et al. Welcome to the big leaves: best practices for improving genome annotation in non-model plant genomes. bioRxiv. 2022. https:\/\/doi.org\/10.1101\/2022.10.03.510643","DOI":"10.1101\/2022.10.03.510643"},{"issue":"9","key":"5449_CR43","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1093\/nar\/gkw092","volume":"44","author":"J Keilwagen","year":"2016","unstructured":"Keilwagen J, Wenk M, Erickson JL, Schattat MH, Grau J, Hartung F. Using intron position conservation for homology-based gene prediction. Nucleic Acids Res. 2016;44(9):89\u201389.","journal-title":"Nucleic Acids Res"},{"key":"5449_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-018-2203-5","volume":"19","author":"J Keilwagen","year":"2018","unstructured":"Keilwagen J, Hartung F, Paulini M, Twardziok SO, Grau J. Combining RNA-seq data and homology-based gene prediction for plants, animals and fungi. BMC Bioinform. 2018;19:1\u201312.","journal-title":"BMC Bioinform"},{"key":"5449_CR45","doi-asserted-by":"crossref","unstructured":"Keilwagen J, Hartung F, Grau J. GeMoMa: homology-based gene prediction utilizing intron position conservation and RNA-seq data. Gene prediction: Methods Protoc. 2019;161\u2013177.","DOI":"10.1007\/978-1-4939-9173-0_9"},{"issue":"5","key":"5449_CR46","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1093\/bioinformatics\/btv661","volume":"32","author":"KJ Hoff","year":"2016","unstructured":"Hoff KJ, Lange S, Lomsadze A, Borodovsky M, Stanke M. BRAKER1: unsupervised RNA-Seq-based genome annotation with GeneMark-ET and AUGUSTUS. Bioinformatics. 2016;32(5):767\u20139.","journal-title":"Bioinformatics"},{"issue":"23","key":"5449_CR47","doi-asserted-by":"publisher","first-page":"6211","DOI":"10.1111\/mec.16099","volume":"30","author":"M Errbii","year":"2021","unstructured":"Errbii M, Keilwagen J, Hoff KJ, Steffen R, Altm\u00fcller J, Oettler J, Schrader L. Transposable elements and introgression introduce genetic variation in the invasive ant Cardiocondyla obscurior. Mol Ecol. 2021;30(23):6211\u201328.","journal-title":"Mol Ecol"},{"issue":"6","key":"5449_CR48","doi-asserted-by":"publisher","first-page":"4173","DOI":"10.1016\/j.ygeno.2021.11.002","volume":"113","author":"TW W\u00f6hner","year":"2021","unstructured":"W\u00f6hner TW, Emeriewen OF, Wittenberg AH, Schneiders H, Vrijenhoek I, Hal\u00e1sz J, Hrotk\u00f3 K, Hoff KJ, Gabriel L, Lempe J, et al. The draft chromosome-level genome assembly of tetraploid ground cherry (Prunus fruticosa Pall.) from long reads. Genomics. 2021;113(6):4173\u201383.","journal-title":"Genomics"},{"key":"5449_CR49","doi-asserted-by":"crossref","unstructured":"Woehner TW, Emeriewen OF, Wittenberg AH, Nijbroek K, Wang RP, Blom E-J, Keilwagen J, Berner T, Hoff KJ, Gabriel L, et al. The structure of the tetraploid sour cherry \u2019Schattenmorelle\u2019(Prunus cerasus L.) genome reveals insights into its segmental allopolyploid nature. bioRxiv, 2023\u201303;2023.","DOI":"10.1101\/2023.03.28.534503"},{"issue":"22\u201323","key":"5449_CR50","first-page":"5291","volume":"36","author":"F Stiehler","year":"2020","unstructured":"Stiehler F, Steinborn M, Scholz S, Dey D, Weber AP, Denton AK. Helixer: cross-species gene annotation of large eukaryotic genomes using deep learning. Bioinformatics. 2020;36(22\u201323):5291\u20138.","journal-title":"Bioinformatics"},{"issue":"22\u201323","key":"5449_CR51","first-page":"5514","volume":"36","author":"R Martin","year":"2020","unstructured":"Martin R, Hackl T, Hattab G, Fischer MG, Heider D. Mosga: modular open-source genome annotator. Bioinformatics. 