{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:21:40Z","timestamp":1769851300437,"version":"3.49.0"},"reference-count":12,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T00:00:00Z","timestamp":1726531200000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472120"],"award-info":[{"award-number":["62472120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402140"],"award-info":[{"award-number":["62402140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62331012"],"award-info":[{"award-number":["62331012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["LH2023F014"],"award-info":[{"award-number":["LH2023F014"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Mobile genetic elements (MEs) are heritable mutagens that significantly contribute to genetic diseases. The advent of long-read sequencing technologies, capable of resolving large DNA fragments, offers promising prospects for the comprehensive detection of ME variants (MEVs). However, achieving high precision while maintaining recall performance remains challenging mainly brought by the variable length and similar content of MEV signatures, which are often obscured by the noise in long reads. Here, we propose MEHunter, a high-performance MEV detection approach utilizing a fine-tuned transformer model adept at identifying potential MEVs with fragmented features. Benchmark experiments on both simulated and real datasets demonstrate that MEHunter consistently achieves higher accuracy and sensitivity than the state-of-the-art tools. Furthermore, it is capable of detecting novel potentially individual-specific MEVs that have been overlooked in published population projects.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>MEHunter is available from https:\/\/github.com\/120L021101\/MEHunter.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae557","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T17:50:58Z","timestamp":1726595458000},"source":"Crossref","is-referenced-by-count":3,"title":["MEHunter: transformer-based mobile element variant detection from long reads"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0673-8503","authenticated-orcid":false,"given":"Tao","family":"Jiang","sequence":"first","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001, China"},{"name":"Zhengzhou Research Institute, Harbin Institute of Technology , Zhengzhou, Henan 450000, China"}]},{"given":"Zuji","family":"Zhou","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7819-849X","authenticated-orcid":false,"given":"Zhendong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001, China"}]},{"given":"Shuqi","family":"Cao","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-6217","authenticated-orcid":false,"given":"Yadong","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001, China"},{"name":"Zhengzhou Research Institute, Harbin Institute of Technology , Zhengzhou, Henan 450000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8385-1908","authenticated-orcid":false,"given":"Yadong","family":"Liu","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001, China"},{"name":"Zhengzhou Research Institute, Harbin Institute of Technology , Zhengzhou, Henan 450000, China"}]}],"member":"286","published-online":{"date-parts":[[2024,9,16]]},"reference":[{"key":"2024092110555701100_btae557-B1","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1038\/s41467-023-35996-1","article-title":"Deciphering the exact breakpoints of structural variations using long sequencing reads with DeBreak","volume":"14","author":"Chen","year":"2023","journal-title":"Nat Commun"},{"key":"2024092110555701100_btae557-B2","doi-asserted-by":"crossref","first-page":"3836","DOI":"10.1038\/s41467-021-24041-8","article-title":"Comprehensive identification of transposable element insertions using multiple sequencing technologies","volume":"12","author":"Chu","year":"2021","journal-title":"Nat Commun"},{"key":"2024092110555701100_btae557-B3","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1126\/science.abf7117","article-title":"Haplotype-resolved diverse human genomes and integrated analysis of structural variation","volume":"372","author":"Ebert","year":"2021","journal-title":"Science"},{"key":"2024092110555701100_btae557-B4","doi-asserted-by":"crossref","first-page":"3384","DOI":"10.1093\/bioinformatics\/btab587","article-title":"abPOA: an SIMD-based C library for fast partial order alignment using adaptive band","volume":"37","author":"Gao","year":"2021","journal-title":"Bioinformatics"},{"key":"2024092110555701100_btae557-B5","doi-asserted-by":"crossref","first-page":"1916","DOI":"10.1101\/gr.218032.116","article-title":"The Mobile Element Locator Tool (MELT): population-scale mobile element discovery and biology","volume":"27","author":"Gardner","year":"2017","journal-title":"Genome Res"},{"key":"2024092110555701100_btae557-B6","doi-asserted-by":"crossref","first-page":"3484","DOI":"10.1093\/bioinformatics\/btz106","article-title":"rMETL: sensitive mobile element insertion detection with long read realignment","volume":"35","author":"Jiang","year":"2019","journal-title":"Bioinformatics"},{"key":"2024092110555701100_btae557-B7","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1186\/s13059-020-02107-y","article-title":"Long-read-based human genomic structural variation detection with cuteSV","volume":"21","author":"Jiang","year":"2020","journal-title":"Genome Biol"},{"key":"2024092110555701100_btae557-B8","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1038\/s41588-023-01390-2","article-title":"Mobile element variation contributes to population-specific genome diversification, gene regulation and disease risk","volume":"55","author":"Kojima","year":"2023","journal-title":"Nat Genet"},{"key":"2024092110555701100_btae557-B9","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":"2024092110555701100_btae557-B10","doi-asserted-by":"crossref","first-page":"1024","DOI":"10.1016\/j.cell.2024.01.002","article-title":"A 25-year odyssey of genomic technology advances and structural variant discovery","volume":"187","author":"Porubsky","year":"2024","journal-title":"Cell"},{"key":"2024092110555701100_btae557-B11","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1093\/nar\/gkz1173","article-title":"Identification and characterization of occult human-specific LINE-1 insertions using long-read sequencing technology","volume":"48","author":"Zhou","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2024092110555701100_btae557-B12","author":"Zhou","year":"2023"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae557\/59147513\/btae557.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae557\/59216429\/btae557.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae557\/59216429\/btae557.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T10:56:13Z","timestamp":1726916173000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae557\/7759021"}},"subtitle":[],"editor":[{"given":"Peter","family":"Robinson","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":12,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae557","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,9]]},"article-number":"btae557"}}