{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T16:19:11Z","timestamp":1764260351684,"version":"3.41.2"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"vor","delay-in-days":24,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"NSERC","doi-asserted-by":"publisher","award":["RGPIN-04973"],"award-info":[{"award-number":["RGPIN-04973"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"NSERC","doi-asserted-by":"publisher","award":["RGPIN-2021-03530"],"award-info":[{"award-number":["RGPIN-2021-03530"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001804","name":"Canada Research Chair","doi-asserted-by":"crossref","award":["CRC-2021-00232"],"award-info":[{"award-number":["CRC-2021-00232"]}],"id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Michael Smith Health Research","award":["SCH-2022-2553"],"award-info":[{"award-number":["SCH-2022-2553"]}]},{"name":"Genomic Applications Partnership Program","award":["189GRP"],"award-info":[{"award-number":["189GRP"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Plant viral infections cause significant economic losses, totalling $350 billion USD in 2021. With no treatment for virus-infected plants, accurate and efficient diagnosis is crucial to preventing and controlling these diseases. High-throughput sequencing (HTS) enables cost-efficient identification of known and unknown viruses. However, existing diagnostic pipelines face challenges. First, many methods depend on subjectively chosen parameter values, undermining their robustness across various data sources. Second, artifacts (e.g. false peaks) in the mapped sequence data can lead to incorrect diagnostic results. While some methods require manual or subjective verification to address these artifacts, others overlook them entirely, affecting the overall method performance and leading to imprecise or labour-intensive outcomes. To address these challenges, we introduce IIMI, a new automated analysis pipeline using machine learning to diagnose infections from 1583 plant viruses with HTS data. It adopts a data-driven approach for parameter selection, reducing subjectivity, and automatically filters out regions affected by artifacts, thus improving accuracy. Testing with in-house and published data shows IIMI\u2019s superiority over existing methods. Besides a prediction model, IIMI also provides resources on plant virus genomes, including annotations of regions prone to artifacts. The method is available as an R package (iimi) on CRAN and will integrate with the web application www.virtool.ca, enhancing accessibility and user convenience.<\/jats:p>","DOI":"10.1093\/bib\/bbae501","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:53:12Z","timestamp":1729169592000},"source":"Crossref","is-referenced-by-count":5,"title":["Diagnostics of viral infections using high-throughput genome sequencing data"],"prefix":"10.1093","volume":"25","author":[{"given":"Haochen","family":"Ning","sequence":"first","affiliation":[{"name":"Department of Mathematics and Statistics, University of Victoria , 3800 Finnerty Road (Ring Road), BC V8P 5C2 ,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Boyes","sequence":"additional","affiliation":[{"name":"Canadian Food Inspection Agency, Centre for Plant Health , 8801 Saanich Road E., North Saanich, BC V8L 1H3 ,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2970-7937","authenticated-orcid":false,"given":"Ibrahim","family":"Numanagi\u0107","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Victoria , 3800 Finnerty Road (Ring Road), BC V8P 5C2 ,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8501-5145","authenticated-orcid":false,"given":"Michael","family":"Rott","sequence":"additional","affiliation":[{"name":"Canadian Food Inspection Agency, Centre for Plant Health , 8801 Saanich Road E., North Saanich, BC V8L 1H3 ,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-7909","authenticated-orcid":false,"given":"Li","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, University of Saskatchewan , 106 Wiggins Road, Saskatoon, SK S7N 5E6 ,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4728-2343","authenticated-orcid":false,"given":"Xuekui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, University of Victoria , 3800 Finnerty Road (Ring Road), BC V8P 5C2 ,","place":["Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,10,17]]},"reference":[{"key":"2024101712151477900_ref1","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-94-007-7820-7_2","article-title":"Management of Virus and Viroid Diseases of crops in the tropics","volume-title":"Plant Virus and Viroid Diseases in the Tropics, Epidemiology and Management","author":"Sastry","year":"2014"},{"volume-title":"Invasive Pest Spread another Fallout from Climate Change, UN-Backed Study Finds [Internet]","year":"2021","author":"Ogolla","key":"2024101712151477900_ref2"},{"volume-title":"Scientific Review of the Impact of Climate Change on Plant Pests","year":"2020","author":"International Plant Protection Convention