{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T06:50:50Z","timestamp":1780469450977,"version":"3.54.1"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T00:00:00Z","timestamp":1722297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Traits for Life Indoors"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Genome assembly projects have grown exponentially due to breakthroughs in sequencing technologies and assembly algorithms. Evaluating the quality of genome assemblies is critical to ensure the reliability of downstream analysis and interpretation. To fulfil this task, we have developed the AssemblyQC pipeline that performs file-format validation, contaminant checking, contiguity measurement, gene- and repeat-space completeness quantification, telomere inspection, taxonomic assignment, synteny alignment, scaffold examination through Hi-C contact-map visualization, and assessments of completeness, consensus quality and phasing through k-mer analysis. It produces a comprehensive HTML report with method descriptions, tables, and visualizations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The pipeline uses Nextflow for workflow orchestration and adheres to the best-practice established by the nf-core community. This pipeline offers a reproducible, scalable, and portable method to assess the quality of genome assemblies\u2014the code is available online at GitHub: https:\/\/github.com\/Plant-Food-Research-Open\/assemblyqc.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae477","type":"journal-article","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T20:15:27Z","timestamp":1722370527000},"source":"Crossref","is-referenced-by-count":12,"title":["AssemblyQC: a Nextflow pipeline for reproducible reporting of assembly quality"],"prefix":"10.1093","volume":"40","author":[{"given":"Usman","family":"Rashid","sequence":"first","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Shiller","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 3182 Te Puke, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Smith","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Crowhurst","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcus","family":"Davy","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 3182 Te Puke, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting-Hsuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 7608 Lincoln, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ignacio","family":"Carvajal","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Bailey","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan","family":"Thomson","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 7608 Lincoln, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2954-762X","authenticated-orcid":false,"given":"Cecilia H","family":"Deng","sequence":"additional","affiliation":[{"name":"Molecular & Digital Breeding, The New Zealand Institute for Plant and Food Research Limited , 1025 Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,7,30]]},"reference":[{"key":"2024082005161502200_btae477-B1","first-page":"199","author":"Agarwal","year":"2020"},{"key":"2024082005161502200_btae477-B2","volume-title":"FastQC: A Quality Control Tool for High Throughput Sequence Data","author":"Andrews","year":"2010"},{"key":"2024082005161502200_btae477-B3","author":"Astashyn"},{"key":"2024082005161502200_btae477-B4","author":"Brown"},{"key":"2024082005161502200_btae477-B5","doi-asserted-by":"crossref","first-page":"e4958","DOI":"10.7717\/peerj.4958","article-title":"D-GENIES: dot plot large genomes in an interactive, efficient and simple way","volume":"6","author":"Cabanettes","year":"2018","journal-title":"PeerJ"},{"key":"2024082005161502200_btae477-B6","doi-asserted-by":"crossref","first-page":"i884","DOI":"10.1093\/bioinformatics\/bty560","article-title":"fastp: an ultra-fast all-in-one FASTQ preprocessor","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2024082005161502200_btae477-B7","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s13059-022-02619-9","article-title":"Contamination detection in genomic data: more is not enough","volume":"23","author":"Cornet","year":"2022","journal-title":"Genome Biol"},{"key":"2024082005161502200_btae477-B8","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1093\/bioinformatics\/btx192","article-title":"BioContainers: an open-source and community-driven framework for software standardization","volume":"33","author":"da Veiga Leprevost","year":"2017","journal-title":"Bioinformatics"},{"key":"2024082005161502200_btae477-B9","doi-asserted-by":"crossref","first-page":"giab008","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and BCFtools","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"2024082005161502200_btae477-B10","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1038\/nbt.3820","article-title":"Nextflow enables reproducible computational workflows","volume":"35","author":"Di Tommaso","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2024082005161502200_btae477-B11","doi-asserted-by":"crossref","first-page":"e636","DOI":"10.7717\/peerj-cs.636","article-title":"Empirical evaluation of methods for de novo genome assembly","volume":"7","author":"Dida","year":"2021","journal-title":"PeerJ Comput Sci"},{"key":"2024082005161502200_btae477-B12","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1126\/science.aal3327","article-title":"De novo assembly of the Aedes aegypti genome using Hi-C yields chromosome-length scaffolds","volume":"356","author":"Dudchenko","year":"2017","journal-title":"Science"},{"key":"2024082005161502200_btae477-B13","author":"EBP","year":"2024"},{"key":"2024082005161502200_btae477-B14","author":"Edwards","year":"2019"},{"key":"2024082005161502200_btae477-B15","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/1471-2105-9-18","article-title":"LTRharvest, an efficient and flexible software for de novo detection of LTR retrotransposons","volume":"9","author":"Ellinghaus","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2024082005161502200_btae477-B16","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1038\/s41587-020-0439-x","article-title":"The nf-core framework for community-curated bioinformatics pipelines","volume":"38","author":"Ewels","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2024082005161502200_btae477-B17","doi-asserted-by":"crossref","first-page":"2503","DOI":"10.1093\/bioinformatics\/btu314","article-title":"SAMBLASTER: fast duplicate marking and structural variant read extraction","volume":"30","author":"Faust","year":"2014","journal-title":"Bioinformatics"},{"key":"2024082005161502200_btae477-B18","doi-asserted-by":"crossref","first-page":"2922","DOI":"10.1093\/bioinformatics\/btac196","article-title":"plotsr: