Symphonizing pileup and full-alignment for deep learning-based long-read variant calling
Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alig...
Gespeichert in:
| Veröffentlicht in: | Nature Computational Science 2022-12, Vol.2 (12), p.797-803 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 803 |
|---|---|
| container_issue | 12 |
| container_start_page | 797 |
| container_title | Nature Computational Science |
| container_volume | 2 |
| creator | Zheng, Zhenxian Li, Shumin Su, Junhao Leung, Amy Wing-Sze Lam, Tak-Wah Luo, Ruibang |
| description | Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alignment tackles complicated candidates to maximize precision and recall. Clair3 runs faster than any of the other state-of-the-art variant callers and demonstrates improved performance, especially at lower coverage. |
| doi_str_mv | 10.1038/s43588-022-00387-x |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2911842386</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2911842386</sourcerecordid><originalsourceid>FETCH-LOGICAL-c277t-cdb005206904d5ffd23b8e2b0773b96095ca71e13339b4b0a9f42eed812373fa3</originalsourceid><addsrcrecordid>eNpNkEtLAzEUhYMottT-AReSpZtoHvPILKX4goILFdyFZHJTRzIPk460_nqjreLqnss953D5EDpl9IJRIS9jJnIpCeWc0LSXZHOAprwoOJFZXh7-0xM0j_GNUspzJmghjtFESFaWouJT9PK4bYfXvms-m26Fh8bDOGDdWexG74n2zaproVtj1wdsAQbsQYcueYnRESz2fZIBtMUfOjQ6OWvtfbqfoCOnfYT5fs7Q88310-KOLB9u7xdXS1LzslyT2hpKc06LimY2d85yYSRwQ9N_pipolde6ZMCEEJXJDNWVyziAlYyLUjgtZuh81zuE_n2EuFZtE2vwXnfQj1HxijGZcSGLZOU7ax36GAM4NYSm1WGrGFXfUNUOqkpQ1Q9UtUmhs33_aFqwf5FfhOILz05y9A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2911842386</pqid></control><display><type>article</type><title>Symphonizing pileup and full-alignment for deep learning-based long-read variant calling</title><source>MEDLINE</source><source>SpringerLink Journals - AutoHoldings</source><creator>Zheng, Zhenxian ; Li, Shumin ; Su, Junhao ; Leung, Amy Wing-Sze ; Lam, Tak-Wah ; Luo, Ruibang</creator><creatorcontrib>Zheng, Zhenxian ; Li, Shumin ; Su, Junhao ; Leung, Amy Wing-Sze ; Lam, Tak-Wah ; Luo, Ruibang</creatorcontrib><description>Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alignment tackles complicated candidates to maximize precision and recall. Clair3 runs faster than any of the other state-of-the-art variant callers and demonstrates improved performance, especially at lower coverage.</description><identifier>ISSN: 2662-8457</identifier><identifier>EISSN: 2662-8457</identifier><identifier>DOI: 10.1038/s43588-022-00387-x</identifier><identifier>PMID: 38177392</identifier><language>eng</language><publisher>United States</publisher><subject>Deep Learning ; High-Throughput Nucleotide Sequencing - methods ; Polymorphism, Single Nucleotide - genetics</subject><ispartof>Nature Computational Science, 2022-12, Vol.2 (12), p.797-803</ispartof><rights>2022. The Author(s), under exclusive licence to Springer Nature America, Inc.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c277t-cdb005206904d5ffd23b8e2b0773b96095ca71e13339b4b0a9f42eed812373fa3</citedby><cites>FETCH-LOGICAL-c277t-cdb005206904d5ffd23b8e2b0773b96095ca71e13339b4b0a9f42eed812373fa3</cites><orcidid>0000-0002-8560-3999 ; 0000-0002-6546-2324 ; 0000-0001-9711-6533</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38177392$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zheng, Zhenxian</creatorcontrib><creatorcontrib>Li, Shumin</creatorcontrib><creatorcontrib>Su, Junhao</creatorcontrib><creatorcontrib>Leung, Amy Wing-Sze</creatorcontrib><creatorcontrib>Lam, Tak-Wah</creatorcontrib><creatorcontrib>Luo, Ruibang</creatorcontrib><title>Symphonizing pileup and full-alignment for deep learning-based long-read variant calling</title><title>Nature Computational Science</title><addtitle>Nat Comput Sci</addtitle><description>Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alignment tackles complicated candidates to maximize precision and recall. Clair3 runs faster than any of the other state-of-the-art variant callers and demonstrates improved performance, especially at lower coverage.