{"id":"https://openalex.org/W4313430536","doi":"https://doi.org/10.1038/s42256-022-00577-2","title":"Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data","display_name":"Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data","publication_year":2022,"publication_date":"2022-12-19","ids":{"openalex":"https://openalex.org/W4313430536","doi":"https://doi.org/10.1038/s42256-022-00577-2"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-022-00577-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00577-2","pdf_url":"https://www.nature.com/articles/s42256-022-00577-2.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s42256-022-00577-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057710320","display_name":"Eric Bach","orcid":"https://orcid.org/0000-0001-6200-5462"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eric Bach","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-6200-5462","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016319274","display_name":"Emma Schymanski","orcid":"https://orcid.org/0000-0001-6868-8145"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Emma L. Schymanski","raw_affiliation_strings":["Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, Belvaux, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0001-6868-8145","affiliations":[{"raw_affiliation_string":"Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, Belvaux, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091883185","display_name":"Juho Rousu","orcid":"https://orcid.org/0000-0002-0705-4314"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juho Rousu","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-0705-4314","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":11690,"currency":"USD","value_usd":11690},"apc_paid":{"value":11690,"currency":"USD","value_usd":11690},"fwci":2.5881,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.91245658,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"4","issue":"12","first_page":"1224","last_page":"1237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":1.0,"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":1.0,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9991999864578247,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6778856515884399},{"id":"https://openalex.org/keywords/tandem-mass-spectrometry","display_name":"Tandem mass spectrometry","score":0.6169504523277283},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"Mass spectrometry","score":0.6159170269966125},{"id":"https://openalex.org/keywords/liquid-chromatography\u2013mass-spectrometry","display_name":"Liquid chromatography\u2013mass spectrometry","score":0.5421420335769653},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.5368320345878601},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.5284259915351868},{"id":"https://openalex.org/keywords/metabolomics","display_name":"Metabolomics","score":0.4517854154109955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41355717182159424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18190523982048035}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6778856515884399},{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.6169504523277283},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.6159170269966125},{"id":"https://openalex.org/C64489805","wikidata":"https://www.wikidata.org/wiki/Q873864","display_name":"Liquid chromatography\u2013mass spectrometry","level":3,"score":0.5421420335769653},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.5368320345878601},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.5284259915351868},{"id":"https://openalex.org/C21565614","wikidata":"https://www.wikidata.org/wiki/Q12149006","display_name":"Metabolomics","level":2,"score":0.4517854154109955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41355717182159424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18190523982048035}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1038/s42256-022-00577-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00577-2","pdf_url":"https://www.nature.com/articles/s42256-022-00577-2.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/118664","is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/118664","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:orbilu.uni.lu:10993/54236","is_oa":true,"landing_page_url":"http://orbilu.uni.lu/handle/10993/54236","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nature Machine Intelligence, 4 (12), 1224--1237 (2022)","raw_type":"http://purl.org/coar/resource_type/c_6501"}],"best_oa_location":{"id":"doi:10.1038/s42256-022-00577-2","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00577-2","pdf_url":"https://www.nature.com/articles/s42256-022-00577-2.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1731480922","display_name":null,"funder_award_id":"A18/BM/12341006","funder_id":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg"},{"id":"https://openalex.org/G200073512","display_name":null,"funder_award_id":"310107","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G6999706713","display_name":"Machine learning for digItal diagnostics of antimicrobial resistance","funder_award_id":"334790","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320320923","display_name":"Branco Weiss Fellowship \u2013 Society in Science","ror":"https://ror.org/05a28rw58"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313430536.pdf","grobid_xml":"https://content.openalex.org/works/W4313430536.