visualizing structural similarities and rearrangements between multiple genomes","volume":"38","author":"Goel","year":"2022","journal-title":"Bioinformatics"},{"key":"2024082005161502200_btae477-B19","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TCBB.2013.68","article-title":"GenomeTools: a comprehensive software library for efficient processing of structured genome annotations","volume":"10","author":"Gremme","year":"2013","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2024082005161502200_btae477-B20","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1038\/s41592-018-0046-7","article-title":"Bioconda: sustainable and comprehensive software distribution for the life sciences","volume":"15","author":"Gr\u00fcning","year":"2018","journal-title":"Nat Methods"},{"key":"2024082005161502200_btae477-B21","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1101\/gr.092759.109","article-title":"Circos: an information aesthetic for comparative genomics","volume":"19","author":"Krzywinski","year":"2009","journal-title":"Genome Res"},{"key":"2024082005161502200_btae477-B22","doi-asserted-by":"crossref","first-page":"e0177459","DOI":"10.1371\/journal.pone.0177459","article-title":"Singularity: scientific containers for mobility of compute","volume":"12","author":"Kurtzer","year":"2017","journal-title":"PLoS One"},{"key":"2024082005161502200_btae477-B23","author":"Langer","year":"2024"},{"key":"2024082005161502200_btae477-B24","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2024082005161502200_btae477-B25","author":"Li","year":"2013"},{"key":"2024082005161502200_btae477-B26","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1186\/s12864-020-6568-2","article-title":"GenomeQC: a quality assessment tool for genome assemblies and gene structure annotations","volume":"21","author":"Manchanda","year":"2020","journal-title":"BMC Genomics"},{"key":"2024082005161502200_btae477-B27","doi-asserted-by":"crossref","first-page":"e1005944","DOI":"10.1371\/journal.pcbi.1005944","article-title":"MUMmer4: a fast and versatile genome alignment system","volume":"14","author":"Mar\u00e7ais","year":"2018","journal-title":"PLoS Comput Biol"},{"key":"2024082005161502200_btae477-B28","first-page":"2","article-title":"Docker: lightweight linux containers for consistent development and deployment","volume":"239","author":"Merkel","year":"2014","journal-title":"Linux J"},{"key":"2024082005161502200_btae477-B29","author":"NCBI"},{"key":"2024082005161502200_btae477-B30","author":"NHGRI"},{"key":"2024082005161502200_btae477-B31","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1186\/1471-2105-12-385","article-title":"Interactive metagenomic visualization in a web browser","volume":"12","author":"Ondov","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2024082005161502200_btae477-B32","doi-asserted-by":"crossref","first-page":"1410","DOI":"10.1104\/pp.17.01310","article-title":"LTR_retriever: a highly accurate and sensitive program for identification of long terminal repeat retrotransposons","volume":"176","author":"Ou","year":"2018","journal-title":"Plant Physiol"},{"key":"2024082005161502200_btae477-B33","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s13100-019-0193-0","article-title":"LTR_FINDER_parallel: parallelization of LTR_FINDER enabling rapid identification of long terminal repeat retrotransposons","volume":"10","author":"Ou","year":"2019","journal-title":"Mob DNA"},{"key":"2024082005161502200_btae477-B34","first-page":"e126","article-title":"Assessing genome assembly quality using the LTR assembly index (LAI)","volume":"46","author":"Ou","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2024082005161502200_btae477-B35","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1186\/s13059-020-02134-9","article-title":"Merqury: reference-free quality, completeness, and phasing assessment for genome assemblies","volume":"21","author":"Rhie","year":"2020","journal-title":"Genome Biol"},{"key":"2024082005161502200_btae477-B36","first-page":"737","author":"Rhie"},{"key":"2024082005161502200_btae477-B37","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.cels.2018.01.001","article-title":"Juicebox.js provides a cloud-based visualization system for Hi-C data","volume":"6","author":"Robinson","year":"2018","journal-title":"Cell Syst"},{"key":"2024082005161502200_btae477-B38","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/978-1-4939-9173-0_14","article-title":"BUSCO: assessing genome assembly and annotation completeness","volume":"1962","author":"Seppey","year":"2019","journal-title":"Methods Mol Biol"},{"key":"2024082005161502200_btae477-B39","doi-asserted-by":"crossref","first-page":"e0163962","DOI":"10.1371\/journal.pone.0163962","article-title":"SeqKit: a cross-platform and ultrafast toolkit for FASTA\/Q file manipulation","volume":"11","author":"Shen","year":"2016","journal-title":"PLoS One"},{"key":"2024082005161502200_btae477-B40","doi-asserted-by":"crossref","first-page":"3210","DOI":"10.1093\/bioinformatics\/btv351","article-title":"BUSCO: assessing genome assembly and annotation completeness with single-copy orthologs","volume":"31","author":"Sim\u00e3o","year":"2015","journal-title":"Bioinformatics"},{"key":"2024082005161502200_btae477-B41","author":"Sullivan","year":"2022"},{"key":"2024082005161502200_btae477-B42","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.tplants.2021.10.006","article-title":"Twenty years of plant genome sequencing: achievements and challenges","volume":"27","author":"Sun","year":"2022","journal-title":"Trends Plant Sci"},{"key":"2024082005161502200_btae477-B43","author":"UCDAVIS-Bioinformatics"},{"key":"2024082005161502200_btae477-B44","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.tig.2022.10.005","article-title":"A proposed metric set for evaluation of genome assembly quality","volume":"39","author":"Wang","year":"2023","journal-title":"Trends Genet"},{"key":"2024082005161502200_btae477-B45","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with Kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae477\/58689553\/btae477.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/8\/btae477\/58856587\/btae477.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/8\/btae477\/58856587\/btae477.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T05:16:48Z","timestamp":1724131008000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae477\/7723991"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,7,30]]},"references-count":45,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae477","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,8]]},"published":{"date-parts":[[2024,7,30]]},"article-number":"btae477"}}