{"id":"https://openalex.org/W2905575949","doi":"https://doi.org/10.1093/bioinformatics/bty1015","title":"SPRING: a next-generation compressor for FASTQ data","display_name":"SPRING: a next-generation compressor for FASTQ data","publication_year":2018,"publication_date":"2018-12-06","ids":{"openalex":"https://openalex.org/W2905575949","doi":"https://doi.org/10.1093/bioinformatics/bty1015","mag":"2905575949","pmid":"https://pubmed.ncbi.nlm.nih.gov/30535063"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty1015","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty1015","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":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6662292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086012490","display_name":"Shubham Chandak","orcid":"https://orcid.org/0000-0002-1130-9762"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shubham Chandak","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1130-9762","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045177980","display_name":"Kedar Tatwawadi","orcid":"https://orcid.org/0000-0003-3677-4174"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kedar Tatwawadi","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045294377","display_name":"Idoia Ochoa","orcid":"https://orcid.org/0000-0003-1864-7868"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Idoia Ochoa","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044149683","display_name":"Mikel Hern\u00e1ez","orcid":"https://orcid.org/0000-0003-0443-2305"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mikel Hernaez","raw_affiliation_strings":["Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-0443-2305","affiliations":[{"raw_affiliation_string":"Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043344688","display_name":"Tsachy Weissman","orcid":"https://orcid.org/0009-0008-1099-691X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsachy Weissman","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044149683","https://openalex.org/A5086012490"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I97018004"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":6.4592,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.97182328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"35","issue":"15","first_page":"2674","last_page":"2676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8141999840736389,"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":0.8141999840736389,"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":0.1216999962925911,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.009999999776482582,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.832419753074646},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.7965043783187866},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6084150075912476},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5266121625900269},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5196479558944702},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5037862658500671},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4921847879886627},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.468948096036911},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.44054800271987915},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2878776788711548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19519734382629395},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08742532134056091},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08141627907752991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832419753074646},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.7965043783187866},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6084150075912476},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5266121625900269},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5196479558944702},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5037862658500671},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4921847879886627},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.468948096036911},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.44054800271987915},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2878776788711548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19519734382629395},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08742532134056091},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08141627907752991},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bty1015","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty1015","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:30535063","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30535063","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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:6662292","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6662292","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:6662292","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6662292","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1040472009","display_name":null,"funder_award_id":"2018-182798","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4131991648","display_name":null,"funder_award_id":"U01 CA198943","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G8243774520","display_name":null,"funder_award_id":"2018-182799","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8766125661","display_name":"Genomic Compression: From Information Theory to Parallel Algorithms","funder_award_id":"5u01ca198943-03","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306192","display_name":"Silicon Valley Community Foundation","ror":"https://ror.org/001ader08"},{"id":"https://openalex.org/F4320312516","display_name":"Sunnybrook Research Institute","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2092880969","https://openalex.org/W2111044311","https://openalex.org/W2114792961","https://openalex.org/W2125557405","https://openalex.org/W2296597603","https://openalex.org/W2538355508","https://openalex.org/W2764165465","https://openalex.org/W2892853757","https://openalex.org/W2951070849","https://openalex.org/W6697520301"],"related_works":["https://openalex.org/W2385628723","https://openalex.org/W2547124190","https://openalex.org/W3180760233","https://openalex.org/W1970394887","https://openalex.org/W3035703949","https://openalex.org/W4247601675","https://openalex.org/W755971114","https://openalex.org/W2118338613","https://openalex.org/W1982468865","https://openalex.org/W4210455546"],"abstract_inverted_index":{"MOTIVATION:":[0],"High-Throughput":[1],"Sequencing":[2],"technologies":[3],"produce":[4],"huge":[5],"amounts":[6],"of":[7,12,23,40,50,57,62,103,115,138],"data":[8,182],"in":[9,28,60],"the":[10,24,41],"form":[11],"short":[13],"genomic":[14],"reads,":[15,74],"associated":[16],"quality":[17,116],"values":[18],"and":[19,82,106,121],"read":[20,119],"identifiers.":[21],"Because":[22],"significant":[25],"structure":[26],"present":[27],"these":[29],"FASTQ":[30,54,96,143,159],"datasets,":[31,79],"general-purpose":[32],"compressors":[33],"are":[34,183],"unable":[35],"to":[36,76,148],"completely":[37],"exploit":[38],"much":[39],"inherent":[42],"redundancy.":[43],"Although":[44],"there":[45],"has":[46],"been":[47],"a":[48,92,100],"lot":[49],"work":[51],"on":[52],"designing":[53],"compressors,":[55],"most":[56],"them":[58],"lack":[59],"support":[61,70],"one":[63],"or":[64],"more":[65],"crucial":[66],"properties,":[67],"such":[68],"as":[69],"for":[71,95,132],"variable":[72],"length":[73],"scalability":[75],"high":[77],"coverage":[78],"pairing-preserving":[80,111],"compression":[81,104,114,120,128],"lossless":[83,109],"compression.":[84],"RESULTS:":[85],"In":[86],"this":[87,163],"work,":[88],"we":[89],"propose":[90],"SPRING,":[91],"reference-free":[93],"compressor":[94],"files.":[97],"SPRING":[98,124,134,161,173],"supports":[99],"wide":[101],"variety":[102],"modes":[105],"features,":[107],"including":[108],"compression,":[110,112],"lossy":[113],"values,":[117],"long":[118],"random":[122],"access.":[123],"achieves":[125,162],"substantially":[126],"better":[127],"than":[129,150,156],"existing":[130],"tools,":[131],"example,":[133],"compresses":[135],"195":[136],"GB":[137],"25\u00d7":[139],"whole":[140],"genome":[141],"human":[142],"from":[144,177],"Illumina's":[145],"NovaSeq":[146],"sequencer":[147],"less":[149],"7":[151],"GB,":[152],"around":[153],"1.6\u00d7":[154],"smaller":[155],"previous":[157],"state-of-the-art":[158],"compressors.":[160],"improvement":[164],"while":[165],"using":[166],"comparable":[167],"computational":[168],"resources.":[169],"AVAILABILITY":[170],"AND":[171],"IMPLEMENTATION:":[172],"can":[174],"be":[175],"downloaded":[176],"https://github.com/shubhamchandak94/SPRING.":[178],"SUPPLEMENTARY":[179],"INFORMATION:":[180],"Supplementary":[181],"available":[184],"at":[185],"Bioinformatics":[186],"online.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
