{"id":"https://openalex.org/W4405442497","doi":"https://doi.org/10.1145/3698587.3701490","title":"Normalized Compression Distance for DNA Classification","display_name":"Normalized Compression Distance for DNA Classification","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4405442497","doi":"https://doi.org/10.1145/3698587.3701490"},"language":"en","primary_location":{"id":"doi:10.1145/3698587.3701490","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698587.3701490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","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/A5098975021","display_name":"Gavin Hearne","orcid":"https://orcid.org/0009-0006-9193-4264"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gavin L.A. Hearne","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0006-9193-4264","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112389147","display_name":"Mohammad S. Refahi","orcid":null},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad S. Refahi","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0000-9581-5883","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115464740","display_name":"Haozhe Neil Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haozhe Neil Duan","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0004-4330-196X","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089794666","display_name":"James R. Brown","orcid":"https://orcid.org/0000-0002-9368-627X"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James R. Brown","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9368-627X","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail L. Rosen","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1763-5750","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72816309"],"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":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9847999811172485,"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":0.9847999811172485,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.978600025177002,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9449999928474426,"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":0.5734467506408691},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5124750733375549},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4899386763572693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4272548258304596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.357101708650589},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11008870601654053},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.05846723914146423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734467506408691},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5124750733375549},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4899386763572693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4272548258304596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.357101708650589},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11008870601654053},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.05846723914146423}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698587.3701490","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698587.3701490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G839467699","display_name":null,"funder_award_id":"1936791","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4385571422"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"The":[0,18],"increasingly":[1,51],"common":[2],"use":[3,132],"of":[4,21,54,62,72,87,133,141,149,156,174],"next-generation":[5],"sequencing":[6],"has":[7,23,81],"enabled":[8],"greater":[9],"access":[10],"to":[11,58,94,102,110,118,170],"large-scale":[12],"(meta-)genomic":[13],"datasets":[14],"than":[15],"ever":[16],"before.":[17],"resulting":[19],"deluge":[20],"data":[22,56],"made":[24],"the":[25,59,85,131,154,166],"quest":[26],"for":[27,36,43,69,168],"efficient":[28],"DNA":[29,44],"sequence":[30,40,45,55,73,123],"classification":[31,46,89,148],"methods":[32,42,70],"an":[33,108],"urgent":[34],"challenge":[35],"downstream":[37],"analyses.":[38],"Traditional":[39],"alignment-based":[41],"struggle":[47],"when":[48],"presented":[49],"with":[50],"large":[52],"volumes":[53],"due":[57],"computational":[60],"complexity":[61],"alignment.":[63,76],"Subsequently,":[64],"there":[65],"is":[66],"a":[67,91,134],"need":[68],"capable":[71],"identification":[74],"without":[75],"Normalized":[77],"compression":[78,100],"distance":[79],"(NCD)":[80],"demonstrated":[82],"capabilities":[83],"in":[84,158],"field":[86],"text":[88],"as":[90,121],"low-resource":[92],"alternative":[93],"deep":[95],"neural":[96],"networks":[97],"by":[98],"leveraging":[99],"algorithms":[101],"approximate":[103],"Kolmogorov":[104],"information":[105],"distance.":[106],"In":[107],"effort":[109],"apply":[111],"this":[112],"technique":[113],"toward":[114],"genomics":[115],"tasks":[116],"akin":[117],"tools":[119],"such":[120],"Many-against-Many":[122],"searching":[124],"(MMseqs)":[125],"and":[126,146,162],"Kraken2,":[127],"we":[128,163],"have":[129],"explored":[130],"gzip-based":[135],"NCD":[136,157,169],"towards":[137],"both":[138],"gene":[139],"labeling":[140],"ORFs":[142],"(open":[143],"reading":[144],"frames)":[145],"taxonomic":[147],"short":[150],"reads.":[151,176],"This":[152],"demonstrates":[153],"efficacy":[155],"diverse":[159],"multitask":[160],"classification,":[161],"further":[164],"explore":[165],"capacity":[167],"classify":[171],"larger":[172],"libraries":[173],"metagenomic":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
