{"id":"https://openalex.org/W7204853587","doi":"https://doi.org/10.26434/chemrxiv.15005624/v2","title":"Quantifying Fragment Ambiguity inLC-ESI-HRMS-MS2 Spectral Databases","display_name":"Quantifying Fragment Ambiguity inLC-ESI-HRMS-MS2 Spectral Databases","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204853587","doi":"https://doi.org/10.26434/chemrxiv.15005624/v2"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15005624/v2","doi":"https://doi.org/10.26434/chemrxiv.15005624/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15005624/v2","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15005624/v2","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.15005624/v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091949517","display_name":"Viktoriia Turkina","orcid":"https://orcid.org/0000-0002-7153-2333","observed_orcids":["https://orcid.org/0000-0002-7153-2333"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Viktoriia Turkina","raw_affiliation_strings":["Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam"],"raw_orcid":"https://orcid.org/0000-0002-7153-2333","affiliations":[{"raw_affiliation_string":"Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074973851","display_name":"Lapo Renai","orcid":"https://orcid.org/0000-0002-0738-7901","observed_orcids":["https://orcid.org/0000-0002-0738-7901"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lapo Renai","raw_affiliation_strings":["Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022268736","display_name":"Annemieke Petrignani","orcid":"https://orcid.org/0000-0002-6116-5867","observed_orcids":["https://orcid.org/0000-0002-6116-5867"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Annemieke Petrignani","raw_affiliation_strings":["Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040594335","display_name":"Garry L. Corthals","orcid":"https://orcid.org/0000-0001-9423-5596","observed_orcids":["https://orcid.org/0000-0001-9423-5596"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Garry Corthals","raw_affiliation_strings":["Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075470113","display_name":"Jake William O'Brien","orcid":"https://orcid.org/0000-0001-9336-9656","observed_orcids":["https://orcid.org/0000-0001-9336-9656"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["AU","NL"],"is_corresponding":false,"raw_author_name":"Jake W. O\u2019Brien","raw_affiliation_strings":["Queensland Alliance for Environmental Health Sciences (QAEHS, University of Queensland, 20 Cornwall Street, Woolloongabba, QLD, Australia, 4102","Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland Alliance for Environmental Health Sciences (QAEHS, University of Queensland, 20 Cornwall Street, Woolloongabba, QLD, Australia, 4102","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036460989","display_name":"Saer Samanipour","orcid":"https://orcid.org/0000-0001-8270-6979","observed_orcids":["https://orcid.org/0000-0001-8270-6979"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["AU","NL"],"is_corresponding":false,"raw_author_name":"Saer Samanipour","raw_affiliation_strings":["Queensland Alliance for Environmental Health Sciences (QAEHS, University of Queensland, 20 Cornwall Street, Woolloongabba, QLD, Australia, 4102","University of Amsterdam","UvA Data Science Center","Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland Alliance for Environmental Health Sciences (QAEHS, University of Queensland, 20 Cornwall Street, Woolloongabba, QLD, Australia, 4102","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"UvA Data Science Center","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Van \u2018t Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.5859000086784363,"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":0.5859000086784363,"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":0.3840000033378601,"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":0.008899999782443047,"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/spectral-library","display_name":"spectral library","score":0.640999972820282},{"id":"https://openalex.org/keywords/non-targeted-analysis","display_name":"non-targeted analysis","score":0.7269999980926514},{"id":"https://openalex.org/keywords/compound-annotation","display_name":"compound annotation","score":0.6510000228881836},{"id":"https://openalex.org/keywords/suspect-screening","display_name":"suspect screening","score":0.7020000219345093},{"id":"https://openalex.org/keywords/spectral-library-matching","display_name":"spectral library matching","score":0.8320000171661377},{"id":"https://openalex.org/keywords/identification-confidence","display_name":"identification confidence","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.8600000143051147},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.8224999904632568},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5235000252723694},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.4629000127315521},{"id":"https://openalex.org/C2777559092","wikidata":"https://www.wikidata.org/wiki/Q4741445","display_name":"Ambiguity