2020;36(22\u201323):5514\u20135.","journal-title":"Bioinformatics"},{"key":"5449_CR52","unstructured":"Bruna T. EukSpecies-BRAKER2. https:\/\/github.com\/gatech-genemark\/EukSpecies-BRAKER2. Accessed 10 April 2023. 2023."},{"key":"5449_CR53","unstructured":"Bruna T. BRAKER2-exp. https:\/\/github.com\/gatech-genemark\/BRAKER2-exp. Accessed 10 April 2023. 2023."},{"key":"5449_CR54","unstructured":"Bruna T. GeneMark-ETP-exp. https:\/\/github.com\/gatech-genemark\/GeneMark-ETP-exp. Accessed 10 April 2023. 2023."},{"key":"5449_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-019-3182-x","volume":"20","author":"M Stanke","year":"2019","unstructured":"Stanke M, Bruhn W, Becker F, Hoff KJ. VARUS: sampling complementary RNA reads from the sequence read archive. BMC Bioinform. 2019;20:1\u20137.","journal-title":"BMC Bioinform."},{"key":"5449_CR56","doi-asserted-by":"publisher","first-page":"baaa062","DOI":"10.1093\/database\/baaa062","volume":"2020","author":"CL Schoch","year":"2020","unstructured":"Schoch CL, Ciufo S, Domrachev M, Hotton CL, Kannan S, Khovanskaya R, Leipe D, Mcveigh R, O\u2019Neill K, Robbertse B, et al. NCBI Taxonomy: a comprehensive update on curation, resources and tools. Database. 2020;2020:baaa062.","journal-title":"Database"},{"key":"5449_CR57","doi-asserted-by":"crossref","unstructured":"K\u00f6nig S, Romoth L, Stanke M. Comparative genome annotation. Comp Genom Methods Protoc 2018;189\u2013212.","DOI":"10.1007\/978-1-4939-7463-4_6"},{"key":"5449_CR58","unstructured":"Bruna T. Unsupervised algorithms for automated gene prediction in novel eukaryotic genomes. Ph.D thesis, Georgia Institute of Technology. 2022."},{"issue":"17","key":"5449_CR59","doi-asserted-by":"publisher","first-page":"9451","DOI":"10.1073\/pnas.1921046117","volume":"117","author":"JM Flynn","year":"2020","unstructured":"Flynn JM, Hubley R, Goubert C, Rosen J, Clark AG, Feschotte C, Smit AF. RepeatModeler2 for automated genomic discovery of transposable element families. Proc Natl Acad Sci. 2020;117(17):9451\u20137.","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"5449_CR60","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1002\/0471250953.bi0410s05","volume":"5","author":"N Chen","year":"2004","unstructured":"Chen N. Using Repeat Masker to identify repetitive elements in genomic sequences. Curr Protoc Bioinform. 2004;5(1):4\u201310.","journal-title":"Curr Protoc Bioinform"},{"issue":"2","key":"5449_CR61","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1093\/nar\/27.2.573","volume":"27","author":"G Benson","year":"1999","unstructured":"Benson G. Tandem repeats finder: a program to analyze DNA sequences. Nucleic Acids Res. 1999;27(2):573\u201380.","journal-title":"Nucleic Acids Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-023-05449-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-023-05449-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-023-05449-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T15:03:03Z","timestamp":1700406183000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-023-05449-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,31]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["5449"],"URL":"https:\/\/doi.org\/10.1186\/s12859-023-05449-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.04.10.536199","asserted-by":"object"}]},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,31]]},"assertion":[{"value":"18 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"327"}}