{"id":"https://openalex.org/W4372346368","doi":"https://doi.org/10.1109/icassp49357.2023.10096124","title":"Rethinking Learning-Based Method for Lossless Genome Compression","display_name":"Rethinking Learning-Based Method for Lossless Genome Compression","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346368","doi":"https://doi.org/10.1109/icassp49357.2023.10096124"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5091216233","display_name":"Han Yang","orcid":"https://orcid.org/0000-0003-1860-1472"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Han Yang","raw_affiliation_strings":["Alibaba Group,City Brain Lab, DAMO Academy","City Brain Lab, DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,City Brain Lab, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"City Brain Lab, DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722536","display_name":"Fei Gu","orcid":"https://orcid.org/0009-0007-4503-3155"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Fei Gu","raw_affiliation_strings":["Alibaba Group,City Brain Lab, DAMO Academy","City Brain Lab, DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,City Brain Lab, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"City Brain Lab, DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["Alibaba Group,City Brain Lab, DAMO Academy","City Brain Lab, DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,City Brain Lab, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"City Brain Lab, DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210086143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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":0.9991000294685364,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9972000122070312,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9908999800682068,"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/genome","display_name":"Genome","score":0.7636314630508423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.670082688331604},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5888671875},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5517138242721558},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5240975618362427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43124568462371826},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4283354580402374},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.425920695066452},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.419005423784256},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.41047149896621704},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2100169062614441},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20058521628379822},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11678799986839294}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7636314630508423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670082688331604},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5888671875},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5517138242721558},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5240975618362427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43124568462371826},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4283354580402374},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.425920695066452},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.419005423784256},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.41047149896621704},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2100169062614441},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20058521628379822},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11678799986839294}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W196533652","https://openalex.org/W1522301498","https://openalex.org/W1528514765","https://openalex.org/W1580101844","https://openalex.org/W1970231722","https://openalex.org/W1995875735","https://openalex.org/W2068841489","https://openalex.org/W2074490119","https://openalex.org/W2096410194","https://openalex.org/W2127912200","https://openalex.org/W2147492358","https://openalex.org/W2158190429","https://openalex.org/W2158678815","https://openalex.org/W2896457183","https://openalex.org/W2912135067","https://openalex.org/W2963940468","https://openalex.org/W3095840733","https://openalex.org/W3112249938","https://openalex.org/W4281926582","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6607873503","https://openalex.org/W6631190155","https://openalex.org/W6678795934","https://openalex.org/W6683269077","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2057878850","https://openalex.org/W2169871401","https://openalex.org/W3008492011"],"abstract_inverted_index":{"Lossless":[0],"genome":[1,20,26,51,85,106,116,131,137],"compression":[2,138],"plays":[3],"a":[4,78],"vital":[5],"role":[6],"in":[7,39,64,119],"genomic":[8],"analysis":[9],"procedure.":[10],"The":[11],"main":[12],"challenges":[13],"are":[14],"from":[15,149],"long":[16],"range":[17],"of":[18,25,50,60,103],"the":[19,61,72,104,115,141],"sequence":[21,52,107,117],"and":[22,53,76],"high":[23],"frequency":[24],"variants.":[27],"However,":[28],"existing":[29],"learning-based":[30],"methods":[31],"almost":[32],"all":[33],"rely":[34],"on":[35,94,146],"local":[36],"DNA":[37],"fragments":[38],"small":[40],"windows,":[41],"which":[42,112,133],"makes":[43],"them":[44],"unable":[45],"to":[46,56],"capture":[47],"deep":[48,73,110,126],"regularities":[49],"may":[54],"lead":[55],"unsatisfactory":[57],"performance":[58],"because":[59],"large":[62],"variability":[63],"different":[65,150],"individuals.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,99,123],"redesign":[71],"learning":[74],"model":[75,127],"propose":[77],"simple":[79],"yet":[80],"effective":[81],"position-driven":[82],"transformer":[83],"for":[84],"data":[86],"compression.":[87],"Our":[88],"approach,":[89],"called":[90],"CompressBERT,":[91],"is":[92,144],"based":[93],"two":[95],"core":[96],"designs.":[97],"First,":[98],"introduce":[100],"global":[101],"position":[102],"complete":[105],"into":[108],"our":[109,125,156],"model,":[111],"can":[113,134],"make":[114],"distinguishable":[118],"base":[120],"level.":[121],"Second,":[122],"pre-train":[124],"by":[128],"identifying":[129],"SNP":[130],"variants,":[132],"further":[135],"facilitate":[136],"task.":[139],"Furthermore,":[140],"proposed":[142],"CompressBERT":[143],"validated":[145],"three":[147],"datasets":[148],"species.":[151],"Experimental":[152],"results":[153],"show":[154],"that":[155],"approach":[157],"outperforms":[158],"state-of-the-art":[159],"methods.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}