{"id":"https://openalex.org/W4286209704","doi":"https://doi.org/10.1186/s12859-022-04833-5","title":"Locality-sensitive hashing enables efficient and scalable signal classification in high-throughput mass spectrometry raw data","display_name":"Locality-sensitive hashing enables efficient and scalable signal classification in high-throughput mass spectrometry raw data","publication_year":2022,"publication_date":"2022-07-20","ids":{"openalex":"https://openalex.org/W4286209704","doi":"https://doi.org/10.1186/s12859-022-04833-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/35858828"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04833-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04833-5","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/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04833-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041768359","display_name":"Konstantin Bob","orcid":"https://orcid.org/0000-0002-1929-9829"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Konstantin Bob","raw_affiliation_strings":["Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076431604","display_name":"David Teschner","orcid":"https://orcid.org/0000-0002-1755-5382"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Teschner","raw_affiliation_strings":["Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056265832","display_name":"Thomas Kemmer","orcid":"https://orcid.org/0000-0003-1180-746X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Kemmer","raw_affiliation_strings":["Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063042434","display_name":"David G\u00f3mez-Zepeda","orcid":"https://orcid.org/0000-0002-9467-1213"},"institutions":[{"id":"https://openalex.org/I4210113347","display_name":"Helmholtz Institute Mainz","ror":"https://ror.org/024thra40","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I169556180","https://openalex.org/I4210113347"]},{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Gomez-Zepeda","raw_affiliation_strings":["Immunoproteomics Unit, Helmholtz-Institute for Translational Oncology (HI-TRON) Mainz, Mainz, Germany","Institute for Immunology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Immunoproteomics Unit, Helmholtz-Institute for Translational Oncology (HI-TRON) Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I4210113347"]},{"raw_affiliation_string":"Institute for Immunology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055066185","display_name":"Stefan Tenzer","orcid":"https://orcid.org/0000-0003-3034-0017"},"institutions":[{"id":"https://openalex.org/I4210113347","display_name":"Helmholtz Institute Mainz","ror":"https://ror.org/024thra40","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I169556180","https://openalex.org/I4210113347"]},{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Tenzer","raw_affiliation_strings":["Immunoproteomics Unit, Helmholtz-Institute for Translational Oncology (HI-TRON) Mainz, Mainz, Germany","Institute for Immunology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Immunoproteomics Unit, Helmholtz-Institute for Translational Oncology (HI-TRON) Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I4210113347"]},{"raw_affiliation_string":"Institute for Immunology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015934308","display_name":"Andreas Hildebrandt","orcid":"https://orcid.org/0000-0003-2180-6516"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andreas Hildebrandt","raw_affiliation_strings":["Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015934308"],"corresponding_institution_ids":["https://openalex.org/I197323543"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072,"provenance":"doaj"},"apc_paid":{"value":1825,"currency":"EUR","value_usd":1968,"provenance":"openapc"},"fwci":0.154,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.399053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":60,"max":70},"biblio":{"volume":"23","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9989,"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":0.9989,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.998,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9943,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5445999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330495},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6660644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5970748},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5445999},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.4983375},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.49513307},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.481811},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3744721},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26030922},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.24646497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