ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing
Abstract Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models...
Gespeichert in:
Veröffentlicht in: | Briefings in bioinformatics 2024-07, Vol.25 (5) |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 5 |
container_start_page | |
container_title | Briefings in bioinformatics |
container_volume | 25 |
creator | Fan, Kechen Li, Mengfan Zhang, Jiarong Xie, Zihan Jiang, Daguang Bo, Xiaochen Zhao, Dongsheng Shi, Shenghui Ni, Ming |
description | Abstract
Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent. |
doi_str_mv | 10.1093/bib/bbae435 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11370629</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/bib/bbae435</oup_id><sourcerecordid>3100562731</sourcerecordid><originalsourceid>FETCH-LOGICAL-c329t-8b24b62bd1e8b0462ea54ed5ac727a49fe3afc75fca51e21ca7bdc2742f2d8733</originalsourceid><addsrcrecordid>eNp9kUtr3DAUhUVpaV5ddV8EgVIoTvSyZXVTyqRpCiGB9LEVV_J14uCRppIdyL-vhpmEJouu7oH7cTiHQ8hbzo44M_LYDe7YOUAl6xdklyutK8Vq9XKtG13VqpE7ZC_nW8YE0y1_TXakEaJpDdslP64QusWcEobpEwX6-2RxcVE5yNjRKcaR9jHRHvJEIXQUvJ8TTEgDhLiKCWnGEf003K3VnxmDH8L1AXnVw5jxzfbuk1-nX38uzqrzy2_fF1_OKy-FmarWCeUa4TqOrWOqEQi1wq4Gr4UGZXqU0Htd9x5qjoJ70K7zQivRi67VUu6Tzxvf1eyW2PlSIcFoV2lYQrq3EQb79BOGG3sd7yznUrNGmOLwYeuQYkmfJ7scssdxhIBxzlZyxupGaMkLevgMvY1zCqXfmhLGGMFVoT5uKJ9izgn7xzSc2fVatqxlt2sV-t2_BR7Zh3kK8H4DxHn1X6e_Ewye0g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3102999214</pqid></control><display><type>article</type><title>ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing</title><source>MEDLINE</source><source>Oxford Open</source><source>PubMed Central</source><creator>Fan, Kechen ; Li, Mengfan ; Zhang, Jiarong ; Xie, Zihan ; Jiang, Daguang ; Bo, Xiaochen ; Zhao, Dongsheng ; Shi, Shenghui ; Ni, Ming</creator><creatorcontrib>Fan, Kechen ; Li, Mengfan ; Zhang, Jiarong ; Xie, Zihan ; Jiang, Daguang ; Bo, Xiaochen ; Zhao, Dongsheng ; Shi, Shenghui ; Ni, Ming</creatorcontrib><description>Abstract
Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent.</description><identifier>ISSN: 1467-5463</identifier><identifier>ISSN: 1477-4054</identifier><identifier>EISSN: 1477-4054</identifier><identifier>DOI: 10.1093/bib/bbae435</identifier><identifier>PMID: 39226890</identifier><language>eng</language><publisher>England: Oxford University Press</publisher><subject>Accuracy ; Alignment ; Artificial neural networks ; Classification ; Computational Biology - methods ; Computer applications ; Computing costs ; Deep Learning ; Deoxyribonucleic acid ; DNA ; DNA sequencing ; Experimental methods ; Gene sequencing ; High-Throughput Nucleotide Sequencing - methods ; Human performance ; Humans ; Hybridization ; Machine learning ; Microorganisms ; Nanopore Sequencing - methods ; Nanopores ; Neural networks ; Neural Networks, Computer ; Nucleotide sequence ; Polymerase chain reaction ; Problem Solving Protocol ; Sequence Analysis, DNA - methods ; Software ; Yeasts</subject><ispartof>Briefings in bioinformatics, 2024-07, Vol.25 (5)</ispartof><rights>The Author(s) 2024. Published by Oxford University Press. 2024</rights><rights>The Author(s) 2024. Published by Oxford University Press.