{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:16:13Z","timestamp":1787940973900,"version":"build-2784847793"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF1202104"],"award-info":[{"award-number":["2022YFF1202104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["32401256"],"award-info":[{"award-number":["32401256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62571401"],"award-info":[{"award-number":["62571401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>DNA storage offers exceptional information density and archival longevity but is constrained by complex biochemical noise inherent to synthesis, storage, and sequencing. Conventional hard-decision error-correction schemes often rely on excessive redundancy to mitigate these imperfections, which significantly compromises storage efficiency and density.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present Polus, a Transformer-based enhancement framework that improves digital reliability through soft-decision decoding (SDD) without requiring encoder modification. At its core is SeqFormer, a Transformer-based channel model that synergizes sequence context with quality signals to generate calibrated per-base confidence scores, effectively transforming uncertain biochemical noise into informative \u201csoft\u201d erasures. In in silico benchmarks, Polus significantly upgrades mainstream DNA storage codecs. It reduces the sequencing coverage required for DNA Fountain by 38.9%\u2014increasing effective physical density by approximately 80%\u2014and eliminates persistent indel-induced errors in the Yin\u2013Yang codec. Furthermore, it enables a targeted resequencing strategy that achieves full recovery with 99.9% less overhead than uniform deepening. Moreover, a nine-metric evaluation suite was employed to provide multi-dimensional quantitative comparisons of DNA storage codecs across reliability, density, and cost. Collectively, Polus provides a reproducible framework for context-aware decoding and system design guidance for DNA storage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>All source code of the Polus, including the SeqFormer implementation, codec algorithms, test data used, and the simulation pipeline is available on GitHub (https:\/\/github.com\/dinglulu\/Polus) and Zenodo (https:\/\/zenodo.org\/communities\/bioinfoszu\/). A web hosted instance of Polus is available at https:\/\/polus.bioailab.net\/polls\/home. The SeqFormer model is also released as a standalone repository at https:\/\/github.com\/dinglulu\/SeqFormer and https:\/\/zenodo.org\/communities\/bioinfoszu\/.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag563","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T11:22:38Z","timestamp":1785151358000},"source":"Crossref","is-referenced-by-count":0,"title":["Polus: a context-aware enhancement framework for DNA storage via transformer-based soft-decision decoding"],"prefix":"10.1093","volume":"42","author":[{"given":"Lulu","family":"Ding","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University , Shenzhen 518060,","place":["China"]},{"name":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University , Shenzhen 518060,","place":["China"]},{"name":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , Shenzhen 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohui","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , Shenzhen 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinlong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , Shenzhen 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4414-4001","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]},{"name":"Key Laboratory of Biological Bigdata, Ministry of Education, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohua","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]},{"name":"Key Laboratory of Biological Bigdata, Ministry of Education, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University , Guangzhou 510700,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8479-6904","authenticated-orcid":false,"given":"Zexuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University , Shenzhen 518060,","place":["China"]},{"name":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"2026082813173166300_btag563-B1","doi-asserted-by":"crossref","first-page":"e0257521","DOI":"10.1371\/journal.pone.0257521","article-title":"Sequencing DNA with nanopores: troubles and biases","volume":"16","author":"Andr\u00e9s-Le\u00f3n","year":"2021","journal-title":"PLoS One"},{"key":"2026082813173166300_btag563-B2","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1038\/s41576-019-0125-3","article-title":"Molecular