{"id":"https://openalex.org/W2011304494","doi":"https://doi.org/10.1109/icalip.2014.7009935","title":"K-means clustering based compression algorithm for the high-throughput DNA sequence","display_name":"K-means clustering based compression algorithm for the high-throughput DNA sequence","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2011304494","doi":"https://doi.org/10.1109/icalip.2014.7009935","mag":"2011304494"},"language":"en","primary_location":{"id":"doi:10.1109/icalip.2014.7009935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icalip.2014.7009935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Audio, Language and Image Processing","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/A5112642889","display_name":"Li Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Tan","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100327194","display_name":"Jifeng Sun","orcid":"https://orcid.org/0000-0002-0201-8226"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifeng Sun","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"952","last_page":"955"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9958000183105469,"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":0.9886999726295471,"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":0.7829000949859619},{"id":"https://openalex.org/keywords/huffman-coding","display_name":"Huffman coding","score":0.7560930252075195},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7077940106391907},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.514710009098053},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.4988574981689453},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47296279668807983},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4642062783241272},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.46365058422088623},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.44660359621047974},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.41902074217796326},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.16935893893241882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11795985698699951}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829000949859619},{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.7560930252075195},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7077940106391907},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.514710009098053},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.4988574981689453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47296279668807983},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4642062783241272},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.46365058422088623},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.44660359621047974},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.41902074217796326},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.16935893893241882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11795985698699951},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icalip.2014.7009935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icalip.2014.7009935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Audio, Language and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W153132339","https://openalex.org/W1528514765","https://openalex.org/W1979405897","https://openalex.org/W2010637273","https://openalex.org/W2019732294","https://openalex.org/W2024746529","https://openalex.org/W2090667881","https://openalex.org/W2096258819","https://openalex.org/W2138196010","https://openalex.org/W2142003566","https://openalex.org/W2146028503","https://openalex.org/W2147492358","https://openalex.org/W2375624299","https://openalex.org/W6606157611"],"related_works":["https://openalex.org/W1557642114","https://openalex.org/W1762028264","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/W2169871401"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"compression":[4,71],"algorithm":[5],"based":[6,22],"on":[7,23,53],"K-means":[8,24],"clustering":[9,25,49],"for":[10],"high-through":[11],"DNA":[12,69],"sequence":[13,70],"(DNAC-K).":[14],"In":[15],"DNAC-K,":[16],"we":[17],"create":[18],"cluster":[19],"of":[20,37,48,61,65],"sequences":[21],"method":[26],"at":[27],"first,":[28],"then":[29],"iterate":[30],"clusters":[31],"according":[32],"to":[33,44],"the":[34,46,66],"edit":[35],"distances":[36],"subsequences,":[38],"and":[39],"finally,":[40],"adopt":[41],"Huffman":[42],"coding":[43],"encode":[45],"result":[47],"result.":[50],"Experimental":[51],"results":[52],"several":[54],"sequencing":[55],"data":[56],"sets":[57],"demonstrate":[58],"better":[59],"performance":[60],"DNAC-K":[62],"than":[63],"many":[64],"current":[67],"high-throughput":[68],"algorithms.":[72]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}