{"id":"https://openalex.org/W2956005825","doi":"https://doi.org/10.1186/s12859-019-2962-7","title":"MassComp, a lossless compressor for mass spectrometry data","display_name":"MassComp, a lossless compressor for mass spectrometry data","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2956005825","doi":"https://doi.org/10.1186/s12859-019-2962-7","mag":"2956005825","pmid":"https://pubmed.ncbi.nlm.nih.gov/31262247"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-2962-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2962-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2962-7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2962-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041679814","display_name":"Ruochen Yang","orcid":"https://orcid.org/0000-0002-5468-9638"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruochen Yang","raw_affiliation_strings":["Electrical Engineering Department, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329945","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-4151-4820"},"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":"Xi Chen","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","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":true,"raw_author_name":"Idoia Ochoa","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USA. idoia@illinois.edu","Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-1864-7868","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USA. idoia@illinois.edu","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045294377"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.5278,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.56498562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"1","first_page":"368","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.435699999332428,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.435699999332428,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.16050000488758087,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.05950000137090683,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"Mass spectrometry","score":0.609583854675293},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.6012071967124939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47250688076019287},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.38792288303375244},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.29882538318634033},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.2536205053329468},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18471765518188477},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.17520570755004883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13030117750167847}],"concepts":[{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.609583854675293},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6012071967124939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47250688076019287},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.38792288303375244},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.29882538318634033},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.2536205053329468},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18471765518188477},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.17520570755004883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13030117750167847}],"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":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","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":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-019-2962-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2962-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2962-7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31262247","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31262247","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:17af671192ec4bb9a495398b067ed60b","is_oa":true,"landing_page_url":"https://doaj.org/article/17af671192ec4bb9a495398b067ed60b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 20, Iss 1, Pp 1-10 (2019)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5587999","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6604446","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-019-2962-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2962-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-019-2962-7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4301363290","display_name":null,"funder_award_id":"2018-182799","funder_id":"https://openalex.org/F4320315474","funder_display_name":"Chan Zuckerberg Initiative"}],"funders":[{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2956005825.pdf","grobid_xml":"https://content.openalex.org/works/W2956005825.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1542926802","https://openalex.org/W1971606140","https://openalex.org/W1971983473","https://openalex.org/W2023096047","https://openalex.org/W2031095666","https://openalex.org/W2035542044","https://openalex.org/W2046872827","https://openalex.org/W2057761395","https://openalex.org/W2089872141","https://openalex.org/W2108234281","https://openalex.org/W2110455446","https://openalex.org/W2118526609","https://openalex.org/W2125557405","https://openalex.org/W2129768577","https://openalex.org/W2146103026","https://openalex.org/W2147010729","https://openalex.org/W2161811833","https://openalex.org/W2167089719","https://openalex.org/W2167418292","https://openalex.org/W2170255714","https://openalex.org/W2296597603","https://openalex.org/W2528841444","https://openalex.org/W2538355508","https://openalex.org/W2951070849"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3106969033","https://openalex.org/W2186939576","https://openalex.org/W2357988910","https://openalex.org/W2948148442","https://openalex.org/W2377158164","https://openalex.org/W2187600494","https://openalex.org/W2114030128"],"abstract_inverted_index":{"BACKGROUND:":[0],"Mass":[1],"Spectrometry":[2],"(MS)":[3],"is":[4,65,175,216],"a":[5,22,56,82,113,170],"widely":[6],"used":[7],"technique":[8],"in":[9,16,32,177],"biology":[10],"research,":[11],"and":[12,18,74,106,123,145,179,202,232,236],"has":[13,29],"become":[14],"key":[15],"proteomics":[17],"metabolomics":[19],"analyses.":[20],"As":[21],"result,":[23],"the":[24,37,70,87,96,117,120,141,151,163,197,204,220,229,234],"amount":[25],"of":[26,45,62,72,95,119,134,146,189,199,206,222,238],"MS":[27,38,97,104,200,213],"data":[28,50,64,105],"significantly":[30,195],"increased":[31],"recent":[33],"years.":[34],"For":[35],"example,":[36],"repository":[39],"MassIVE":[40,164],"contains":[41],"more":[42,135],"than":[43,136],"123TB":[44],"data.":[46,98,214,240],"Somehow":[47],"surprisingly,":[48],"these":[49,63],"are":[51],"stored":[52],"uncompressed,":[53],"hence":[54],"incurring":[55],"significant":[57],"storage":[58,73,230],"cost.":[59],"Efficient":[60],"representation":[61],"therefore":[66],"paramount":[67],"to":[68,125,130,140,150,194,212,219,227],"lessen":[69,228],"burden":[71,231],"facilitate":[75,233],"its":[76,192],"dissemination.":[77],"RESULTS:":[78],"We":[79,99],"present":[80],"MassComp,":[81],"lossless":[83],"compressor":[84,143,154],"optimized":[85],"for":[86,93],"numerical":[88,121,153],"(m/z)-intensity":[89],"pairs":[90],"that":[91,108],"account":[92],"most":[94],"tested":[100,157],"MassComp":[101,166,174,190,215],"on":[102,111,116,158,168],"several":[103],"show":[107],"it":[109],"delivers":[110],"average":[112,132,169],"46%":[114],"reduction":[115],"size":[118,172],"data,":[122,201],"up":[124],"89%.":[126],"These":[127],"results":[128],"correspond":[129],"an":[131,217],"improvement":[133],"27%":[137],"when":[138,148],"compared":[139,149],"general":[142],"gzip":[144],"40%":[147],"state-of-the-art":[152],"FPC.":[155],"When":[156],"entire":[159],"files":[160],"retrieved":[161],"from":[162],"repository,":[165],"achieves":[167],"59%":[171],"reduction.":[173],"written":[176],"C++":[178],"freely":[180],"available":[181],"at":[182],"https://github.com/iochoa/MassComp":[183],".":[184],"CONCLUSIONS:":[185],"The":[186],"compression":[187,209,224],"performance":[188],"demonstrates":[191],"potential":[193],"reduce":[196],"footprint":[198],"shows":[203],"benefits":[205],"designing":[207],"specialized":[208],"algorithms":[210,225],"tailored":[211],"addition":[218],"family":[221],"omics":[223,239],"designed":[226],"exchange":[235],"dissemination":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
