{"id":"https://openalex.org/W2970104449","doi":"https://doi.org/10.1021/acs.jproteome.9b00291","title":"Extremely Fast and Accurate Open Modification Spectral Library Searching of High-Resolution Mass Spectra Using Feature Hashing and Graphics Processing Units","display_name":"Extremely Fast and Accurate Open Modification Spectral Library Searching of High-Resolution Mass Spectra Using Feature Hashing and Graphics Processing Units","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2970104449","doi":"https://doi.org/10.1021/acs.jproteome.9b00291","mag":"2970104449","pmid":"https://pubmed.ncbi.nlm.nih.gov/31448616","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6886738"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jproteome.9b00291","doi":"https://doi.org/10.1021/acs.jproteome.9b00291","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jproteome.9b00291","pdf_url":null,"source":{"id":"https://openalex.org/S74367812","display_name":"Journal of Proteome Research","issn_l":"1535-3893","issn":["1535-3893","1535-3907"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-d","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Proteome Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2019/08/09/627497.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053271927","display_name":"Wout Bittremieux","orcid":"https://orcid.org/0000-0002-3105-1359","observed_orcids":["https://orcid.org/0000-0002-3105-1359"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210125409","display_name":"Biomedical Informatics Research Center Antwerp","ror":"https://ror.org/02y3cnq68","country_code":"BE","type":"facility","lineage":["https://openalex.org/I4210125409"]}],"countries":["BE","US"],"is_corresponding":true,"raw_author_name":"Wout Bittremieux","raw_affiliation_strings":["Biomedical Informatics Network Antwerpen (biomina), 2020 Antwerp, Belgium","Department of Genome Sciences, University of Washington, Seattle, Washington 98195, United States","Department of Mathematics and Computer Science, University of Antwerp, 2020 Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-3105-1359","affiliations":[{"raw_affiliation_string":"Biomedical Informatics Network Antwerpen (biomina), 2020 Antwerp, Belgium","institution_ids":["https://openalex.org/I4210125409"]},{"raw_affiliation_string":"Department of Genome Sciences, University of Washington, Seattle, Washington 98195, United States","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Antwerp, 2020 Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024445778","display_name":"Kris Laukens","orcid":"https://orcid.org/0000-0002-8217-2564","observed_orcids":["https://orcid.org/0000-0002-8217-2564"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210125409","display_name":"Biomedical Informatics Research Center Antwerp","ror":"https://ror.org/02y3cnq68","country_code":"BE","type":"facility","lineage":["https://openalex.org/I4210125409"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Laukens","raw_affiliation_strings":["Biomedical Informatics Network Antwerpen (biomina), 2020 Antwerp, Belgium","Department of Mathematics and Computer Science, University of Antwerp, 2020 Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Network Antwerpen (biomina), 2020 Antwerp, Belgium","institution_ids":["https://openalex.org/I4210125409"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Antwerp, 2020 Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057375933","display_name":"William Stafford Noble","orcid":"https://orcid.org/0000-0001-7283-4715","observed_orcids":["https://orcid.org/0000-0001-7283-4715"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Stafford Noble","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Washington, Seattle, Washington 98195, United States","Department of Genome Sciences, University of Washington, Seattle, Washington 98195, United States"],"raw_orcid":"https://orcid.org/0000-0001-7283-4715","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Washington, Seattle, Washington 98195, United States","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Department of Genome Sciences, University of Washington, Seattle, Washington 98195, United States","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053271927"],"corresponding_institution_ids":["https://openalex.org/I149213910","https://openalex.org/I201448701","https://openalex.org/I4210125409"],"apc_list":{"value":5000,"currency":"USD","value_usd":5000},"apc_paid":null,"fwci":2.1166,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.87407018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"18","issue":"10","first_page":"3792","last_page":"3799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9829000234603882,"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":0.9829000234603882,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.007699999958276749,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.000699999975040555,"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/spectral-library-search","display_name":"spectral library search","score":0.9330000281333923},{"id":"https://openalex.org/keywords/high-resolution-mass-spectrometry","display_name":"high-resolution mass spectrometry","score":0.8899999856948853},{"id":"https://openalex.org/keywords/feature-hashing","display_name":"feature hashing","score":0.8080000281333923},{"id":"https://openalex.org/keywords/graphics-processing-units","display_name":"graphics processing units","score":0.8330000042915344},{"id":"https://openalex.org/keywords/peptide-identification","display_name":"peptide identification","score":0.8460000157356262},{"id":"https://openalex.org/keywords/protein-modification","display_name":"protein modification","score":0.6729999780654907},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.4259999990463257},{"id":"https://openalex.org/keywords/human-proteome","display_name":"human proteome","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878527641296387},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5210580229759216},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4907478094100952},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4220942258834839},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4140239953994751},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4113544821739197},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4090557396411896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3776072561740875},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.36242979764938354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32414138317108154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.320790559053421},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.24898722767829895},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","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":"D019151","descriptor_name":"Peptide Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1021/acs.jproteome.9b00291","doi":"https://doi.org/10.1021/acs.jproteome.9b00291","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jproteome.9b00291","pdf_url":null,"source":{"id":"https://openalex.org/S74367812","display_name":"Journal of Proteome Research","issn_l":"1535-3893","issn":["1535-3893","1535-3907"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-d","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Proteome Research","raw_type":"journal-article"},{"id":"doi:10.1101/627497","doi":"https://doi.org/10.1101/627497","is_oa":true,"landing_page_url":"https://doi.org/10.1101/627497","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/08/09/627497.