Secretariat","key":"2024101712151477900_ref3"},{"key":"2024101712151477900_ref4","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/B978-0-12-818654-1.00002-5","article-title":"Recent advances of virus diagnostics in horticultural crops","volume-title":"Applied Plant Virology: Advances, Detection, and Antiviral Strategies","author":"Baranwal","year":"2020"},{"key":"2024101712151477900_ref5","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1099\/0022-1317-34-3-475","article-title":"Characteristics of the microplate method of enzyme-linked immunosorbent assay for the detection of plant viruses","volume":"34","author":"Clark","year":"1977","journal-title":"J Gen Virol"},{"key":"2024101712151477900_ref6","doi-asserted-by":"publisher","first-page":"4433","DOI":"10.1007\/s00018-016-2299-6","article-title":"Mechanisms of viral mutation","volume":"73","author":"Sanju\u00e1n","year":"2016","journal-title":"Cell Mol Life Sci"},{"key":"2024101712151477900_ref7","doi-asserted-by":"publisher","first-page":"e1008271","DOI":"10.1371\/journal.pgen.1008271","article-title":"Viral quasispecies","volume":"15","author":"Domingo","year":"2019","journal-title":"PLoS Genet"},{"key":"2024101712151477900_ref8","doi-asserted-by":"publisher","first-page":"e0237951","DOI":"10.1371\/journal.pone.0237951","article-title":"Comparative study on three viral enrichment approaches based on RNA extraction for plant virus\/viroid detection using high-throughput sequencing","volume":"15","author":"Gaafar","year":"2020","journal-title":"PloS One"},{"key":"2024101712151477900_ref9","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1111\/epp.12863","article-title":"Facilitating the adoption of high-throughput sequencing technologies as a plant pest diagnostic test in laboratories: a step-by-step description","volume":"52","author":"Lebas","year":"2022","journal-title":"Bull OEPP"},{"key":"2024101712151477900_ref10","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1093\/bib\/bbaa231","article-title":"A computational toolset for rapid identification of SARS-CoV-2, other viruses, and microorganisms from sequencing data","volume":"22","author":"Chen","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024101712151477900_ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2022.867111","article-title":"VirHunter: a deep learning-based method for detection of novel RNA viruses in plant sequencing data","volume":"2","author":"Sukhorukov","year":"2022","journal-title":"Front Bioinform"},{"key":"2024101712151477900_ref12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/2049-2618-2-33","article-title":"PathoScope 2.0: a complete computational framework for strain identification in environmental or clinical sequencing samples","volume":"2","author":"Hong","year":"2014","journal-title":"Microbiome"},{"volume-title":"Virtool: Viral Infection Diagnostics Using Next-Generation Sequencing [Internet].","year":"2020","author":"Boyes","key":"2024101712151477900_ref13"},{"key":"2024101712151477900_ref14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/nmeth.1923","article-title":"Fast gapped-read alignment with bowtie 2","volume":"9","author":"Langmead","year":"2012","journal-title":"Nat Methods"},{"volume-title":"NCBI Virus [Internet]","author":"National Library of Medicine","key":"2024101712151477900_ref15"},{"key":"2024101712151477900_ref16","doi-asserted-by":"publisher","DOI":"10.15454\/GWDPIN","volume-title":"Peach Sequencing Data (RNAseq) [Internet].","author":"Khalili","year":"2022"},{"key":"2024101712151477900_ref17","doi-asserted-by":"publisher","DOI":"10.15454\/MK1JIW","volume-title":"Sugar Beet Sequencing Data (RNAseq) [Internet].","author":"Candresse","year":"2022"},{"key":"2024101712151477900_ref18","doi-asserted-by":"publisher","DOI":"10.15454\/KUYAT9","volume-title":"Grapevine Sequencing Data (RNAseq) [Internet].","author":"Candresse","year":"2022"},{"key":"2024101712151477900_ref19","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":"2024101712151477900_ref20","doi-asserted-by":"publisher","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":"2024101712151477900_ref21","doi-asserted-by":"publisher","first-page":"e1003118","DOI":"10.1371\/journal.pcbi.1003118","article-title":"Software for computing and annotating genomic ranges","volume":"9","author":"Lawrence","year":"2013","journal-title":"PLoS Comput Biol"},{"key":"2024101712151477900_ref22","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1038\/nrg3117","article-title":"Repetitive DNA and next-generation sequencing: computational challenges and solutions","volume":"13","author":"Treangen","year":"2011","journal-title":"Nat Rev Genet"},{"key":"2024101712151477900_ref23","doi-asserted-by":"publisher","first-page":"R51","DOI":"10.1186\/gb-2013-14-5-r51","article-title":"Characterizing and measuring bias in sequence data","volume":"14","author":"Ross","year":"2013","journal-title":"Genome Biol"},{"key":"2024101712151477900_ref24","doi-asserted-by":"publisher","first-page":"R18","DOI":"10.1186\/gb-2011-12-2-r18","article-title":"Analyzing