{"id":"https://openalex.org/W4393207757","doi":"https://doi.org/10.1109/icpads60453.2023.00018","title":"SR2C: A Structurally Redundant Short Reads Collapser for Optimizing DNA Data Compression","display_name":"SR2C: A Structurally Redundant Short Reads Collapser for Optimizing DNA Data Compression","publication_year":2023,"publication_date":"2023-12-17","ids":{"openalex":"https://openalex.org/W4393207757","doi":"https://doi.org/10.1109/icpads60453.2023.00018"},"language":"en","primary_location":{"id":"doi:10.1109/icpads60453.2023.00018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads60453.2023.00018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"article","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/A5104667219","display_name":"Hui Sun","orcid":"https://orcid.org/0000-0003-0290-142X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Sun","raw_affiliation_strings":["Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101194582","display_name":"Huidong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huidong Ma","raw_affiliation_strings":["Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021782904","display_name":"Yingfeng Zheng","orcid":"https://orcid.org/0000-0002-0914-7864"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfeng Zheng","raw_affiliation_strings":["Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055033","display_name":"Haonan Xie","orcid":"https://orcid.org/0000-0001-5623-2845"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Xie","raw_affiliation_strings":["Guangxi University,School of Electrical Engineering,Nanning,China,530004"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi University,School of Electrical Engineering,Nanning,China,530004","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363453","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0001-8953-9050"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390120","display_name":"Xiaoguang Liu","orcid":"https://orcid.org/0000-0002-9010-3278"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Liu","raw_affiliation_strings":["Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367433","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0003-0387-2501"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of C.S., Nankai-Orange D.T. Joint Lab, Nankai-Baidu Joint Lab, ICIC, TMCC, SysNet, DISSec, GTIISC,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7133,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73105774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"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":0.9965999722480774,"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":0.6689473986625671},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5442188382148743},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4347352385520935},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24816244840621948},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07816869020462036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689473986625671},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5442188382148743},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4347352385520935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24816244840621948},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07816869020462036},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads60453.2023.00018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads60453.2023.00018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W645173616","https://openalex.org/W2013469333","https://openalex.org/W2097606916","https://openalex.org/W2108234281","https://openalex.org/W2111643688","https://openalex.org/W2155266131","https://openalex.org/W2257016270","https://openalex.org/W2267954589","https://openalex.org/W2371310157","https://openalex.org/W2610251765","https://openalex.org/W2795206838","https://openalex.org/W2968108654","https://openalex.org/W2998672854","https://openalex.org/W3004396747","https://openalex.org/W3008215921","https://openalex.org/W3044926932","https://openalex.org/W3097167873","https://openalex.org/W3137279194","https://openalex.org/W4280508214","https://openalex.org/W4317795251","https://openalex.org/W4361864316","https://openalex.org/W4379875228","https://openalex.org/W7032768804"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"The":[0],"current":[1],"redundant":[2,113],"sequence":[3,104,114],"deduplication":[4,115,156],"algorithms":[5,129],"cannot":[6,30],"remove":[7],"structural":[8],"repetitive":[9],"DNA":[10,85],"short":[11],"reads":[12],"such":[13],"as":[14],"mirror,":[15],"reverse,":[16],"paired,":[17],"and":[18,62,133,139,157],"complementary":[19],"palindromes":[20],"in":[21],"high-throughput":[22],"genomics":[23],"sequencing":[24,86],"data.":[25,87],"Moreover,":[26],"these":[27,52],"methods":[28],"also":[29],"construct":[31],"indexes":[32],"to":[33,40,79,110],"recover":[34],"the":[35,42,81,94,111,123],"original":[36],"sequences,":[37],"thus":[38],"failing":[39],"meet":[41],"requirements":[43],"of":[44,84,107,127],"lossless":[45],"compression":[46,82,125,128],"for":[47],"downstream":[48],"applications.":[49],"To":[50],"address":[51],"problems,":[53],"we":[54],"propose":[55],"a":[56,64],"data":[57,92],"structure":[58],"called":[59],"Cycle-Hash-Linkage":[60],"(CHL)":[61],"present":[63],"CPU":[65,145],"parallelism":[66],"optimization":[67,121],"algorithm":[68],"named":[69],"SR2C":[70,99,119,148],"(Structurally":[71],"Redundant":[72],"Short":[73],"Reads":[74],"Collapser)":[75],"based":[76],"on":[77,90],"CHL":[78],"improve":[80],"ratio":[83],"Experimental":[88],"results":[89],"actual":[91],"from":[93],"NCBI":[95],"database":[96],"demonstrate":[97],"that":[98],"achieves":[100,154],"an":[101],"average":[102,124],"residual":[103],"percentage":[105],"improvement":[106],"2.556%":[108],"compared":[109],"state-of-the-art":[112],"algorithm,":[116],"Minirmd.":[117],"Furthermore,":[118],"cascaded":[120],"improves":[122],"ratios":[126],"Pigz,":[130],"PBzip2,":[131],"XZ,":[132],"7Z":[134],"by":[135],"92.345%,":[136],"78.999%,":[137],"10.132%,":[138],"7.434%,":[140],"respectively.":[141],"By":[142],"leveraging":[143],"multi-core":[144],"parallel":[146],"computation,":[147],"effectively":[149],"reduces":[150],"time":[151],"consumption,":[152],"which":[153],"2-5X":[155],"recovers":[158],"acceleration.The":[159],"same":[160],"name":[161],"Linux":[162],"toolkit":[163],"is":[164],"freely":[165],"available":[166],"at":[167],"https://github.com/fahaihi/SR2C.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}