19492081},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.17399198},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04833-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04833-5","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/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/7fbe9bcd7cb8405d93beb2c2c61ca1d5","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":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9301846","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35858828","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04833-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04833-5","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/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft","award_id":"329350978"},{"funder":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung","award_id":"031L0217B"},{"funder":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung","award_id":"031L0217A"}],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W111509594","https://openalex.org/W1579534339","https://openalex.org/W1977290961","https://openalex.org/W2006869437","https://openalex.org/W2010399703","https://openalex.org/W2012833704","https://openalex.org/W2015732856","https://openalex.org/W2023096047","https://openalex.org/W2037199116","https://openalex.org/W2056666869","https://openalex.org/W2066138347","https://openalex.org/W2080752012","https://openalex.org/W2086502504","https://openalex.org/W2094889803","https://openalex.org/W2121418514","https://openalex.org/W2130729839","https://openalex.org/W2147717514","https://openalex.org/W2154802890","https://openalex.org/W2220258027","https://openalex.org/W2308569764","https://openalex.org/W2465480251","https://openalex.org/W2469486851","https://openalex.org/W2745994342","https://openalex.org/W2901011101","https://openalex.org/W2952261448","https://openalex.org/W2952907530","https://openalex.org/W2959428074","https://openalex.org/W2990072002","https://openalex.org/W3010753112","https://openalex.org/W3025057718","https://openalex.org/W3033804171","https://openalex.org/W3093062675","https://openalex.org/W3136321589"],"related_works":["https://openalex.org/W3108918257","https://openalex.org/W3016124764","https://openalex.org/W2750730210","https://openalex.org/W2236974868","https://openalex.org/W2144265691","https://openalex.org/W2116854923","https://openalex.org/W2033383639","https://openalex.org/W2000601968","https://openalex.org/W1661087619","https://openalex.org/W1542224353"],"abstract_inverted_index":{"Mass":[0],"spectrometry":[1,17,63,99,166],"is":[2,89,111,157,179],"an":[3,127],"important":[4],"experimental":[5],"technique":[6],"in":[7,97,164],"the":[8,54,66,83],"field":[9],"of":[10,14,22,34,41,49,61,107],"proteomics.":[11],"However,":[12],"analysis":[13],"certain":[15],"mass":[16,62,98,165],"data":[18,37,64,101,134,169,178],"faces":[19],"a":[20,27,31,122,158],"combination":[21],"two":[23],"challenges:":[24],"first,":[25],"even":[26],"single":[28,45],"experiment":[29],"produces":[30],"large":[32],"amount":[33,60],"multi-dimensional":[35],"raw":[36,100,167],"and,":[38],"second,":[39],"signals":[40,84],"interest":[42],"are":[43,172],"not":[44],"peaks":[46,50],"but":[47],"patterns":[48],"that":[51,91],"span":[52],"along":[53],"different":[55],"dimensions.":[56],"The":[57],"rapidly":[58],"growing":[59],"increases":[65],"demand":[67],"for":[68,74,161],"scalable":[69],"solutions.":[70],"Furthermore,":[71],"existing":[72],"approaches":[73],"signal":[75,95,162],"detection":[76],"usually":[77],"rely":[78],"on":[79],"strong":[80],"assumptions":[81],"concerning":[82],"properties.In":[85],"this":[86],"study,":[87],"it":[88,110],"shown":[90],"locality-sensitive":[92],"hashing":[93,156],"enables":[94],"classification":[96,163],"at":[102,174,181],"scale.":[103],"Through":[104],"appropriate":[105],"choice":[106],"algorithm":[108],"parameters":[109],"possible":[112],"to":[113,126,148],"balance":[114],"false-positive":[115],"and":[116,151,170],"false-negative":[117],"rates.":[118],"On":[119],"synthetic":[120],"data,":[121],"superior":[123],"performance":[124],"compared":[125],"intensity":[128],"thresholding":[129],"approach":[130,160],"was":[131],"achieved.":[132],"Real":[133],"could":[135],"be":[136],"strongly":[137],"reduced":[138],"without":[139],"losing":[140],"relevant":[141],"information.":[142],"Our":[143],"implementation":[144],"scaled":[145],"out":[146],"up":[147],"32":[149],"threads":[150],"supports":[152],"acceleration":[153],"by":[154],"GPUs.Locality-sensitive":[155],"desirable":[159],"data.Generated":[168],"code":[171],"available":[173,180],"https://github.com/hildebrandtlab/mzBucket":[175],".":[176,183],"Raw":[177],"https://zenodo.org/record/5036526":[182]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4286209704","counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-01-09T14:20:25.176339","created_date":"2022-07-21"}