resolution","level":4,"score":0.40790000557899475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3808000087738037},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C124967146","wikidata":"https://www.wikidata.org/wiki/Q3457898","display_name":"Spectral resolution","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C152822103","wikidata":"https://www.wikidata.org/wiki/Q7575207","display_name":"Spectral shape analysis","level":3,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15005624/v2","doi":"https://doi.org/10.26434/chemrxiv.15005624/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15005624/v2","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15005624/v2","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.15005624/v2","doi":"https://doi.org/10.26434/chemrxiv.15005624/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15005624/v2","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15005624/v2","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":[{"id":"https://openalex.org/G5042321550","display_name":"Comprehensive characterisation of the PFAS exposome","funder_award_id":"1185347","funder_id":"https://openalex.org/F4320334705","funder_display_name":"National Health and Medical Research Council"},{"id":"https://openalex.org/G5217127770","display_name":null,"funder_award_id":"EL12009209","funder_id":"https://openalex.org/F4320334705","funder_display_name":"National Health and Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320311869","display_name":"Queensland Health","ror":"https://ror.org/00c1dt378"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320984","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422"},{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"},{"id":"https://openalex.org/F4320334705","display_name":"National Health and Medical Research Council","ror":"https://ror.org/011kf5r70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204853587.pdf","grobid_xml":"https://content.openalex.org/works/W7204853587.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7167264737","https://openalex.org/W3191832991","https://openalex.org/W2066493889","https://openalex.org/W3006054343","https://openalex.org/W3001626355","https://openalex.org/W7164399956","https://openalex.org/W7204029792","https://openalex.org/W4380853382","https://openalex.org/W4412184154","https://openalex.org/W2965340304"],"abstract_inverted_index":{"LC\u2013MS/HRMS-based":[0],"non-target":[1],"analysis":[2],"relies":[3],"heavily":[4],"on":[5,168],"MS2":[6,92],"spectral":[7,66,83,151,159,180,192,230],"matching":[8,182],"for":[9,110,206,225],"compound":[10],"annotation.":[11],"However,":[12],"not":[13],"all":[14],"fragments":[15,95,116,202],"contribute":[16],"equally":[17],"to":[18,38,176,191],"identification":[19],"confidence,":[20],"and":[21,54,72,79,121,148,156,171,179,209],"quantitative":[22,223],"measures":[23],"of":[24,76,100,115,154,174,200,213,216],"fragment":[25,40,52,164,185,227],"ambiguity":[26,165,187,228],"remain":[27],"lacking.":[28],"In":[29],"this":[30],"study,":[31],"we":[32],"developed":[33],"a":[34,222],"data-driven":[35],"probabilistic":[36],"framework":[37,220],"assess":[39],"level":[41,186],"diagnostic":[42,111,135],"power":[43],"through":[44],"the":[45,108,118,124,198,211],"Fragment":[46],"Ambiguity":[47],"Score":[48],"(FAS),":[49],"which":[50],"combines":[51],"stability":[53],"specificity":[55],"within":[56],"precursor-mass-defined":[57],"candidate":[58],"spaces.":[59],"FAS":[60,103,175],"was":[61],"evaluated":[62,145],"using":[63],"five":[64],"experimental":[65,119,155],"databases":[67,120,138,160],"(MassBank,":[68],"MoNA,":[69],"GNPS,":[70],"NIST20,":[71],"MSnLib),":[73],"comprising":[74],"together":[75],"1,026,855":[77],"spectra":[78,93],"an":[80],"in":[81,117,123,125,136,157,229],"silico":[82,126,158],"library":[84,127,181],"containing":[85],"256,865":[86],"spectra.":[87],"The":[88,218],"results":[89],"showed":[90],"that":[91,163,184,197],"contain":[94],"with":[96],"substantially":[97,141],"different":[98],"levels":[99],"ambiguity.":[101],"Using":[102],"\u2264":[104],"0.5":[105],"as":[106,130],"12":[107],"threshold":[109],"fragments,":[112],"only":[113],"14.1%":[114],"10.7%":[122],"were":[128],"classified":[129],"diagnostic.":[131],"Fragments":[132],"appearing":[133],"highly":[134],"smaller":[137],"often":[139],"become":[140],"more":[142,149],"ambiguous":[143],"when":[144],"against":[146],"larger":[147],"diverse":[150],"collections.":[152],"Comparison":[153],"further":[161],"illustrated":[162],"estimates":[166],"depend":[167],"database":[169],"origin":[170],"composition.":[172],"Application":[173],"suspect":[177],"screening":[178],"demonstrated":[183],"provides":[188,221],"complementary":[189,214],"evidence":[190],"similarity.":[193],"These":[194],"findings":[195],"demonstrate":[196],"number":[199],"matched":[201],"alone":[203],"is":[204],"insufficient":[205],"confidence":[207],"assessment":[208],"highlight":[210],"importance":[212],"sources":[215],"evidence.":[217],"proposed":[219],"basis":[224],"assessing":[226],"databases.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-01T00:00:00"}