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:31448616","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31448616","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,"listed_in":[],"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":"Journal of proteome research","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6886738","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6886738","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,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"J Proteome Res","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1101/627497","doi":"https://doi.org/10.1101/627497","is_oa":true,"landing_page_url":"https://doi.org/10.1101/627497","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/08/09/627497.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8291614145","display_name":"Optimization and joint modeling for peptide detection by tandem mass spectrometry","funder_award_id":"R01GM121818","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306621","display_name":"Belgian American Educational Foundation","ror":"https://ror.org/014rsed66"},{"id":"https://openalex.org/F4320319128","display_name":"Vlaams Supercomputer Centrum","ror":"https://ror.org/05sqppn31"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970104449.pdf","grobid_xml":"https://content.openalex.org/works/W2970104449.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1566086199","https://openalex.org/W1672197616","https://openalex.org/W1968044788","https://openalex.org/W1979231364","https://openalex.org/W1995268935","https://openalex.org/W2013589890","https://openalex.org/W2021613526","https://openalex.org/W2056499061","https://openalex.org/W2059651000","https://openalex.org/W2070996757","https://openalex.org/W2073637473","https://openalex.org/W2080258378","https://openalex.org/W2081465448","https://openalex.org/W2085467029","https://openalex.org/W2104266030","https://openalex.org/W2109204063","https://openalex.org/W2131846894","https://openalex.org/W2135581618","https://openalex.org/W2146292423","https://openalex.org/W2245493112","https://openalex.org/W2289616942","https://openalex.org/W2398637015","https://openalex.org/W2537132940","https://openalex.org/W2593864460","https://openalex.org/W2607310450","https://openalex.org/W2728534204","https://openalex.org/W2749103096","https://openalex.org/W2757662681","https://openalex.org/W2786505886","https://openalex.org/W2789457189","https://openalex.org/W2804552715","https://openalex.org/W2894727674","https://openalex.org/W2904845587","https://openalex.org/W2930099314","https://openalex.org/W2949278902","https://openalex.org/W2962766560","https://openalex.org/W2993327327","https://openalex.org/W6601052344"],"related_works":["https://openalex.org/W6968879003","https://openalex.org/W2949278902","https://openalex.org/W7126272003","https://openalex.org/W3211268010","https://openalex.org/W4382198841","https://openalex.org/W6949952587","https://openalex.org/W4317750000","https://openalex.org/W2728534204","https://openalex.org/W7213890065","https://openalex.org/W4291335647"],"abstract_inverted_index":{"Open":[0],"modification":[1,40,200],"searching":[2],"(OMS)":[3],"is":[4,57,167,224,231],"a":[5,21,71,104,139,189,194,214],"powerful":[6],"search":[7],"strategy":[8],"to":[9,27,31,67,97,113,115,143,147,169,183,192],"identify":[10],"peptides":[11],"with":[12,158],"any":[13],"type":[14],"of":[15,53,73,107,153,165,172,210,218],"modification.":[16],"OMS":[17,100],"works":[18],"by":[19,101],"using":[20,132],"very":[22],"wide":[23],"precursor":[24,48],"mass":[25,49],"window":[26],"allow":[28],"modified":[29],"spectra":[30,112,146],"match":[32],"against":[33,70],"their":[34],"unmodified":[35],"variants,":[36],"after":[37],"which":[38],"the":[39,46,58,80,108,151,162,198,204,219,235],"types":[41],"can":[42,128],"be":[43,68,129],"inferred":[44],"from":[45],"corresponding":[47],"differences.":[50],"A":[51],"disadvantage":[52],"this":[54,124],"strategy,":[55],"however,":[56],"large":[59,190,215],"computational":[60,205],"cost,":[61],"because":[62],"each":[63],"query":[64,118],"spectrum":[65],"has":[66],"compared":[69],"multitude":[72],"candidate":[74,125],"peptides.":[75],"We":[76,202],"have":[77],"previously":[78],"introduced":[79],"ANN-SoLo":[81,91,166,211,223],"tool":[82],"for":[83],"fast":[84],"and":[85,207,228],"accurate":[86],"open":[87,186],"spectral":[88],"library":[89,111],"searching.":[90],"uses":[92],"approximate":[93],"nearest":[94],"neighbor":[95],"indexing":[96],"speed":[98],"up":[99,168],"selecting":[102],"only":[103],"limited":[105],"number":[106],"most":[109],"relevant":[110],"compare":[114],"an":[116,170],"unknown":[117],"spectrum.":[119],"Here":[120],"we":[121,137],"demonstrate":[122,203],"how":[123],"selection":[126],"procedure":[127],"further":[130],"optimized":[131],"graphics":[133],"processing":[134],"units.":[135],"Additionally,":[136],"introduce":[138],"feature":[140],"hashing":[141],"scheme":[142],"convert":[144],"high-resolution":[145],"low-dimensional":[148],"vectors.":[149],"On":[150],"basis":[152],"these":[154],"algorithmic":[155],"advances,":[156],"along":[157],"low-level":[159],"code":[160],"optimizations,":[161],"new":[163],"version":[164],"order":[171],"magnitude":[173],"faster":[174],"than":[175],"its":[176],"initial":[177],"version.":[178],"This":[179],"makes":[180],"it":[181],"possible":[182],"efficiently":[184],"perform":[185],"searches":[187],"on":[188,213],"scale":[191],"gain":[193],"deeper":[195],"understanding":[196],"about":[197],"protein":[199],"landscape.":[201],"efficiency":[206],"identification":[208],"performance":[209],"based":[212],"data":[216],"set":[217],"draft":[220],"human":[221],"proteome.":[222],"implemented":[225],"in":[226],"Python":[227],"C++.":[229],"It":[230],"freely":[232],"available":[233],"under":[234],"Apache":[236],"2.0":[237],"license":[238],"at":[239],"https://github.com/bittremieux/ANN-SoLo":[240],".":[241]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2019-09-05T00:00:00"}