{"id":"https://openalex.org/W4281786521","doi":"https://doi.org/10.1145/3523286.3524511","title":"Study on reference-based FASTQ genome sequences compression","display_name":"Study on reference-based FASTQ genome sequences compression","publication_year":2022,"publication_date":"2022-01-21","ids":{"openalex":"https://openalex.org/W4281786521","doi":"https://doi.org/10.1145/3523286.3524511"},"language":"en","primary_location":{"id":"doi:10.1145/3523286.3524511","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523286.3524511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 2nd International Conference on Bioinformatics and Intelligent Computing","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/A5100425944","display_name":"Wenlong Li","orcid":"https://orcid.org/0000-0002-5351-7076"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlong Li","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385443","display_name":"Jianhua Chen","orcid":"https://orcid.org/0000-0002-3637-2565"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Chen","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002064126","display_name":"Zhiwen Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Lu","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9764000177383423,"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/lossless-compression","display_name":"Lossless compression","score":0.8711011409759521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773318886756897},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6527791619300842},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5957077741622925},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5819234251976013},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5261109471321106},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5118564963340759},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.49166470766067505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2967619299888611},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08626732230186462},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0858793556690216},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07064181566238403}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8711011409759521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773318886756897},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6527791619300842},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5957077741622925},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5819234251976013},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5261109471321106},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5118564963340759},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.49166470766067505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2967619299888611},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08626732230186462},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0858793556690216},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07064181566238403},{"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/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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523286.3524511","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523286.3524511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 2nd International Conference on Bioinformatics and Intelligent Computing","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":10,"referenced_works":["https://openalex.org/W1931027898","https://openalex.org/W2013697960","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2597471102","https://openalex.org/W2764165465","https://openalex.org/W2890254075","https://openalex.org/W2998912266","https://openalex.org/W4400064739","https://openalex.org/W6959643953"],"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":{"As":[0],"the":[1,7,15,32,75,78,85,97,103,115,120],"cost":[2],"of":[3,10,18,27,34,38,106,112],"genome":[4,52,113],"sequencing":[5],"decreases,":[6],"large":[8],"amount":[9],"genomic":[11],"data":[12,36],"generated":[13],"brings":[14],"storage":[16],"problem":[17],"this":[19],"massive":[20],"data.":[21],"We":[22,57],"still":[23],"have":[24],"a":[25,46,59],"lot":[26],"work":[28],"to":[29,44,69,94],"do":[30],"in":[31,54,128],"field":[33],"specialized":[35],"compression":[37,49,60,98,123],"FASTQ":[39,55,121],"files.":[40],"This":[41],"paper":[42],"aims":[43],"explore":[45],"reference-based":[47],"lossless":[48],"algorithm":[50,117],"for":[51],"sequences":[53],"format.":[56],"propose":[58],"scheme":[61],"based":[62],"on":[63,109],"longest":[64],"matching":[65],"by":[66],"using":[67],"FMD-index":[68],"support":[70],"exact":[71],"match":[72],"searching.":[73],"At":[74],"same":[76],"time,":[77],"reverse":[79],"complementary":[80],"sequence":[81],"is":[82,126],"used":[83],"and":[84,88,125],"insertion,":[86],"deletion":[87],"replacement":[89],"operations":[90],"are":[91],"described":[92],"effectively":[93],"further":[95],"improve":[96],"ratio.":[99],"In":[100],"comparison":[101],"with":[102],"experimental":[104],"results":[105],"five":[107],"compressors":[108],"seven":[110],"sets":[111],"data,":[114],"proposed":[116],"significantly":[118],"improves":[119],"file":[122],"ratios,":[124],"competitive":[127],"running":[129],"time.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}