{"id":"https://openalex.org/W4406774579","doi":"https://doi.org/10.3389/fbinf.2024.1489704","title":"A novel lossless encoding algorithm for data compression\u2013genomics data as an exemplar","display_name":"A novel lossless encoding algorithm for data compression\u2013genomics data as an exemplar","publication_year":2025,"publication_date":"2025-01-23","ids":{"openalex":"https://openalex.org/W4406774579","doi":"https://doi.org/10.3389/fbinf.2024.1489704","pmid":"https://pubmed.ncbi.nlm.nih.gov/39917339"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2024.1489704","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2024.1489704","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2024.1489704/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2024.1489704/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074178239","display_name":"Anas Al-okaily","orcid":"https://orcid.org/0000-0002-1188-8266"},"institutions":[{"id":"https://openalex.org/I2799468983","display_name":"King Hussein Cancer Center","ror":"https://ror.org/0564xsr50","country_code":"JO","type":"nonprofit","lineage":["https://openalex.org/I2799468983"]}],"countries":["JO"],"is_corresponding":true,"raw_author_name":"Anas Al-okaily","raw_affiliation_strings":["Department of Cell Therapy and Applied Genomics, King Hussein Cancer Center, Amman, Jordan"],"affiliations":[{"raw_affiliation_string":"Department of Cell Therapy and Applied Genomics, King Hussein Cancer Center, Amman, Jordan","institution_ids":["https://openalex.org/I2799468983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055032061","display_name":"Abdelghani Tbakhi","orcid":null},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdelghani Tbakhi","raw_affiliation_strings":["Department of Pathology and Molecular Medicine, McMaster University, Hamilton, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Pathology and Molecular Medicine, McMaster University, Hamilton, ON, Canada","institution_ids":["https://openalex.org/I98251732"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074178239"],"corresponding_institution_ids":["https://openalex.org/I2799468983"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":2.2283,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87207046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"4","issue":null,"first_page":"1489704","last_page":"1489704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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":0.9937999844551086,"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":0.9785000085830688,"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":0.7677491903305054},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.7502378225326538},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.7210835218429565},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5917987823486328},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5498273372650146},{"id":"https://openalex.org/keywords/entropy-encoding","display_name":"Entropy encoding","score":0.5275570750236511},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47538459300994873},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43462440371513367},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4331135153770447},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4145238697528839},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.41194531321525574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.276541143655777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677491903305054},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.7502378225326538},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.7210835218429565},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5917987823486328},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5498273372650146},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.5275570750236511},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47538459300994873},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43462440371513367},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4331135153770447},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4145238697528839},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.41194531321525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.276541143655777},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2024.1489704","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2024.1489704","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2024.1489704/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:39917339","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39917339","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11799261","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11799261","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11799261/pdf/fbinf-04-1489704.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Bioinform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:3c58369ff8fc4259bdd5d3a4439859ee","is_oa":true,"landing_page_url":"https://doaj.org/article/3c58369ff8fc4259bdd5d3a4439859ee","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 4 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2024.1489704","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2024.1489704","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2024.1489704/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406774579.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W133505062","https://openalex.org/W1568325880","https://openalex.org/W1696088198","https://openalex.org/W1830917984","https://openalex.org/W1970231722","https://openalex.org/W1975965284","https://openalex.org/W1990653637","https://openalex.org/W1993742159","https://openalex.org/W2022126655","https://openalex.org/W2029195137","https://openalex.org/W2057978375","https://openalex.org/W2060108852","https://openalex.org/W2069056415","https://openalex.org/W2085880494","https://openalex.org/W2092880969","https://openalex.org/W2107745473","https://openalex.org/W2107927941","https://openalex.org/W2108234281","https://openalex.org/W2117608012","https://openalex.org/W2122962290","https://openalex.org/W2123810473","https://openalex.org/W2126377735","https://openalex.org/W2128777897","https://openalex.org/W2137012911","https://openalex.org/W2138026948","https://openalex.org/W2155729921","https://openalex.org/W2161488606","https://openalex.org/W2161628678","https://openalex.org/W2163294786","https://openalex.org/W2298002002","https://openalex.org/W2461250372","https://openalex.org/W2531091319","https://openalex.org/W2585360326","https://openalex.org/W2766668450","https://openalex.org/W2802735740","https://openalex.org/W2804154915","https://openalex.org/W2978725006","https://openalex.org/W3016802618","https://openalex.org/W3035703949","https://openalex.org/W3038746171","https://openalex.org/W4232099444","https://openalex.org/W6633884508","https://openalex.org/W6733550226"],"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/W2032414556","https://openalex.org/W1513042817","https://openalex.org/W2096000848"],"abstract_inverted_index":{"Data":[0],"compression":[1,40,122,141],"is":[2,35,74,83],"a":[3,31,51,101,117],"challenging":[4],"and":[5,21,44,67,152,159],"increasingly":[6],"important":[7],"problem.":[8],"As":[9],"the":[10,39,56,86,121,134,140],"amount":[11],"of":[12,41,123,142],"data":[13,43,73,144],"generated":[14,157],"daily":[15,158],"continues":[16],"to":[17,112,130,139],"increase,":[18],"efficient":[19],"transmission":[20],"storage":[22],"have":[23],"never":[24],"been":[25],"more":[26],"critical.":[27],"In":[28],"this":[29],"study,":[30],"novel":[32],"encoding":[33],"algorithm":[34,49,135],"proposed,":[36],"motivated":[37],"by":[38,54],"DNA":[42],"associated":[45],"characteristics.":[46],"The":[47,72,114],"proposed":[48],"follows":[50],"divide-and-conquer":[52],"approach":[53,82],"scanning":[55],"whole":[57],"genome,":[58,125],"classifying":[59],"subsequences":[60,70],"based":[61],"on":[62],"similarities":[63],"in":[64,108,120,161],"their":[65],"content,":[66],"binning":[68],"similar":[69],"together.":[71],"then":[75],"compressed":[76],"into":[77],"each":[78,124],"bin":[79],"independently.":[80],"This":[81],"different":[84],"than":[85],"currently":[87],"known":[88],"approaches:":[89],"entropy,":[90],"dictionary,":[91],"predictive,":[92],"or":[93],"transform-based":[94],"methods.":[95],"Proof-of-concept":[96],"performance":[97],"was":[98],"evaluated":[99],"using":[100],"benchmark":[102],"dataset":[103],"with":[104],"seventeen":[105],"genomes":[106],"ranging":[107],"size":[109],"from":[110],"kilobytes":[111],"gigabytes.":[113],"results":[115],"showed":[116],"considerable":[118],"improvement":[119],"preserving":[126],"several":[127],"megabytes":[128],"compared":[129],"state-of-the-art":[131],"tools.":[132],"Moreover,":[133],"can":[136],"be":[137],"applied":[138],"other":[143],"types":[145],"include":[146],"mainly":[147],"text,":[148],"numbers,":[149],"images,":[150],"audio,":[151],"video":[153],"which":[154],"are":[155],"being":[156],"unprecedentedly":[160],"massive":[162],"volumes.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}