{"id":"https://openalex.org/W7225200310","doi":"https://doi.org/10.64898/2026.10.27.762387","title":"Improving real-time search through deep learning-enhanced fragment ion indexing","display_name":"Improving real-time search through deep learning-enhanced fragment ion indexing","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225200310","doi":"https://doi.org/10.64898/2026.10.27.762387"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.27.762387","doi":"https://doi.org/10.64898/2026.10.27.762387","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762387","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.27.762387.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.27.762387.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011565192","display_name":"Jimmy K. Eng","orcid":"https://orcid.org/0000-0001-6352-6737","observed_orcids":["https://orcid.org/0000-0001-6352-6737"]},"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":true,"raw_author_name":"Jimmy Eng","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0001-6352-6737","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018903678","display_name":"Michael R. Hoopmann","orcid":"https://orcid.org/0000-0001-7029-7792","observed_orcids":["https://orcid.org/0000-0001-7029-7792"]},"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":"Michael Hoopmann","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0001-7029-7792","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065677258","display_name":"Devin K. Schweppe","orcid":"https://orcid.org/0000-0002-3241-6276","observed_orcids":["https://orcid.org/0000-0002-3241-6276"]},"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":"Devin K. Schweppe","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0002-3241-6276","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043959168","display_name":"Michael J. MacCoss","orcid":"https://orcid.org/0000-0003-1853-0256","observed_orcids":["https://orcid.org/0000-0003-1853-0256"]},"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":"Michael J. MacCoss","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0003-1853-0256","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","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":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0001-7283-4715","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011332528","display_name":"Bo Wen","orcid":"https://orcid.org/0000-0003-2261-3150","observed_orcids":["https://orcid.org/0000-0003-2261-3150"]},"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":"Bo Wen","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0003-2261-3150","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011565192"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9735999703407288,"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":0.9735999703407288,"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":0.017899999395012856,"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":0.0005000000237487257,"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/carafe","display_name":"carafe","score":0.9660000205039978},{"id":"https://openalex.org/keywords/peptide-spectrum-matches","display_name":"peptide-spectrum matches","score":0.6970000267028809},{"id":"https://openalex.org/keywords/memory-reduction","display_name":"memory reduction","score":0.6019999980926514},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.4950000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358999848365784},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.707099974155426},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.6909000277519226},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.4677000045776367},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.4544000029563904},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C94081185","wikidata":"https://www.wikidata.org/wiki/Q3559","display_name":"Comet","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C204259536","wikidata":"https://www.wikidata.org/wiki/Q787903","display_name":"Linear search","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C21782646","wikidata":"https://www.wikidata.org/wiki/Q841666","display_name":"Search cost","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C121610932","wikidata":"https://www.wikidata.org/wiki/Q243754","display_name":"Binary search algorithm","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.27.762387","doi":"https://doi.org/10.64898/2026.10.27.762387","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762387","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.27.762387.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.27.762387","doi":"https://doi.org/10.64898/2026.10.27.762387","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762387","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/03/2026.10.27.762387.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306159","display_name":"W. M. Keck Foundation","ror":"https://ror.org/000dswa46"},{"id":"https://openalex.org/F4320306854","display_name":"Washington Research Foundation","ror":"https://ror.org/00hasdx88"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"},{"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"},{"id":"https://openalex.org/F4562087700","display_name":"National Science Foundation Graduate Research Fellowship Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225200310.pdf","grobid_xml":"https://content.openalex.org/works/W7225200310.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4404458588","https://openalex.org/W7222963189"],"related_works":["https://openalex.org/W3004571255","https://openalex.org/W4411370226","https://openalex.org/W7167266296","https://openalex.org/W7222963189","https://openalex.org/W2911264380","https://openalex.org/W4401919263","https://openalex.org/W2031764625","https://openalex.org/W4380146585","https://openalex.org/W7164209008","https://openalex.org/W4315702991"],"abstract_inverted_index":{"The":[0,198],"fragment":[1,86,97,142],"ion":[2,87,98,143],"indexed":[3],"database":[4,13,75,189],"searching":[5],"approach":[6,124],"enables":[7],"highly":[8],"efficient":[9],"tandem":[10],"mass":[11],"spectrometry":[12],"searches,":[14],"including":[15],"real-time":[16],"search":[17,76,127,149,196],"workflows.":[18],"However,":[19],"the":[20,31,40,44,47,50,55,73,109,139,187],"index":[21,131,144],"can":[22,60],"require":[23],"tens":[24],"of":[25,27,46,57,141,165,186],"gigabytes":[26],"memory,":[28],"often":[29],"exceeding":[30],"free":[32],"memory":[33,150],"available":[34],"on":[35,90,125],"instrument":[36],"acquisition":[37],"computers":[38],"running":[39],"search.":[41],"This":[42],"restricts":[43],"size":[45],"searchable":[48],"database,":[49],"variable":[51],"modification":[52,191],"space,":[53],"and":[54,160,171,190],"number":[56,140,164],"searches":[58,153,159,185],"that":[59,84,100,113,135],"run":[61],"concurrently.":[62],"To":[63],"address":[64],"this":[65,123],"problem,":[66],"we":[67],"developed":[68],"an":[69,205],"index-pruning":[70],"pipeline":[71],"within":[72],"Comet":[74],"tool":[77,83],"using":[78],"Carafe,":[79],"a":[80,162],"deep":[81],"learning":[82],"predicts":[85],"intensities":[88],"based":[89],"peptide":[91],"sequences.":[92],"In":[93],"our":[94],"approach,":[95],"only":[96],"positions":[99],"are":[101,106,114,174],"predicted":[102],"to":[103,116,118,133],"be":[104],"observable":[105],"written":[107],"in":[108,129],"index,":[110],"eliminating":[111],"entries":[112,145],"unlikely":[115],"contribute":[117],"spectrum":[119],"detection.":[120],"We":[121],"evaluated":[122],"two":[126],"spaces":[128],"three":[130],"configurations":[132],"demonstrate":[134],"masking":[136,172],"significantly":[137],"reduced":[138],"and,":[146],"consequently,":[147],"peak":[148],"use.":[151],"Masked":[152],"were":[154],"also":[155],"faster":[156],"than":[157],"unmasked":[158],"identified":[161],"comparable":[163],"peptide-spectrum":[166],"matches.":[167],"Because":[168],"all":[169],"prediction":[170],"steps":[173],"performed":[175],"before":[176],"searching,":[177],"their":[178],"cost":[179],"is":[180,201],"amortized":[181],"across":[182],"repeated,":[183],"future":[184],"same":[188],"configuration,":[192],"introducing":[193],"no":[194],"per-spectrum":[195],"overhead.":[197],"complete":[199],"implementation":[200],"open":[202],"source":[203],"with":[204],"Apache":[206],"license.":[207]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}