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c329t-8b24b62bd1e8b0462ea54ed5ac727a49fe3afc75fca51e21ca7bdc2742f2d8733</cites><orcidid>0009-0009-3262-6909 ; 0000-0003-2616-8891 ; 0000-0001-9465-2787</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11370629/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11370629/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,1598,27903,27904,53770,53772</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39226890$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Fan, Kechen</creatorcontrib><creatorcontrib>Li, Mengfan</creatorcontrib><creatorcontrib>Zhang, Jiarong</creatorcontrib><creatorcontrib>Xie, Zihan</creatorcontrib><creatorcontrib>Jiang, Daguang</creatorcontrib><creatorcontrib>Bo, Xiaochen</creatorcontrib><creatorcontrib>Zhao, Dongsheng</creatorcontrib><creatorcontrib>Shi, Shenghui</creatorcontrib><creatorcontrib>Ni, Ming</creatorcontrib><title>ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing</title><title>Briefings in bioinformatics</title><addtitle>Brief Bioinform</addtitle><description>Abstract
Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent.</description><subject>Accuracy</subject><subject>Alignment</subject><subject>Artificial neural networks</subject><subject>Classification</subject><subject>Computational Biology - methods</subject><subject>Computer applications</subject><subject>Computing costs</subject><subject>Deep Learning</subject><subject>Deoxyribonucleic acid</subject><subject>DNA</subject><subject>DNA sequencing</subject><subject>Experimental methods</subject><subject>Gene sequencing</subject><subject>High-Throughput Nucleotide Sequencing - methods</subject><subject>Human performance</subject><subject>Humans</subject><subject>Hybridization</subject><subject>Machine learning</subject><subject>Microorganisms</subject><subject>Nanopore Sequencing - methods</subject><subject>Nanopores</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Nucleotide sequence</subject><subject>Polymerase chain reaction</subject><subject>Problem Solving Protocol</subject><subject>Sequence Analysis, DNA - methods</subject><subject>Software</subject><subject>Yeasts</subject><issn>1467-5463</issn><issn>1477-4054</issn><issn>1477-4054</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>TOX</sourceid><sourceid>EIF</sourceid><recordid>eNp9kUtr3DAUhUVpaV5ddV8EgVIoTvSyZXVTyqRpCiGB9LEVV_J14uCRppIdyL-vhpmEJouu7oH7cTiHQ8hbzo44M_LYDe7YOUAl6xdklyutK8Vq9XKtG13VqpE7ZC_nW8YE0y1_TXakEaJpDdslP64QusWcEobpEwX6-2RxcVE5yNjRKcaR9jHRHvJEIXQUvJ8TTEgDhLiKCWnGEf003K3VnxmDH8L1AXnVw5jxzfbuk1-nX38uzqrzy2_fF1_OKy-FmarWCeUa4TqOrWOqEQi1wq4Gr4UGZXqU0Htd9x5qjoJ70K7zQivRi67VUu6Tzxvf1eyW2PlSIcFoV2lYQrq3EQb79BOGG3sd7yznUrNGmOLwYeuQYkmfJ7scssdxhIBxzlZyxupGaMkLevgMvY1zCqXfmhLGGMFVoT5uKJ9izgn7xzSc2fVatqxlt2sV-t2_BR7Zh3kK8H4DxHn1X6e_Ewye0g</recordid><startdate>20240725</startdate><enddate>20240725</enddate><creator>Fan, Kechen</creator><creator>Li, Mengfan</creator><creator>Zhang, Jiarong</creator><creator>Xie, Zihan</creator><creator>Jiang, Daguang</creator><creator>Bo, Xiaochen</creator><creator>Zhao, Dongsheng</creator><creator>Shi, Shenghui</creator><creator>Ni, Ming</creator><general>Oxford University Press</general><general>Oxford Publishing Limited (England)</general><scope>TOX</scope><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>7QO</scope><scope>7SC</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>K9.</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0009-0009-3262-6909</orcidid><orcidid>https://orcid.org/0000-0003-2616-8891</orcidid><orcidid>https://orcid.org/0000-0001-9465-2787</orcidid></search><sort><creationdate>20240725</creationdate><title>ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing</title><author>Fan, Kechen ; Li, Mengfan ; Zhang, Jiarong ; Xie, Zihan ; Jiang, Daguang ; Bo, Xiaochen ; Zhao, Dongsheng ; Shi, Shenghui ; Ni, Ming</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c329t-8b24b62bd1e8b0462ea54ed5ac727a49fe3afc75fca51e21ca7bdc2742f2d8733</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Alignment</topic><topic>Artificial neural