{"id":"https://openalex.org/W4392360643","doi":"https://doi.org/10.1016/j.csbj.2024.02.019","title":"Robust multi-read reconstruction from noisy clusters using deep neural network for DNA storage","display_name":"Robust multi-read reconstruction from noisy clusters using deep neural network for DNA storage","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4392360643","doi":"https://doi.org/10.1016/j.csbj.2024.02.019","pmid":"https://pubmed.ncbi.nlm.nih.gov/39807110","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11725466"},"language":"en","primary_location":{"id":"doi:10.1016/j.csbj.2024.02.019","doi":"https://doi.org/10.1016/j.csbj.2024.02.019","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csbj.2024.02.019","pdf_url":null,"source":{"id":"https://openalex.org/S2764539591","display_name":"Computational and Structural Biotechnology Journal","issn_l":"2001-0370","issn":["2001-0370"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","norway-1","oarl","poland-100","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and Structural Biotechnology Journal","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.csbj.2024.02.019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102816650","display_name":"Yun Qin","orcid":"https://orcid.org/0009-0006-2865-3873","observed_orcids":["https://orcid.org/0009-0006-2865-3873"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Qin","raw_affiliation_strings":["Center for Applied Mathematics, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Applied Mathematics, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049872589","display_name":"Fei Zhu","orcid":"https://orcid.org/0000-0002-8113-3707","observed_orcids":["https://orcid.org/0000-0002-8113-3707"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Zhu","raw_affiliation_strings":["Center for Applied Mathematics, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Applied Mathematics, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085604381","display_name":"Bo Xi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xi","raw_affiliation_strings":["Center for Applied Mathematics, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Applied Mathematics, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057068738","display_name":"Lifu Song","orcid":"https://orcid.org/0000-0003-1092-4568","observed_orcids":["https://orcid.org/0000-0003-1092-4568"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210139473","display_name":"Tianjin Institute of Industrial Biotechnology","ror":"https://ror.org/042pyga86","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210139473"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifu Song","raw_affiliation_strings":["Haihe Laboratory of Synthetic Biology, Tianjin, China","Systems Biology Center, Key Laboratory of Engineering Biology for Low-carbon Manufacturing, Tianjin Institute of Industrial Biotechnology, Chinese Academy of Sciences, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Haihe Laboratory of Synthetic Biology, Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"Systems Biology Center, Key Laboratory of Engineering Biology for Low-carbon Manufacturing, Tianjin Institute of Industrial Biotechnology, Chinese Academy of Sciences, Tianjin, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210139473"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049872589"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":{"value":3230,"currency":"USD","value_usd":3230},"apc_paid":{"value":3230,"currency":"USD","value_usd":3230},"fwci":3.9803,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93501805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":null,"first_page":"1076","last_page":"1087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.03790000081062317,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dna-storage","display_name":"DNA data storage","score":0.9729999899864197},{"id":"https://openalex.org/keywords/sequence-reconstruction","display_name":"sequence reconstruction","score":0.8930000066757202},{"id":"https://openalex.org/keywords/strand-breaks","display_name":"strand breaks","score":0.871999979019165},{"id":"https://openalex.org/keywords/dna-rearrangement","display_name":"DNA rearrangement","score":0.8050000071525574},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.6899999976158142},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912215948104858},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5781093239784241},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5600505471229553},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5470056533813477},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4957026243209839},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48536813259124756},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.44733887910842896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44312429428100586},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41849568486213684},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.3885471224784851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3424914479255676},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19776973128318787},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12150096893310547},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1016/j.csbj.2024.02.019","doi":"https://doi.org/10.1016/j.csbj.2024.02.019","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csbj.2024.02.019","pdf_url":null,"source":{"id":"https://openalex.org/S2764539591","display_name":"Computational and Structural Biotechnology Journal","issn_l":"2001-0370","issn":["2001-0370"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","norway-1","oarl","poland-100","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and Structural Biotechnology Journal","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11725466","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11725466","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11725466/pdf/main.