{"id":"https://openalex.org/W7204993907","doi":"https://doi.org/10.26434/chemrxiv.15008195/v1","title":"Reproducibility Limits of Public MS/MS Spectral Libraries: Irreproducibility, Outlier Spectra, and Indistinguishable Compounds Across One Million Reference Spectra","display_name":"Reproducibility Limits of Public MS/MS Spectral Libraries: Irreproducibility, Outlier Spectra, and Indistinguishable Compounds Across One Million Reference Spectra","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7204993907","doi":"https://doi.org/10.26434/chemrxiv.15008195/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008195/v1","doi":"https://doi.org/10.26434/chemrxiv.15008195/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008195/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008195/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008195/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100710024","display_name":"Yong\u2010Seok Kim","orcid":"https://orcid.org/0000-0001-7861-7375","observed_orcids":["https://orcid.org/0000-0001-7861-7375"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yongseok Kim","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0000-0001-7861-7375","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100710024"],"corresponding_institution_ids":[],"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.975600004196167,"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"}},"topics":[{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.975600004196167,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.01489999983459711,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.005100000184029341,"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/reproducibility","display_name":"reproducibility","score":0.7630000114440918},{"id":"https://openalex.org/keywords/spectral-similarity","display_name":"spectral similarity","score":0.6010000109672546},{"id":"https://openalex.org/keywords/compound-annotation","display_name":"compound annotation","score":0.5820000171661377},{"id":"https://openalex.org/keywords/untargeted-metabolomics","display_name":"untargeted metabolomics","score":0.9549999833106995},{"id":"https://openalex.org/keywords/sampling-depth","display_name":"sampling depth","score":0.6859999895095825},{"id":"https://openalex.org/keywords/gnps","display_name":"GNPS","score":0.609000027179718},{"id":"https://openalex.org/keywords/ms-dial","display_name":"MS-DIAL","score":0.871999979019165},{"id":"https://openalex.org/keywords/spectral-matching","display_name":"spectral matching","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6746000051498413},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4909000098705292},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4341000020503998},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42570000886917114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.37400001287460327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36890000104904175},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008195/v1","doi":"https://doi.org/10.26434/chemrxiv.15008195/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008195/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008195/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008195/v1","doi":"https://doi.org/10.26434/chemrxiv.15008195/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008195/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008195/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204993907.pdf","grobid_xml":"https://content.openalex.org/works/W7204993907.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W2059327215","https://openalex.org/W2070181523","https://openalex.org/W2084709148","https://openalex.org/W2100806274","https://openalex.org/W2114390083","https://openalex.org/W2132400619","https://openalex.org/W2165681080","https://openalex.org/W2311978772","https://openalex.org/W2536128108","https://openalex.org/W2810239295","https://openalex.org/W2901205421","https://openalex.org/W2995966112","https://openalex.org/W3016527036","https://openalex.org/W3034300141","https://openalex.org/W4213068307","https://openalex.org/W4309655157","https://openalex.org/W4310780836","https://openalex.org/W7154447424"],"related_works":["https://openalex.org/W7222465469","https://openalex.org/W7171815884","https://openalex.org/W3209276240","https://openalex.org/W6912333664","https://openalex.org/W7134274856","https://openalex.org/W2951677912","https://openalex.org/W7203672782","https://openalex.org/W6950387725","https://openalex.org/W6931727796","https://openalex.org/W4309655157"],"abstract_inverted_index":{"Compound":[0],"annotation":[1],"in":[2,153],"untargeted":[3],"metabolomics":[4],"relies":[5],"on":[6],"matching":[7,183],"an":[8,129,241],"experimental":[9],"MS/MS":[10],"spectrum":[11,29],"against":[12],"a":[13,32,79,95,147,233],"reference":[14],"library,":[15],"and":[16,54,63,67,200,220],"the":[17,26,83,177,196,214,226,238],"quality":[18,127],"of":[19,28,40,56,81,111,132,159,190,202],"such":[20],"libraries":[21],"is":[22,42,142,179],"routinely":[23],"summarized":[24],"by":[25,75,94,103,181],"proportion":[27],"pairs":[30],"exceeding":[31],"similarity":[33],"threshold.":[34],"We":[35,144,212],"show":[36],"that":[37,69,118,150],"this":[38,186],"class":[39],"metric":[41],"structurally":[43,171],"invalid.":[44],"Analyzing":[45],"1,022,449":[46],"spectra":[47,163,203],"covering":[48],"66,843":[49],"compounds":[50,160],"from":[51,88],"GNPS,":[52],"MS-DIAL,":[53],"MassBank":[55],"North":[57],"America,":[58],"we":[59],"compute":[60],"all":[61],"within-":[62],"between-compound":[64],"pairwise":[65],"similarities":[66],"demonstrate":[68],"proportion-based":[70],"consistency":[71],"estimates":[72],"are":[73],"confounded":[74],"sampling":[76],"depth":[77,122,141],"as":[78,205,232,240],"matter":[80],"construction:":[82],"apparent":[84,130],"high-consistency":[85],"rate":[86],"falls":[87],"91%":[89],"for":[90,100,175],"compound":[91,210],"groups":[92,101],"supported":[93,102],"single":[96],"comparison":[97,110],"to":[98],"5%":[99],"more":[104],"than":[105,126,231],"one":[106,133,170],"hundred.":[107],"Consequently,":[108],"any":[109],"libraries,":[112],"instrument":[113,134],"platforms,":[114],"or":[115],"acquisition":[116],"conditions":[117],"does":[119],"not":[120],"control":[121],"measures":[123],"coverage":[124],"rather":[125,230],"\u2014":[128],"advantage":[131],"platform":[135],"over":[136],"another":[137],"narrows":[138],"substantially":[139],"once":[140],"matched.":[143],"further":[145],"identify":[146],"resolution":[148],"floor":[149],"no":[151],"improvement":[152],"library":[154],"curation":[155],"can":[156],"remove:":[157],"31.7%":[158],"share":[161],"near-identical":[162],"(cosine":[164],"\u2265":[165],"0.9)":[166],"with":[167,217,237],"at":[168],"least":[169],"distinct":[172],"compound,":[173],"so":[174],"these":[176],"identification":[178],"underdetermined":[180],"spectral":[182],"alone.":[184],"Against":[185],"corrected":[187],"framework,":[188],"49.6%":[189],"12,613,259":[191],"same-compound":[192],"comparisons":[193],"fall":[194],"below":[195],"conventional":[197],"0.7":[198],"threshold":[199],"6.4%":[201],"behave":[204],"outliers":[206],"within":[207],"their":[208],"own":[209],"group.":[211],"release":[213],"collection":[215],"annotated":[216],"spectrum-,":[218],"group-,":[219],"compound-level":[221],"metrics,":[222],"each":[223],"reported":[224],"alongside":[225],"evidence":[227],"supporting":[228],"it":[229],"bare":[234],"proportion,":[235],"together":[236],"pipeline":[239],"open-source":[242],"R":[243],"package.":[244]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-02T00:00:00"}