digital data storage using DNA","volume":"20","author":"Ceze","year":"2019","journal-title":"Nat Rev Genet"},{"key":"2026082813173166300_btag563-B3","volume-title":"Trace Reconstruction from Noisy Polynucleotides Sequencer Reads","author":"Ceze","year":"2018"},{"key":"2026082813173166300_btag563-B4","first-page":"8822","author":"Chandak"},{"key":"2026082813173166300_btag563-B5","doi-asserted-by":"crossref","first-page":"nwab028","DOI":"10.1093\/nsr\/nwab028","article-title":"An artificial chromosome for data storage","volume":"8","author":"Chen","year":"2021","journal-title":"Natl Sci Rev"},{"key":"2026082813173166300_btag563-B6","doi-asserted-by":"crossref","first-page":"1628","DOI":"10.1126\/science.1226355","article-title":"Next-generation digital information storage in DNA","volume":"337","author":"Church","year":"2012","journal-title":"Science"},{"key":"2026082813173166300_btag563-B7","doi-asserted-by":"crossref","first-page":"nwad229","DOI":"10.1093\/nsr\/nwad229","article-title":"Improving error-correcting capability in DNA digital storage via soft-decision decoding","volume":"11","author":"Ding","year":"2024","journal-title":"Natl Sci Rev"},{"key":"2026082813173166300_btag563-B8","doi-asserted-by":"crossref","first-page":"6026","DOI":"10.1038\/s41467-023-41729-1","article-title":"A digital twin for DNA data storage based on comprehensive quantification of errors and biases","volume":"14","author":"Gimpel","year":"2023","journal-title":"Nat Commun"},{"key":"2026082813173166300_btag563-B9","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/nature11875","article-title":"Towards practical, high-capacity, low-maintenance information storage in synthesized DNA","volume":"494","author":"Goldman","year":"2013","journal-title":"Nature"},{"key":"2026082813173166300_btag563-B10","doi-asserted-by":"crossref","first-page":"2552","DOI":"10.1002\/anie.201411378","article-title":"Robust chemical preservation of digital information on DNA in silica with error-correcting codes","volume":"54","author":"Grass","year":"2015","journal-title":"Angew Chem Int Ed Engl"},{"key":"2026082813173166300_btag563-B11","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/TNB.2023.3284406","article-title":"Iterative soft decoding algorithm for DNA storage using quality score and redecoding","volume":"23","author":"Jeong","year":"2024","journal-title":"IEEE Trans Nanobiosci"},{"key":"2026082813173166300_btag563-B12","doi-asserted-by":"crossref","first-page":"12095","DOI":"10.1038\/s41598-022-16222-2","article-title":"Quantification of synthetic errors during chemical synthesis of DNA and its suppression by non-canonical nucleosides","volume":"12","author":"Masaki","year":"2022","journal-title":"Sci Rep"},{"key":"2026082813173166300_btag563-B13","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1038\/s41467-021-21587-5","article-title":"DNA stability: a central design consideration for DNA data storage systems","volume":"12","author":"Matange","year":"2021","journal-title":"Nat Commun"},{"key":"2026082813173166300_btag563-B14","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41596-019-0244-5","article-title":"Reading and writing digital data in DNA","volume":"15","author":"Meiser","year":"2020","journal-title":"Nat Protoc"},{"key":"2026082813173166300_btag563-B15","doi-asserted-by":"crossref","first-page":"e90","DOI":"10.1093\/nar\/gkr344","article-title":"Sequence-specific error profile of illumina sequencers","volume":"39","author":"Nakamura","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2026082813173166300_btag563-B16","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1038\/nbt.4079","article-title":"Random access in large-scale DNA data storage","volume":"36","author":"Organick","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2026082813173166300_btag563-B17","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1038\/s43588-022-00231-2","article-title":"Towards practical and robust DNA-based data archiving using the yin-yang codec system","volume":"2","author":"Ping","year":"2022","journal-title":"Nat Comput Sci"},{"key":"2026082813173166300_btag563-B18","doi-asserted-by":"crossref","first-page":"18489","DOI":"10.1073\/pnas.2004821117","article-title":"HEDGES error-correcting code for DNA storage corrects indels and allows sequence constraints","volume":"117","author":"Press","year":"2020","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026082813173166300_btag563-B19","doi-asserted-by":"crossref","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":"2026082813173166300_btag563-B20","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.1038\/s41598-024-51730-3","article-title":"Reconstruction