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Comput Struct Biotechnol J","raw_type":"Text"},{"id":"pmid:39807110","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39807110","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and structural biotechnology journal","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2210.11106","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.11106","pdf_url":"https://arxiv.org/pdf/2210.11106","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:ceb52dc331e0448a9d6f59ba41f72b40","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/ceb52dc331e0448a9d6f59ba41f72b40","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational and Structural Biotechnology Journal, Vol 23, Iss , Pp 1076-1087 (2024)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2210.11106","doi":"https://doi.org/10.48550/arxiv.2210.11106","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.11106","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.csbj.2024.02.019","doi":"https://doi.org/10.1016/j.csbj.2024.02.019","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csbj.2024.02.019","pdf_url":null,"source":{"id":"https://openalex.org/S2764539591","display_name":"Computational and Structural Biotechnology Journal","issn_l":"2001-0370","issn":["2001-0370"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","norway-1","oarl","poland-100","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational and Structural Biotechnology Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1156022499","display_name":null,"funder_award_id":"# 2020YFA0712100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392360643.pdf","grobid_xml":"https://content.openalex.org/works/W4392360643.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W2103441770","https://openalex.org/W2116699248","https://openalex.org/W2123637716","https://openalex.org/W2302781903","https://openalex.org/W2583335622","https://openalex.org/W2592122940","https://openalex.org/W2626778328","https://openalex.org/W2753923014","https://openalex.org/W2788257106","https://openalex.org/W2944582089","https://openalex.org/W2976279718","https://openalex.org/W2989744057","https://openalex.org/W2993276217","https://openalex.org/W2998987329","https://openalex.org/W3001660245","https://openalex.org/W3024869864","https://openalex.org/W3042993760","https://openalex.org/W3080465559","https://openalex.org/W3081119335","https://openalex.org/W3092532862","https://openalex.org/W3095078462","https://openalex.org/W3097777922","https://openalex.org/W3127443464","https://openalex.org/W3128107836","https://openalex.org/W3135906068","https://openalex.org/W3145006624","https://openalex.org/W3159986226","https://openalex.org/W3166542265","https://openalex.org/W3201304016","https://openalex.org/W4206816857","https://openalex.org/W4223644132","https://openalex.org/W4230531492","https://openalex.org/W4289655141","https://openalex.org/W4292092908","https://openalex.org/W4295453817","https://openalex.org/W4313731376","https://openalex.org/W4321835840","https://openalex.org/W4365800074","https://openalex.org/W4386214154","https://openalex.org/W4391144496","https://openalex.org/W4407813519","https://openalex.org/W6768415740"],"related_works":["https://openalex.org/W4307077127","https://openalex.org/W4405899410","https://openalex.org/W4413748273","https://openalex.org/W4414404547","https://openalex.org/W3201304016","https://openalex.org/W7131349997","https://openalex.org/W4411453075","https://openalex.org/W7138134354","https://openalex.org/W7153970526","https://openalex.org/W4403344677"],"abstract_inverted_index":{"DNA":[0,16,49,86],"holds":[1],"immense":[2],"potential":[3],"as":[4,69],"an":[5,127],"emerging":[6],"data":[7],"storage":[8,17,39],"medium.":[9],"However,":[10],"the":[11,48,73,79,123,149,180,218],"recovery":[12],"of":[13,54,72,81,148,170,182,212],"information":[14],"in":[15,179,197],"systems":[18],"faces":[19],"challenges":[20],"posed":[21],"by":[22,85],"various":[23],"errors,":[24,27],"including":[25],"IDS":[26,142],"strand":[28,116],"breaks,":[29,87],"and":[30,38,119,126,137,146,173,215],"rearrangements,":[31,88,118],"inevitably":[32],"introduced":[33],"during":[34],"synthesis,":[35],"amplification,":[36],"sequencing,":[37],"processes.":[40],"Sequence":[41],"reconstruction,":[42],"crucial":[43],"for":[44],"decoding,":[45],"involves":[46],"inferring":[47],"reference":[50],"from":[51,63],"a":[52,67,99],"cluster":[53,68],"erroneous":[55],"copies.":[56],"While":[57],"most":[58],"methods":[59],"assume":[60],"equal":[61],"contributions":[62],"all":[64],"reads":[65],"within":[66],"noisy":[70,113,183],"copies":[71],"same":[74],"reference,":[75],"they":[76],"often":[77],"overlook":[78],"existence":[80],"contaminated":[82,189,200],"sequences":[83],"caused":[84],"or":[89],"mis-clustering":[90],"reads.":[91],"To":[92],"address":[93],"this":[94],"issue,":[95],"we":[96],"propose":[97],"RobuSeqNet,":[98],"robust":[100],"multi-read":[101],"reconstruction":[102,167,194],"neural":[103],"network":[104,129],"specifically":[105],"designed":[106],"to":[107,134,187,206],"robustly":[108],"reconstruct":[109],"multiple":[110],"reads,":[111],"accommodating":[112],"clusters":[114,136,184],"with":[115,140],"breakage,":[117],"mis-clustered":[120],"strands.":[121],"Leveraging":[122],"attention":[124],"mechanism":[125],"elaborate":[128],"design,":[130],"RobuSeqNet":[131,163],"exhibits":[132,203],"resilience":[133],"highly-noisy":[135],"effectively":[138],"deals":[139],"in-strand":[141],"errors.":[143],"The":[144],"effectiveness":[145],"robustness":[147],"proposed":[150],"method":[151],"are":[152],"validated":[153],"on":[154],"three":[155,176,219],"representative":[156],"next-generation":[157],"sequencing":[158],"datasets.":[159,220],"Results":[160],"demonstrate":[161],"that":[162],"maintains":[164],"high":[165],"sequence":[166,193],"success":[168,210],"rates":[169,211],"99.74%,":[171],"99.58%,":[172],"96.44%":[174],"across":[175,217],"datasets,":[177],"even":[178],"presence":[181],"containing":[185],"up":[186],"20%":[188],"sequences,":[190,201],"outperforming":[191],"known":[192],"models.":[195],"Additionally,":[196],"scenarios":[198],"without":[199],"it":[202],"comparable":[204],"performance":[205],"existing":[207],"models,":[208],"achieving":[209],"99.88%,":[213],"99.82%,":[214],"97.68%":[216]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2024-03-05T00:00:00"}