and minimizing PCR amplification bias in Illumina sequencing libraries","volume":"12","author":"Aird","year":"2011","journal-title":"Genome Biol"},{"key":"2024101712151477900_ref25","doi-asserted-by":"publisher","first-page":"e1005375","DOI":"10.1371\/journal.pcbi.1005375","article-title":"High GC content causes orphan proteins to be intrinsically disordered","volume":"13","author":"Basile","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2024101712151477900_ref26","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/nrg.2016.49","article-title":"Coming of age: ten years of next-generation sequencing technologies","volume":"17","author":"Goodwin","year":"2016","journal-title":"Nat Rev Genet"},{"key":"2024101712151477900_ref27","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/nrg2626","article-title":"Sequencing technologies - the next generation","volume":"11","author":"Metzker","year":"2010","journal-title":"Nat Rev Genet"},{"key":"2024101712151477900_ref28","doi-asserted-by":"publisher","first-page":"e72","DOI":"10.1093\/nar\/gks001","article-title":"Summarizing and correcting the GC content bias in high-throughput sequencing","volume":"40","author":"Benjamini","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2024101712151477900_ref29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/0022-2836(87)90689-9","article-title":"CpG islands in vertebrate genomes","volume":"196","author":"Gardiner-Garden","year":"1987","journal-title":"J Mol Biol"},{"key":"2024101712151477900_ref30","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1101\/gr.078212.108","article-title":"Mapping short DNA sequencing reads and calling variants using mapping quality scores","volume":"18","author":"Li","year":"2008","journal-title":"Genome Res"},{"key":"2024101712151477900_ref31","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1038\/nbt.1621","article-title":"Transcript assembly and quantification by RNA-Seq reveals unannotated transcripts and isoform switching during cell differentiation","volume":"28","author":"Trapnell","year":"2010","journal-title":"Nat Biotechnol"},{"key":"2024101712151477900_ref32","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1038\/ng.806","article-title":"A framework for variation discovery and genotyping using next-generation DNA sequencing data","volume":"43","author":"DePristo","year":"2011","journal-title":"Nat Genet"},{"key":"2024101712151477900_ref33","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1111\/j.1541-0420.2010.01441.x","article-title":"PICS: probabilistic inference for ChIP-seq","volume":"67","author":"Zhang","year":"2011","journal-title":"Biometrics"},{"key":"2024101712151477900_ref34","doi-asserted-by":"publisher","first-page":"e32095","DOI":"10.1371\/journal.pone.0032095","article-title":"Probabilistic inference for nucleosome positioning with MNase-based or sonicated short-read data","volume":"7","author":"Zhang","year":"2012","journal-title":"PloS One"},{"volume-title":"Tree: Classification and Regression Trees [internet].","author":"Ripley","key":"2024101712151477900_ref35"},{"key":"2024101712151477900_ref36","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"article-title":"XGBoost: eXtreme Gradient Boosting [Internet]. Vienna, Austria: R Foundation for Statistical Computing;","year":"2023","author":"Chen","key":"2024101712151477900_ref37"},{"key":"2024101712151477900_ref38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J Stat Softw"},{"article-title":"GBM developers. GBM: generalized boosted regression models","year":"2024","author":"Ridgeway","key":"2024101712151477900_ref39"},{"article-title":"Naivebayes: high performance implementation of the naive Bayes algorithm in R","year":"2024","author":"Majka","key":"2024101712151477900_ref40"},{"article-title":"e1071: misc functions of the Department of Statistics, Probability Theory Group (formerly: E1071), TU Wien","year":"2023","author":"Meyer","key":"2024101712151477900_ref41"},{"key":"2024101712151477900_ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21706-2","volume-title":"Modern Applied Statistics with S","author":"Venables","year":"2002"},{"volume-title":"Collaborating with Genome Specialists to Protect Canada\u00e2&Euro;Plant Health [Internet]","year":"2021","author":"Canada Food Inspection Agency","key":"2024101712151477900_ref43"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae501\/59826192\/bbae501.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae501\/59826192\/bbae501.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T12:53:25Z","timestamp":1729169605000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae501\/7824630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,9,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae501","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"type":"print","value":"1467-5463"},{"type":"electronic","value":"1477-4054"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,9,23]]},"article-number":"bbae501"}}