{"id":"https://openalex.org/W2912330639","doi":"https://doi.org/10.1109/cisp-bmei.2018.8633219","title":"A Novel Compression Algorithm for High-Throughput DNA Sequence Based on Huffman Coding Method","display_name":"A Novel Compression Algorithm for High-Throughput DNA Sequence Based on Huffman Coding Method","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2912330639","doi":"https://doi.org/10.1109/cisp-bmei.2018.8633219","mag":"2912330639"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei.2018.8633219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei.2018.8633219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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/A5042436075","display_name":"Chuan He","orcid":"https://orcid.org/0000-0002-9983-7526"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan He","raw_affiliation_strings":["Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, 100871, P.R. China","Department of Biomedical Engineering, Peking University, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, 100871, P.R. China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Peking University, Beijing, P.R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060533782","display_name":"Huaiqiu Zhu","orcid":"https://orcid.org/0000-0002-6376-218X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiqiu Zhu","raw_affiliation_strings":["Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, 100871, P.R. China","Center for Quantitative Biology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, College of Engineering, Peking University, Beijing, 100871, P.R. China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Quantitative Biology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9933000206947327,"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":0.9925000071525574,"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/huffman-coding","display_name":"Huffman coding","score":0.9096571207046509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314907312393188},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6881848573684692},{"id":"https://openalex.org/keywords/arithmetic-coding","display_name":"Arithmetic coding","score":0.5516341328620911},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.522848904132843},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4927709400653839},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4741365611553192},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.4349161684513092},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42824065685272217},{"id":"https://openalex.org/keywords/context-adaptive-binary-arithmetic-coding","display_name":"Context-adaptive binary arithmetic coding","score":0.32802557945251465},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.29310306906700134},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.28549760580062866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12544718384742737},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11618000268936157},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11343982815742493},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10524570941925049}],"concepts":[{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.9096571207046509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314907312393188},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6881848573684692},{"id":"https://openalex.org/C153338461","wikidata":"https://www.wikidata.org/wiki/Q2651","display_name":"Arithmetic coding","level":4,"score":0.5516341328620911},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.522848904132843},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4927709400653839},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4741365611553192},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4349161684513092},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42824065685272217},{"id":"https://openalex.org/C175732694","wikidata":"https://www.wikidata.org/wiki/Q1128713","display_name":"Context-adaptive binary arithmetic coding","level":3,"score":0.32802557945251465},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.29310306906700134},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.28549760580062866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12544718384742737},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11618000268936157},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11343982815742493},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10524570941925049},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cisp-bmei.2018.8633219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei.2018.8633219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W18298531","https://openalex.org/W1794001512","https://openalex.org/W1931027898","https://openalex.org/W1969757078","https://openalex.org/W1970231722","https://openalex.org/W1992595091","https://openalex.org/W1994057432","https://openalex.org/W2016848076","https://openalex.org/W2092880969","https://openalex.org/W2128114769","https://openalex.org/W2138270253","https://openalex.org/W2146028503","https://openalex.org/W2147492358","https://openalex.org/W2153707226","https://openalex.org/W2346680365"],"related_works":["https://openalex.org/W1499106570","https://openalex.org/W2129652681","https://openalex.org/W4312628177","https://openalex.org/W1579872668","https://openalex.org/W4393034742","https://openalex.org/W3002053150","https://openalex.org/W4297360799","https://openalex.org/W2288784419","https://openalex.org/W2064300363","https://openalex.org/W2123072960"],"abstract_inverted_index":{"NGS":[0],"(Next":[1],"generation":[2],"sequencing)":[3],"technology":[4],"can":[5],"concurrently":[6],"accomplish":[7],"sequencing":[8],"of":[9,13,24,32,44,117],"a":[10,21,78,144],"large":[11,22,69],"scale":[12],"DNA":[14,25,33,49,62,85,152],"data":[15,34,63],"in":[16,20],"one":[17],"time,":[18],"resulting":[19],"number":[23],"short":[26],"reads.":[27],"The":[28,94,158],"transportation":[29],"and":[30,53,91,102,110,121,149,156],"processing":[31],"are":[35,41],"thus":[36],"faced":[37],"with":[38,134,143],"difficulties.":[39],"There":[40],"two":[42,150],"kinds":[43],"compression":[45,86,109,125,137,146,153],"methods":[46],"for":[47,60,71],"high-throughput":[48,84],"data,":[50],"reference-based":[51],"method":[52,57],"reference-free":[54,79,151],"method.":[55,93],"Reference-free":[56],"is":[58],"adaptive":[59],"compressing":[61,130],"from":[64],"different":[65],"species":[66],"without":[67],"storing":[68],"genome":[70,133],"reference.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"proposed":[77],"algorithm,":[80],"named":[81],"HDC,":[82],"realizing":[83],"based":[87],"on":[88,114],"Huffman":[89,100],"coding":[90,101],"dictionary":[92,105],"algorithm":[95,147,164],"builds":[96],"multiple":[97],"dictionaries":[98],"through":[99],"uses":[103],"the":[104,108,115,131,162,169],"to":[106],"finish":[107],"decompression.":[111],"By":[112],"testing":[113],"genomes":[116],"human,":[118],"green":[119],"monkey":[120],"horse,":[122],"HDC's":[123],"lowest":[124],"rate":[126],"reaches":[127],"0.192":[128],"when":[129],"human":[132],"chromosome":[135],"as":[136],"unit.":[138],"We":[139],"also":[140],"compared":[141],"HDC":[142,163],"conventional":[145],"gzip,":[148],"algorithms":[154],"Leon":[155],"ORCOM.":[157],"result":[159],"demonstrates":[160],"that":[161],"performs":[165],"significantly":[166],"best":[167],"among":[168],"three":[170],"algorithms.":[171]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}