{"id":"https://openalex.org/W4392904401","doi":"https://doi.org/10.1109/icassp48485.2024.10448360","title":"GeneFormer: Learned Gene Compression using Transformer-Based Context Modeling","display_name":"GeneFormer: Learned Gene Compression using Transformer-Based Context Modeling","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904401","doi":"https://doi.org/10.1109/icassp48485.2024.10448360"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5012574500","display_name":"Zhanbei Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanbei Cui","raw_affiliation_strings":["Tsinghua University,Institute for AI Industry Research (AIR)","Beijing University of Posts and Telecommunications","Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI Industry Research (AIR)","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022610350","display_name":"Tongda Xu","orcid":"https://orcid.org/0000-0002-5594-3992"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongda Xu","raw_affiliation_strings":["Tsinghua University,Institute for AI Industry Research (AIR)","Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI Industry Research (AIR)","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025137072","display_name":"Jia Wang","orcid":"https://orcid.org/0000-0003-2308-2259"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Wang","raw_affiliation_strings":["Tsinghua University,Institute for AI Industry Research (AIR)","Xidian University","Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI Industry Research (AIR)","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100957202","display_name":"Yu Liao","orcid":"https://orcid.org/0000-0001-7478-2867"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liao","raw_affiliation_strings":["Tsinghua University,Institute for AI Industry Research (AIR)","University of Science and Technology of China","Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI Industry Research (AIR)","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103335314","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-9445-9212"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Tsinghua University,Institute for AI Industry Research (AIR)","Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI Industry Research (AIR)","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4984,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96198043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8035","last_page":"8039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9934999942779541,"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/T12029","display_name":"DNA and Biological Computing","score":0.9829000234603882,"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/computer-science","display_name":"Computer science","score":0.7992600202560425},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.639410674571991},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6110646724700928},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5654400587081909},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5447670817375183},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47608819603919983},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4484335780143738},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4179418087005615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40599024295806885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33687686920166016},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22627884149551392},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09372755885124207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09346142411231995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992600202560425},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.639410674571991},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6110646724700928},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5654400587081909},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5447670817375183},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47608819603919983},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4484335780143738},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4179418087005615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40599024295806885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33687686920166016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22627884149551392},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09372755885124207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09346142411231995},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1777016212","https://openalex.org/W2064675550","https://openalex.org/W2129652681","https://openalex.org/W2143988400","https://openalex.org/W2158678815","https://openalex.org/W2165446840","https://openalex.org/W2552465432","https://openalex.org/W2747329762","https://openalex.org/W2912135067","https://openalex.org/W2964110616","https://openalex.org/W3024135825","https://openalex.org/W3095840733","https://openalex.org/W3184305333","https://openalex.org/W4224314722","https://openalex.org/W4226275767","https://openalex.org/W4239678514","https://openalex.org/W4385245566","https://openalex.org/W4392904401","https://openalex.org/W6810311916","https://openalex.org/W7044205949"],"related_works":["https://openalex.org/W4383723869","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974","https://openalex.org/W3007688875","https://openalex.org/W2766695209","https://openalex.org/W3123970444","https://openalex.org/W2110517301"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,10,16,66],"gene":[3,11,17,31,46,112],"sequencing":[4],"technology":[5],"sparks":[6],"an":[7,21],"explosive":[8],"growth":[9],"data.":[12],"Thus,":[13],"the":[14,64,67,80,102,123],"storage":[15],"data":[18,32],"has":[19],"become":[20],"important":[22],"issue.":[23],"Recently,":[24],"researchers":[25],"begin":[26],"to":[27,62,76],"investigate":[28],"deep":[29],"learning-based":[30,111],"compression,":[33],"which":[34],"outperforms":[35],"general":[36],"traditional":[37],"methods.":[38,114],"In":[39],"this":[40],"paper,":[41],"we":[42,52,71],"propose":[43],"a":[44,55,73],"transformer-based":[45],"compression":[47,81,95,113],"method":[48,75,91],"named":[49],"GeneFormer.":[50],"Specifically,":[51],"first":[53],"introduce":[54],"modified":[56],"transformer":[57],"encoder":[58],"with":[59,98],"latent":[60],"array":[61],"eliminate":[63],"dependency":[65],"nucleotide":[68],"sequence.":[69],"Then,":[70],"design":[72],"multi-level-grouping":[74],"accelerate":[77],"and":[78,101],"improve":[79],"process.":[82],"Experimental":[83],"results":[84],"on":[85,120],"real-world":[86],"datasets":[87],"show":[88],"that":[89],"our":[90,118],"achieves":[92],"significantly":[93,106],"better":[94],"ratio":[96],"compared":[97],"state-of-the-art":[99],"method,":[100],"decoding":[103],"speed":[104],"is":[105,125],"faster":[107],"than":[108],"all":[109],"existing":[110],"We":[115],"will":[116],"release":[117],"code":[119],"github":[121],"once":[122],"paper":[124],"accepted.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}