{"id":"https://openalex.org/W4403094469","doi":"https://doi.org/10.1109/tcbb.2024.3473899","title":"LEC-Codec: Learning-Based Genome Data Compression","display_name":"LEC-Codec: Learning-Based Genome Data Compression","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4403094469","doi":"https://doi.org/10.1109/tcbb.2024.3473899","pmid":"https://pubmed.ncbi.nlm.nih.gov/39361454"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2024.3473899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2024.3473899","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066669376","display_name":"Zhenhao Sun","orcid":"https://orcid.org/0000-0002-3594-8104"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenhao Sun","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3594-8104","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377170","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-5655-1464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Data Sciences, Lingnan University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-5655-1464","affiliations":[{"raw_affiliation_string":"School of Data Sciences, Lingnan University, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["School of Data Sciences, Lingnan University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"School of Data Sciences, Lingnan University, Hong Kong","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2233,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82422263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"6","first_page":"2447","last_page":"2458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9930999875068665,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9930999875068665,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9670000076293945,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9093000292778015,"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/codec","display_name":"Codec","score":0.721264123916626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.623317301273346},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5290089249610901},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5188942551612854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.284925252199173},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14141717553138733},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0909000039100647}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.721264123916626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.623317301273346},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5290089249610901},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5188942551612854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.284925252199173},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14141717553138733},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0909000039100647},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2024.3473899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2024.3473899","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:39361454","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39361454","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W26729696","https://openalex.org/W1498357809","https://openalex.org/W1970231722","https://openalex.org/W1998127289","https://openalex.org/W2000466469","https://openalex.org/W2012680439","https://openalex.org/W2013405042","https://openalex.org/W2096258819","https://openalex.org/W2108278098","https://openalex.org/W2125598538","https://openalex.org/W2127912200","https://openalex.org/W2146028503","https://openalex.org/W2151687858","https://openalex.org/W2158678815","https://openalex.org/W2159906372","https://openalex.org/W2295453219","https://openalex.org/W2560975170","https://openalex.org/W2577653916","https://openalex.org/W2635555833","https://openalex.org/W2763684694","https://openalex.org/W2912135067","https://openalex.org/W2954821630","https://openalex.org/W2963940468","https://openalex.org/W2985586545","https://openalex.org/W2986984493","https://openalex.org/W3095840733","https://openalex.org/W3098741556","https://openalex.org/W4205511747","https://openalex.org/W4294989829","https://openalex.org/W4313255750","https://openalex.org/W4384922969","https://openalex.org/W4391111375"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2107680156","https://openalex.org/W2964213236","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W2039662546","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,87],"Learning-based":[6],"gEnome":[7],"Codec":[8],"(LEC),":[9],"which":[10,38],"is":[11,60,104],"designed":[12],"for":[13,70,82],"high":[14],"efficiency":[15],"and":[16,33,48,77,94,112],"enhanced":[17],"flexibility.":[18],"The":[19,53],"LEC":[20],"integrates":[21],"several":[22],"advanced":[23],"technologies,":[24],"including":[25],"Group":[26],"of":[27,37,89,109],"Bases":[28],"(GoB)":[29],"compression,":[30],"multi-stride":[31],"coding":[32,46],"bidirectional":[34],"prediction,":[35],"all":[36],"are":[39],"aimed":[40],"at":[41],"optimizing":[42],"the":[43,101],"balance":[44],"between":[45],"complexity":[47,81],"performance":[49,111],"in":[50,56,107,116],"lossless":[51],"compression.":[52],"model":[54],"applied":[55],"our":[57],"proposed":[58,102],"codec":[59],"data-driven,":[61],"based":[62],"on":[63,91],"deep":[64],"neural":[65],"networks":[66],"to":[67],"infer":[68],"probabilities":[69],"each":[71],"symbol,":[72],"enabling":[73],"fully":[74],"parallel":[75],"encoding":[76],"decoding":[78],"with":[79],"configured":[80],"diverse":[83],"applications.":[84,118],"Based":[85],"upon":[86],"set":[88],"configurations":[90],"compression":[92,110],"ratios":[93],"inference":[95],"speed,":[96],"experimental":[97],"results":[98],"show":[99],"that":[100],"method":[103],"very":[105],"efficient":[106],"terms":[108],"provides":[113],"improved":[114],"flexibility":[115],"real-world":[117]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}