networks</topic><topic>Classification</topic><topic>Computational Biology - methods</topic><topic>Computer applications</topic><topic>Computing costs</topic><topic>Deep Learning</topic><topic>Deoxyribonucleic acid</topic><topic>DNA</topic><topic>DNA sequencing</topic><topic>Experimental methods</topic><topic>Gene sequencing</topic><topic>High-Throughput Nucleotide Sequencing - methods</topic><topic>Human performance</topic><topic>Humans</topic><topic>Hybridization</topic><topic>Machine learning</topic><topic>Microorganisms</topic><topic>Nanopore Sequencing - methods</topic><topic>Nanopores</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Nucleotide sequence</topic><topic>Polymerase chain reaction</topic><topic>Problem Solving Protocol</topic><topic>Sequence Analysis, DNA - methods</topic><topic>Software</topic><topic>Yeasts</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fan, Kechen</creatorcontrib><creatorcontrib>Li, Mengfan</creatorcontrib><creatorcontrib>Zhang, Jiarong</creatorcontrib><creatorcontrib>Xie, Zihan</creatorcontrib><creatorcontrib>Jiang, Daguang</creatorcontrib><creatorcontrib>Bo, Xiaochen</creatorcontrib><creatorcontrib>Zhao, Dongsheng</creatorcontrib><creatorcontrib>Shi, Shenghui</creatorcontrib><creatorcontrib>Ni, Ming</creatorcontrib><collection>Oxford Open</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Briefings in bioinformatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fan, Kechen</au><au>Li, Mengfan</au><au>Zhang, Jiarong</au><au>Xie, Zihan</au><au>Jiang, Daguang</au><au>Bo, Xiaochen</au><au>Zhao, Dongsheng</au><au>Shi, Shenghui</au><au>Ni, Ming</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing</atitle><jtitle>Briefings in bioinformatics</jtitle><addtitle>Brief Bioinform</addtitle><date>2024-07-25</date><risdate>2024</risdate><volume>25</volume><issue>5</issue><issn>1467-5463</issn><issn>1477-4054</issn><eissn>1477-4054</eissn><abstract>Abstract
Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent.</abstract><cop>England</cop><pub>Oxford University Press</pub><pmid>39226890</pmid><doi>10.1093/bib/bbae435</doi><orcidid>https://orcid.org/0009-0009-3262-6909</orcidid><orcidid>https://orcid.org/0000-0003-2616-8891</orcidid><orcidid>https://orcid.org/0000-0001-9465-2787</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1467-5463 |
ispartof | Briefings in bioinformatics, 2024-07, Vol.25 (5) |
issn | 1467-5463 1477-4054 1477-4054 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11370629 |
source | MEDLINE; Oxford Open; PubMed Central |
subjects | Accuracy Alignment Artificial neural networks Classification Computational Biology - methods Computer applications Computing costs Deep Learning Deoxyribonucleic acid DNA DNA sequencing Experimental methods Gene sequencing High-Throughput Nucleotide Sequencing - methods Human performance Humans Hybridization Machine learning Microorganisms Nanopore Sequencing - methods Nanopores Neural networks Neural Networks, Computer Nucleotide sequence Polymerase chain reaction Problem Solving Protocol Sequence Analysis, DNA - methods Software Yeasts |
title | ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T17%3A06%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ReadCurrent:%20a%20VDCNN-based%20tool%20for%20fast%20and%20accurate%20nanopore%20selective%20sequencing&rft.jtitle=Briefings%20in%20bioinformatics&rft.au=Fan,%20Kechen&rft.date=2024-07-25&rft.volume=25&rft.issue=5&rft.issn=1467-5463&rft.eissn=1477-4054&rft_id=info:doi/10.1093/bib/bbae435&rft_dat=%3Cproquest_pubme%3E3100562731%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3102999214&rft_id=info:pmid/39226890&rft_oup_id=10.1093/bib/bbae435&rfr_iscdi=true |