{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T06:05:00Z","timestamp":1773554700205,"version":"3.50.1"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T00:00:00Z","timestamp":1742256000000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Rainwater Charitable Trust"},{"name":"Weill Institute for Neurosciences"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Pacific Biosciences (PacBio) single-molecule, long-read sequencing enables whole genome annotation and the characterization of 20 complex repetitive repeat regions, especially relevant to neurodegenerative diseases, through their PureTarget panel. Long-read whole-genome sequencing (WGS) also allows for the detection of structural variants that would be difficult to detect with traditional short-read sequencing. However, the raw unaligned Binary Alignment Map data need to be processed before analysis. There is a need for an intuitive comprehensive bioinformatic pipeline that can analyze these data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present nf-core\/pacvar, a comprehensive pipeline for analyzing both PacBio single-molecule PureTarget and WGS data that demultiplexes and parallelizes pre-processing, variant calling and repeat characterization. nf-core\/pacvar is compatible with little configuration and has few dependencies. This pipeline enables rapid end-to-end, parallel processing of PacBio single-molecule whole genome and targeted repeat expansion sequencing.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>nf-core\/pacvar is available on nf-core website (https:\/\/nf-co.re\/pacvar\/) and on github (https:\/\/github.com\/nf-core\/pacvar) under MIT License (DOI: 10.5281\/zenodo.14813048).<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf116","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T05:11:51Z","timestamp":1742274711000},"source":"Crossref","is-referenced-by-count":2,"title":["nf-core\/pacvar: a pipeline for analyzing long-read PacBio whole genome and repeat expansion sequencing data"],"prefix":"10.1093","volume":"41","author":[{"given":"Tanya","family":"Jain","sequence":"first","affiliation":[{"name":"Weill Institute for Neurosciences, University of California , San Francisco, CA, 94158,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9112-2278","authenticated-orcid":false,"given":"Claire","family":"Clelland","sequence":"additional","affiliation":[{"name":"Weill Institute for Neurosciences, University of California , San Francisco, CA, 94158,","place":["United States"]},{"name":"Department of Neurology, Memory & Aging Center, University of California , San Francisco, CA, 94158,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2025,3,17]]},"reference":[{"key":"2025041602170707800_btaf116-B140642","doi-asserted-by":"publisher","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":"2025041602170707800_btaf116-B1","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and BCFtools","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"2025041602170707800_btaf116-B2","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":"2025041602170707800_btaf116-B3","doi-asserted-by":"crossref","first-page":"1606","DOI":"10.1038\/s41587-023-02057-3","article-title":"Characterization and visualization of tandem repeats at genome scale","volume":"42","author":"Dolzhenko","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2025041602170707800_btaf116-B4","doi-asserted-by":"crossref","first-page":"3047","DOI":"10.1093\/bioinformatics\/btw354","article-title":"MultiQC: summarize analysis results for multiple tools and samples in a single report","volume":"32","author":"Ewels","year":"2016","journal-title":"Bioinformatics"},{"key":"2025041602170707800_btaf116-B5","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":"2025041602170707800_btaf116-B28367288","doi-asserted-by":"publisher","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":"2025041602170707800_btaf116-B6","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad150","article-title":"nf-core\/isoseq: simple gene and isoform annotation with PacBio Iso-Seq long-read sequencing","volume":"39","author":"Guizard","year":"2023","journal-title":"Bioinformatics"},{"key":"2025041602170707800_btaf116-B7","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae042","article-title":"HiPhase: jointly phasing small, structural, and tandem repeat variants from HiFi sequencing","volume":"40","author":"Holt","year":"2024","journal-title":"Bioinformatics"},{"key":"2025041602170707800_btaf116-B0787195","doi-asserted-by":"publisher","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":"2025041602170707800_btaf116-B8","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2025041602170707800_btaf116-B9","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1093\/bioinformatics\/btq671","article-title":"Tabix: fast retrieval of sequence features from generic TAB-delimited files","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"key":"2025041602170707800_btaf116-B10","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.1038\/s41598-022-05833-4","article-title":"Comparison of GATK and DeepVariant by trio sequencing","volume":"12","author":"Lin","year":"2022","journal-title":"Sci Rep"},{"key":"2025041602170707800_btaf116-B11","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1038\/nbt.4235","article-title":"A universal SNP and small-indel variant caller using deep neural networks","volume":"36","author":"Poplin","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2025041602170707800_btaf116-B12","doi-asserted-by":"publisher","DOI":"10.1101\/201178","article-title":"Scaling accurate genetic variant discovery to tens of thousands of samples","author":"Poplin","journal-title":"BioRxiv"},{"key":"2025041602170707800_btaf116-B13","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1038\/s41598-023-50667-3","article-title":"Validated assays for the quantification of C9orf72 human pathology","volume":"14","author":"Salomonsson","year":"2024","journal-title":"Sci Rep"},{"key":"2025041602170707800_btaf116-B14","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1093\/bib\/bbs017","article-title":"Integrative genomics viewer (IGV): high-performance genomics data visualization and exploration","volume":"14","author":"Thorvaldsd\u00f3ttir","year":"2013","journal-title":"Brief Bioinformatics"},{"key":"2025041602170707800_btaf116-B15","doi-asserted-by":"crossref","first-page":"e5060","DOI":"10.21769\/BioProtoc.5060","article-title":"Single-molecule sequencing of the C9orf72 repeat expansion in patient iPSCs","volume":"14","author":"Tsai","year":"2024","journal-title":"Bio Protoc"},{"key":"2025041602170707800_btaf116-B16","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1038\/s41587-019-0217-9","article-title":"Accurate circular consensus long-read sequencing improves variant detection and assembly of a human genome","volume":"37","author":"Wenger","year":"2019","journal-title":"Nat Biotechnol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf116\/62434906\/btaf116.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf116\/62434906\/btaf116.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf116\/62434906\/btaf116.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T06:17:21Z","timestamp":1744784241000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf116\/8082929"}},"subtitle":[],"editor":[{"given":"Dr Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,3,17]]},"references-count":19,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf116","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2025,3,17]]},"article-number":"btaf116"}}