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1975147762","https://openalex.org/W1976892175","https://openalex.org/W1983289383","https://openalex.org/W1988037271","https://openalex.org/W1995543670","https://openalex.org/W2015503332","https://openalex.org/W2015612871","https://openalex.org/W2044115597","https://openalex.org/W2047221353","https://openalex.org/W2059327215","https://openalex.org/W2061800084","https://openalex.org/W2069870183","https://openalex.org/W2081301924","https://openalex.org/W2115386194","https://openalex.org/W2115993694","https://openalex.org/W2125069590","https://openalex.org/W2136885855","https://openalex.org/W2144803530","https://openalex.org/W2179948434","https://openalex.org/W2265106087","https://openalex.org/W2285468881","https://openalex.org/W2289191408","https://openalex.org/W2440171437","https://openalex.org/W2548357532","https://openalex.org/W2548695521","https://openalex.org/W2603853601","https://openalex.org/W2622236128","https://openalex.org/W2729094614","https://openalex.org/W2767683865","https://openalex.org/W2802909948","https://openalex.org/W2808125645","https://openalex.org/W2887285382","https://openalex.org/W2892186999","https://openalex.org/W2896473185","https://openalex.org/W2906914952","https://openalex.org/W2914609306","https://openalex.org/W2922522932","https://openalex.org/W2953777054","https://openalex.org/W2954086013","https://openalex.org/W2956970085","https://openalex.org/W2979579661","https://openalex.org/W3009862931","https://openalex.org/W3015831215","https://openalex.org/W3021129126","https://openalex.org/W3040179918","https://openalex.org/W3058514020","https://openalex.org/W3081878206","https://openalex.org/W3097145107","https://openalex.org/W3110221305","https://openalex.org/W3118642024","https://openalex.org/W3156988877","https://openalex.org/W3194841450","https://openalex.org/W4237359806","https://openalex.org/W4256089724","https://openalex.org/W4393664346","https://openalex.org/W4393702174","https://openalex.org/W4393759338"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2103021125","https://openalex.org/W2051901836","https://openalex.org/W1968441093","https://openalex.org/W4210928771","https://openalex.org/W1968381290","https://openalex.org/W1985701257","https://openalex.org/W4323347615"],"abstract_inverted_index":{"Abstract":[0],"Structural":[1],"annotation":[2,71,174,182],"of":[3,33,43,51,72,95,114,184,195],"small":[4],"molecules":[5,44,145],"in":[6,13,19,45,99,138,162,205],"biological":[7],"samples":[8],"remains":[9],"a":[10,46,65,93,100,103,128],"key":[11],"bottleneck":[12],"untargeted":[14],"metabolomics,":[15],"despite":[16],"rapid":[17],"progress":[18],"predictive":[20],"methods":[21,178],"and":[22,119,179,208],"tools":[23],"during":[24],"the":[25,34,48,90,112,139,157,181],"past":[26],"decade.":[27],"Liquid":[28],"chromatography\u2013tandem":[29,78],"mass":[30,79,96],"spectrometry,":[31],"one":[32],"most":[35],"widely":[36],"used":[37],"analysis":[38],"platforms,":[39],"can":[40],"detect":[41],"thousands":[42],"sample,":[47,101],"vast":[49],"majority":[50],"which":[52,202],"remain":[53],"unidentified":[54],"even":[55],"with":[56],"best-of-class":[57],"methods.":[58],"Here":[59],"we":[60],"present":[61],"LC-MS":[62,85,135,168,215],"2":[63,82,86,117,136,165,169,187,216],"Struct,":[64],"machine":[66],"learning":[67],"framework":[68],"for":[69,92,212],"structural":[70],"small-molecule":[73],"data":[74,137],"arising":[75],"from":[76,152],"liquid":[77],"spectrometry":[80,97],"(LC-MS":[81],")":[83],"measurements.":[84],"Struct":[87,170],"jointly":[88],"predicts":[89],"annotations":[91],"set":[94],"features":[98],"using":[102,147],"novel":[104],"structured":[105],"prediction":[106,200],"model":[107],"trained":[108],"to":[109,191],"optimally":[110],"combine":[111],"output":[113],"state-of-the-art":[115,185],"MS":[116,186],"scorers":[118,188],"observed":[120],"retention":[121],"orders.":[122],"We":[123],"evaluate":[124],"our":[125],"method":[126],"on":[127],"dataset":[129],"covering":[130],"all":[131],"publicly":[132],"available":[133],"reversed-phase":[134],"MassBank":[140],"reference":[141],"database,":[142],"including":[143],"4,327":[144],"measured":[146],"18":[148],"different":[149],"LC":[150],"conditions":[151],"16":[153],"contributors,":[154],"greatly":[155],"expanding":[156],"chemical":[158],"analytical":[159],"space":[160],"covered":[161],"previous":[163],"multi-MS":[164],"scorer":[166],"evaluations.":[167],"obtains":[171],"significantly":[172],"higher":[173],"accuracy":[175,183],"than":[176],"earlier":[177],"improves":[180,199],"by":[189],"up":[190],"106%.":[192],"The":[193],"use":[194],"stereochemistry-aware":[196],"molecular":[197],"fingerprints":[198],"performance,":[201],"highlights":[203],"limitations":[204],"existing":[206],"approaches":[207],"has":[209],"strong":[210],"implications":[211],"future":[213],"computational":[214],"developments.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}