algorithms for DNA-storage systems","volume":"14","author":"Sabary","year":"2024","journal-title":"Sci Rep"},{"key":"2026082813173166300_btag563-B21","doi-asserted-by":"crossref","first-page":"qzae025","DOI":"10.1093\/gpbjnl\/qzae025","article-title":"BSAlign: a library for nucleotide sequence alignment","volume":"22","author":"Shao","year":"2024","journal-title":"Genomics Proteomics Bioinformatics"},{"key":"2026082813173166300_btag563-B22","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1016\/j.synbio.2025.03.006","article-title":"DNA storage: the future direction for medical cold data storage","volume":"10","author":"Shen","year":"2025","journal-title":"Synth Syst Biotechnol"},{"key":"2026082813173166300_btag563-B23","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/nature24286","article-title":"DNA sequencing at 40: past, present and future","volume":"550","author":"Shendure","year":"2017","journal-title":"Nature"},{"key":"2026082813173166300_btag563-B24","doi-asserted-by":"crossref","first-page":"5361","DOI":"10.1038\/s41467-022-33046-w","article-title":"Robust data storage in DNA by de Bruijn graph-based de novo strand assembly","volume":"13","author":"Song","year":"2022","journal-title":"Nat Commun"},{"key":"2026082813173166300_btag563-B25","doi-asserted-by":"crossref","first-page":"lqab019","DOI":"10.1093\/nargab\/lqab019","article-title":"Sequencing error profiles of illumina sequencing instruments","volume":"3","author":"Stoler","year":"2021","journal-title":"NAR Genom Bioinform"},{"key":"2026082813173166300_btag563-B26","first-page":"6000","author":"Vaswani","year":"2017"},{"key":"2026082813173166300_btag563-B27","doi-asserted-by":"crossref","first-page":"btaf006","DOI":"10.1093\/bioinformatics\/btaf006","article-title":"Nanopore decoding with speed and versatility for data storage","volume":"41","author":"Volkel","year":"2024","journal-title":"Bioinformatics"},{"key":"2026082813173166300_btag563-B28","doi-asserted-by":"crossref","first-page":"btad572","DOI":"10.1093\/bioinformatics\/btad572","article-title":"FrameD: framework for DNA-based data storage design, verification, and validation","volume":"39","author":"Volkel","year":"2023","journal-title":"Bioinformatics"},{"key":"2026082813173166300_btag563-B29","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.21105\/joss.01316","article-title":"Badread: simulation of error-prone long reads","volume":"4","author":"Wick","year":"2019","journal-title":"JOSS"},{"key":"2026082813173166300_btag563-B30","volume-title":"Worldwide IDC Global DataSphere Forecast, 2024\u20132028: AI Everywhere, But Upsurge in Data Will Take Time","author":"Wright","year":"2024"},{"key":"2026082813173166300_btag563-B31","doi-asserted-by":"crossref","first-page":"5451","DOI":"10.1093\/nar\/gkab230","article-title":"Uncertainties in synthetic DNA-based data storage","volume":"49","author":"Xu","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026082813173166300_btag563-B32","doi-asserted-by":"crossref","first-page":"2402951","DOI":"10.1002\/advs.202402951","article-title":"Overcoming the high error rate of composite DNA letters-based digital storage through soft-decision decoding","volume":"11","author":"Xu","year":"2024","journal-title":"Adv Sci"},{"key":"2026082813173166300_btag563-B33","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1186\/s12859-022-04723-w","article-title":"DeSP: a systematic DNA storage error simulation pipeline","volume":"23","author":"Yuan","year":"2022","journal-title":"BMC Bioinform"},{"key":"2026082813173166300_btag563-B34","doi-asserted-by":"crossref","first-page":"32071","DOI":"10.1038\/s41598-024-83806-5","article-title":"A generative adversarial network for multiple reads reconstruction in DNA storage","volume":"14","author":"Zheng","year":"2024","journal-title":"Sci Rep"},{"key":"2026082813173166300_btag563-B35","first-page":"950","article-title":"DNA fountain enables a robust and efficient storage architecture","volume":"355","author":"Zielinski","year":"2017","journal-title":"Science (1979)"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag563\/70263839\/btag563.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/8\/btag563\/70263839\/btag563.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/8\/btag563\/70263839\/btag563.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:17:42Z","timestamp":1787937462000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag563\/8744088"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,28]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag563","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,7,28]]},"article-number":"btag563"}}