</description><subject>Deep Learning</subject><subject>High-Throughput Nucleotide Sequencing - methods</subject><subject>Polymorphism, Single Nucleotide - genetics</subject><issn>2662-8457</issn><issn>2662-8457</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpNkEtLAzEUhYMottT-AReSpZtoHvPILKX4goILFdyFZHJTRzIPk460_nqjreLqnss953D5EDpl9IJRIS9jJnIpCeWc0LSXZHOAprwoOJFZXh7-0xM0j_GNUspzJmghjtFESFaWouJT9PK4bYfXvms-m26Fh8bDOGDdWexG74n2zaproVtj1wdsAQbsQYcueYnRESz2fZIBtMUfOjQ6OWvtfbqfoCOnfYT5fs7Q88310-KOLB9u7xdXS1LzslyT2hpKc06LimY2d85yYSRwQ9N_pipolde6ZMCEEJXJDNWVyziAlYyLUjgtZuh81zuE_n2EuFZtE2vwXnfQj1HxijGZcSGLZOU7ax36GAM4NYSm1WGrGFXfUNUOqkpQ1Q9UtUmhs33_aFqwf5FfhOILz05y9A</recordid><startdate>20221201</startdate><enddate>20221201</enddate><creator>Zheng, Zhenxian</creator><creator>Li, Shumin</creator><creator>Su, Junhao</creator><creator>Leung, Amy Wing-Sze</creator><creator>Lam, Tak-Wah</creator><creator>Luo, Ruibang</creator><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-8560-3999</orcidid><orcidid>https://orcid.org/0000-0002-6546-2324</orcidid><orcidid>https://orcid.org/0000-0001-9711-6533</orcidid></search><sort><creationdate>20221201</creationdate><title>Symphonizing pileup and full-alignment for deep learning-based long-read variant calling</title><author>Zheng, Zhenxian ; Li, Shumin ; Su, Junhao ; Leung, Amy Wing-Sze ; Lam, Tak-Wah ; Luo, Ruibang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c277t-cdb005206904d5ffd23b8e2b0773b96095ca71e13339b4b0a9f42eed812373fa3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Deep Learning</topic><topic>High-Throughput Nucleotide Sequencing - methods</topic><topic>Polymorphism, Single Nucleotide - genetics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Zhenxian</creatorcontrib><creatorcontrib>Li, Shumin</creatorcontrib><creatorcontrib>Su, Junhao</creatorcontrib><creatorcontrib>Leung, Amy Wing-Sze</creatorcontrib><creatorcontrib>Lam, Tak-Wah</creatorcontrib><creatorcontrib>Luo, Ruibang</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Nature Computational Science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zheng, Zhenxian</au><au>Li, Shumin</au><au>Su, Junhao</au><au>Leung, Amy Wing-Sze</au><au>Lam, Tak-Wah</au><au>Luo, Ruibang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Symphonizing pileup and full-alignment for deep learning-based long-read variant calling</atitle><jtitle>Nature Computational Science</jtitle><addtitle>Nat Comput Sci</addtitle><date>2022-12-01</date><risdate>2022</risdate><volume>2</volume><issue>12</issue><spage>797</spage><epage>803</epage><pages>797-803</pages><issn>2662-8457</issn><eissn>2662-8457</eissn><abstract>Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alignment tackles complicated candidates to maximize precision and recall. Clair3 runs faster than any of the other state-of-the-art variant callers and demonstrates improved performance, especially at lower coverage.</abstract><cop>United States</cop><pmid>38177392</pmid><doi>10.1038/s43588-022-00387-x</doi><tpages>7</tpages><orcidid>https://orcid.org/0000-0002-8560-3999</orcidid><orcidid>https://orcid.org/0000-0002-6546-2324</orcidid><orcidid>https://orcid.org/0000-0001-9711-6533</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2662-8457 |
| ispartof | Nature Computational Science, 2022-12, Vol.2 (12), p.797-803 |
| issn | 2662-8457 2662-8457 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2911842386 |
| source | MEDLINE; SpringerLink Journals - AutoHoldings |
| subjects | Deep Learning High-Throughput Nucleotide Sequencing - methods Polymorphism, Single Nucleotide - genetics |
| title | Symphonizing pileup and full-alignment for deep learning-based long-read variant calling |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T17%3A00%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Symphonizing%20pileup%20and%20full-alignment%20for%20deep%20learning-based%20long-read%20variant%20calling&rft.jtitle=Nature%20Computational%20Science&rft.au=Zheng,%20Zhenxian&rft.date=2022-12-01&rft.volume=2&rft.issue=12&rft.spage=797&rft.epage=803&rft.pages=797-803&rft.issn=2662-8457&rft.eissn=2662-8457&rft_id=info:doi/10.1038/s43588-022-00387-x&rft_dat=%3Cproquest_cross%3E2911842386%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2911842386&rft_id=info:pmid/38177392&rfr_iscdi=true |