{"id":"https://openalex.org/W3200546258","doi":"https://doi.org/10.1093/bioinformatics/btab655","title":"CIndex: compressed indexes for fast retrieval of FASTQ files","display_name":"CIndex: compressed indexes for fast retrieval of FASTQ files","publication_year":2021,"publication_date":"2021-09-10","ids":{"openalex":"https://openalex.org/W3200546258","doi":"https://doi.org/10.1093/bioinformatics/btab655","mag":"3200546258","pmid":"https://pubmed.ncbi.nlm.nih.gov/34524416"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab655","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab655","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"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/A5072102175","display_name":"Hongwei Huo","orcid":"https://orcid.org/0000-0002-5436-1851"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongwei Huo","raw_affiliation_strings":["Department of Computer Science, Xidian University , Xi\u2019an 710071, China"],"raw_orcid":"https://orcid.org/0000-0002-5436-1851","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xidian University , Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355025","display_name":"Pengfei Liu","orcid":"https://orcid.org/0009-0008-6932-7091"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Liu","raw_affiliation_strings":["Department of Computer Science, Xidian University , Xi\u2019an 710071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xidian University , Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369511","display_name":"Chenhui Wang","orcid":"https://orcid.org/0009-0000-0799-7606"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhui Wang","raw_affiliation_strings":["Department of Computer Science, Xidian University , Xi\u2019an 710071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xidian University , Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061448582","display_name":"Hongbo Jiang","orcid":"https://orcid.org/0000-0001-7372-2539"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Jiang","raw_affiliation_strings":["Department of Computer Science, Xidian University , Xi\u2019an 710071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xidian University , Xi\u2019an 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003340402","display_name":"Jeffrey Scott Vitter","orcid":"https://orcid.org/0000-0001-7970-6118"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey Scott Vitter","raw_affiliation_strings":["Department of Computer Science, Tulane University , New Orleans, LA 70118, USA"],"raw_orcid":"https://orcid.org/0000-0001-7970-6118","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tulane University , New Orleans, LA 70118, USA","institution_ids":["https://openalex.org/I114832834"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003340402","https://openalex.org/A5072102175"],"corresponding_institution_ids":["https://openalex.org/I114832834","https://openalex.org/I149594827"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":null,"fwci":0.1402,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60129935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"38","issue":"2","first_page":"335","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.802299976348877,"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":0.802299976348877,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.053300000727176666,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.04100000113248825,"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":0.8837952613830566},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7405672073364258},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6438875198364258},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6133989095687866},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5934901237487793},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4677294194698334},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.43561264872550964},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.41499239206314087},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12536612153053284},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.12214770913124084},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09148171544075012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837952613830566},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7405672073364258},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6438875198364258},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6133989095687866},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5934901237487793},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4677294194698334},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.43561264872550964},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.41499239206314087},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12536612153053284},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.12214770913124084},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09148171544075012}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab655","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab655","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34524416","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34524416","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1054641142","display_name":"\u5927\u89c4\u6a21\u5e8f\u5217\u6570\u636e\u96c6\u7684\u538b\u7f29\u7d22\u5f15\u4e0e\u641c\u7d22\u7b97\u6cd5\u7814\u7a76","funder_award_id":"61373044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W127947978","https://openalex.org/W1969046465","https://openalex.org/W2026723094","https://openalex.org/W2051511420","https://openalex.org/W2057223122","https://openalex.org/W2103441770","https://openalex.org/W2108234281","https://openalex.org/W2109153336","https://openalex.org/W2110553099","https://openalex.org/W2114792961","https://openalex.org/W2117608012","https://openalex.org/W2124985265","https://openalex.org/W2125557405","https://openalex.org/W2128777897","https://openalex.org/W2129713651","https://openalex.org/W2131106408","https://openalex.org/W2138196010","https://openalex.org/W2147492358","https://openalex.org/W2158874082","https://openalex.org/W2159647614","https://openalex.org/W2170727800","https://openalex.org/W2170899819","https://openalex.org/W2569137190","https://openalex.org/W2811012751","https://openalex.org/W2899544675","https://openalex.org/W2900102030","https://openalex.org/W2905575949","https://openalex.org/W2950662571","https://openalex.org/W2951155949","https://openalex.org/W2991364609","https://openalex.org/W3001034374","https://openalex.org/W3031766209","https://openalex.org/W3200390843","https://openalex.org/W6801716448"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2393932274","https://openalex.org/W841163430"],"abstract_inverted_index":{"MOTIVATION:":[0],"Ultrahigh-throughput":[1],"next-generation":[2],"sequencing":[3,104],"instruments":[4,105],"continue":[5],"to":[6,44,82,175],"generate":[7],"vast":[8],"amounts":[9],"of":[10,29,135,160],"genomic":[11,31],"data.":[12],"These":[13],"data":[14,32,75,204],"are":[15,25,205],"generally":[16],"stored":[17],"in":[18,146,168,189],"FASTQ":[19,48,57,93,147],"format.":[20],"Two":[21],"important":[22],"simultaneous":[23],"goals":[24],"space-efficient":[26],"compressed":[27,42,54,92],"storage":[28],"the":[30,63,67,91],"and":[33,46,66,77,80,87,119,131,140,156],"fast":[34,88],"query":[35],"performance.":[36],"Toward":[37],"that":[38,107,169,184],"end,":[39],"we":[40],"introduce":[41],"indexing":[43],"store":[45],"retrieve":[47],"files.":[49,94],"RESULTS:":[50],"We":[51],"propose":[52],"a":[53,133,158,178],"index":[55,110],"for":[56],"files":[58],"called":[59],"CIndex.":[60],"CIndex":[61,163],"uses":[62,126,151],"Burrows-Wheeler":[64],"transform":[65],"wavelet":[68],"tree,":[69],"combined":[70],"with":[71],"hybrid":[72],"encoding,":[73],"succinct":[74],"structures":[76],"tables":[78],"REF":[79],"R\u03b3,":[81],"achieve":[83],"minimal":[84],"space":[85,130,155],"usage":[86],"retrieval":[89],"on":[90,122,198],"Experiments":[95],"conducted":[96],"over":[97],"real":[98],"publicly":[99],"available":[100,197,206],"datasets":[101],"from":[102],"various":[103],"demonstrate":[106],"our":[108,124,149],"proposed":[109],"substantially":[111],"outperforms":[112],"existing":[113],"state-of-the-art":[114],"solutions.":[115],"For":[116,143],"count,":[117],"locate":[118],"extract":[120],"queries":[121],"reads,":[123],"method":[125,150],"2.7-41.66%":[127],"points":[128,153],"less":[129,154],"provides":[132,157],"speedup":[134,159],"70-167.16":[136],"times,":[137],"1.44-35.57":[138],"times":[139],"1.3-55.4":[141],"times.":[142,162],"extracting":[144],"records":[145],"files,":[148],"2.86-14.88%":[152],"3.13-20.1":[161],"has":[164],"an":[165],"additional":[166],"advantage":[167],"it":[170,185],"can":[171],"be":[172],"readily":[173],"adapted":[174],"work":[176],"as":[177],"general-purpose":[179],"text":[180],"index;":[181],"experiments":[182],"show":[183],"performs":[186],"very":[187],"well":[188],"practice.":[190],"AVAILABILITY":[191],"AND":[192],"IMPLEMENTATION:":[193],"The":[194],"software":[195],"is":[196],"Github:":[199],"https://github.com/Hongweihuo-Lab/CIndex.":[200],"SUPPLEMENTARY":[201],"INFORMATION:":[202],"Supplementary":[203],"at":[207],"Bioinformatics":[208],"online.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
