{"id":"https://openalex.org/W4403010856","doi":"https://doi.org/10.1186/s12859-024-05943-y","title":"Efficient and low-complexity variable-to-variable length coding for DNA storage","display_name":"Efficient and low-complexity variable-to-variable length coding for DNA storage","publication_year":2024,"publication_date":"2024-10-01","ids":{"openalex":"https://openalex.org/W4403010856","doi":"https://doi.org/10.1186/s12859-024-05943-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/39354338"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-024-05943-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05943-y","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05943-y.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05943-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007460791","display_name":"Yunfei Gao","orcid":"https://orcid.org/0000-0003-0543-2091"},"institutions":[{"id":"https://openalex.org/I2801556517","display_name":"Ruijin Hospital","ror":"https://ror.org/01hv94n30","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2801556517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Gao","raw_affiliation_strings":["SJTU-Ruijing-UIH Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, No. 197 Ruijin Second Road, Shanghai, 200025, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SJTU-Ruijing-UIH Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, No. 197 Ruijin Second Road, Shanghai, 200025, China","institution_ids":["https://openalex.org/I2801556517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049196468","display_name":"Albert No","orcid":"https://orcid.org/0000-0002-6346-4182"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Albert No","raw_affiliation_strings":["Department of Artificial Intelligence, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, 03722, South Korea. albertno@yonsei.ac.kr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, 03722, South Korea. albertno@yonsei.ac.kr","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049196468"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.5598,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66292519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"320","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.991100013256073,"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-microarray","display_name":"DNA microarray","score":0.5393033623695374},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5289328694343567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48670199513435364},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.47169092297554016},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4547733962535858},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.43457168340682983},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34302982687950134},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3278194069862366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21504747867584229},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14899256825447083},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1259947419166565}],"concepts":[{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5393033623695374},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5289328694343567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48670199513435364},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.47169092297554016},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4547733962535858},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.43457168340682983},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34302982687950134},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3278194069862366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21504747867584229},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14899256825447083},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1259947419166565},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001482","descriptor_name":"Base Composition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-024-05943-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05943-y","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05943-y.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:39354338","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39354338","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,"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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11446080","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11446080","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11446080/pdf/12859_2024_Article_5943.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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:7a58cb30abc84c53b4e047da35802eb4","is_oa":false,"landing_page_url":"https://doaj.org/article/7a58cb30abc84c53b4e047da35802eb4","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,"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":"BMC Bioinformatics, Vol 25, Iss 1, Pp 1-14 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-024-05943-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05943-y","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05943-y.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6055553193","display_name":null,"funder_award_id":"2022M3C1A3081366","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7533041823","display_name":null,"funder_award_id":"NRF-2022M3C1A3081366","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403010856.pdf","grobid_xml":"https://content.openalex.org/works/W4403010856.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W148564650","https://openalex.org/W2025383314","https://openalex.org/W2101294025","https://openalex.org/W2107762567","https://openalex.org/W2162980030","https://openalex.org/W2471091339","https://openalex.org/W2592122940","https://openalex.org/W2896926252","https://openalex.org/W2940793962","https://openalex.org/W2944582089","https://openalex.org/W2951269465","https://openalex.org/W2963960014","https://openalex.org/W2972568116","https://openalex.org/W3023665079","https://openalex.org/W3042993760","https://openalex.org/W3085098780","https://openalex.org/W3091919520","https://openalex.org/W3159176552","https://openalex.org/W4200213163","https://openalex.org/W4205333919","https://openalex.org/W4226211215","https://openalex.org/W4319333566"],"related_works":["https://openalex.org/W2415545834","https://openalex.org/W2069695727","https://openalex.org/W2150084125","https://openalex.org/W2118505788","https://openalex.org/W1802639773","https://openalex.org/W1972196578","https://openalex.org/W1490878237","https://openalex.org/W1542823905","https://openalex.org/W2990314835","https://openalex.org/W4254166511"],"abstract_inverted_index":{"Efficient":[0],"DNA-based":[1],"storage":[2],"systems":[3],"offer":[4],"substantial":[5],"capacity":[6],"and":[7,39,90,113,132,141],"longevity":[8],"at":[9,163],"reduced":[10],"costs,":[11],"addressing":[12],"anticipated":[13],"data":[14,18,131],"growth.":[15],"However,":[16],"encoding":[17,169],"into":[19],"DNA":[20,85],"sequences":[21],"is":[22],"limited":[23],"by":[24],"two":[25],"key":[26],"constraints:":[27],"1)":[28],"a":[29,41,76,96,167],"maximum":[30],"of":[31,84,121,155],"h":[32],"consecutive":[33],"identical":[34],"bases":[35],"(homopolymer":[36],"constraint":[37,56],"h),":[38],"2)":[40],"GC":[42,91],"ratio":[43],"between":[44],"$$":[45,53],"[0.5":[46],"-":[47],"c_{{GC}},":[48],"0.5":[49],"+":[50],"c_{{GC}}":[51],"]":[52],"(GC":[54],"content":[55,92],"$$c_{GC}$$":[57],").":[58],"Sequencing":[59],"or":[60],"synthesis":[61],"errors":[62],"tend":[63],"to":[64,102,151],"increase":[65],"when":[66,137],"these":[67,103],"constraints":[68,104],"are":[69],"violated.":[70],"In":[71],"this":[72],"research,":[73],"we":[74],"address":[75],"pure":[77],"source":[78],"coding":[79,98],"problem":[80],"in":[81],"the":[82,119,122,146,152],"context":[83],"storage,":[86],"considering":[87],"both":[88,128],"homopolymer":[89],"constraints.":[93],"We":[94,117,165],"introduce":[95],"novel":[97],"technique":[99],"that":[100,171],"adheres":[101],"while":[105],"maintaining":[106],"linear":[107],"complexity":[108],"for":[109],"increased":[110],"block":[111],"lengths":[112],"achieving":[114],"near-optimal":[115,182],"rates.":[116,183],"demonstrate":[118],"effectiveness":[120],"proposed":[123],"method":[124,170],"through":[125],"experiments":[126],"on":[127,175],"randomly":[129],"generated":[130],"existing":[133],"files.":[134],"For":[135],"example,":[136],"$$h":[138],"=":[139,143],"4$$":[140],"$$c_{GC}":[142],"0.05$$":[144],",":[145],"rate":[147],"reached":[148],"1.988,":[149],"close":[150],"theoretical":[153],"limit":[154],"1.990.":[156],"The":[157],"associated":[158],"code":[159],"can":[160],"be":[161],"accessed":[162],"GitHub.":[164],"propose":[166],"variable-to-variable-length":[168],"does":[172],"not":[173],"rely":[174],"concatenating":[176],"short":[177],"predefined":[178],"sequences,":[179],"which":[180],"achieves":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}