{"id":"https://openalex.org/W7166307996","doi":"https://doi.org/10.64898/2026.06.23.734138","title":"Agentic AI for Structural Elucidation and Discovery of Drug Metabolites from Mass Spectrometry Data","display_name":"Agentic AI for Structural Elucidation and Discovery of Drug Metabolites from Mass Spectrometry Data","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166307996","doi":"https://doi.org/10.64898/2026.06.23.734138","pmid":"https://pubmed.ncbi.nlm.nih.gov/42395381","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13320852"},"language":"en","primary_location":{"id":"doi:10.64898/2026.06.23.734138","doi":"https://doi.org/10.64898/2026.06.23.734138","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.06.23.734138","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/06/26/2026.06.23.734138.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/06/26/2026.06.23.734138.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135891602","display_name":"Xianghu Wang","orcid":"https://orcid.org/0009-0005-4902-6724","observed_orcids":["https://orcid.org/0009-0005-4902-6724"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianghu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, United States"],"raw_orcid":"https://orcid.org/0009-0005-4902-6724","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, United States","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046351795","display_name":"Abubaker Patan","orcid":"https://orcid.org/0000-0003-1415-7829","observed_orcids":["https://orcid.org/0000-0003-1415-7829"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abubaker Patan","raw_affiliation_strings":["Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":"https://orcid.org/0000-0003-1415-7829","affiliations":[{"raw_affiliation_string":"Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152083336","display_name":"Haoqi Nina Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoqi Nina Zhao","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, United States","Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, United States","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085873057","display_name":"Vincent Charron\u2010Lamoureux","orcid":"https://orcid.org/0000-0001-9440-7036","observed_orcids":["https://orcid.org/0000-0001-9440-7036"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Charron-Lamoureux","raw_affiliation_strings":["Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":"https://orcid.org/0000-0001-9440-7036","affiliations":[{"raw_affiliation_string":"Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010700327","display_name":"Yourae Shin","orcid":"https://orcid.org/0000-0002-3274-726X","observed_orcids":["https://orcid.org/0000-0002-3274-726X"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yourae Shin","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, United States","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012059205","display_name":"Daniel Petras","orcid":"https://orcid.org/0000-0002-6561-3022","observed_orcids":["https://orcid.org/0000-0002-6561-3022"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Petras","raw_affiliation_strings":["Department of Biochemistry, University of California Riverside, Riverside, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry, University of California Riverside, Riverside, CA, United States","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428527","display_name":"Yuhui Hong","orcid":"https://orcid.org/0000-0002-5647-9714","observed_orcids":["https://orcid.org/0000-0002-5647-9714"]},"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":"Yuhui Hong","raw_affiliation_strings":["Department of Genome Sciences, University of Washington, Seattle, WA, United States"],"raw_orcid":"https://orcid.org/0000-0002-5647-9714","affiliations":[{"raw_affiliation_string":"Department of Genome Sciences, University of Washington, Seattle, WA, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049109394","display_name":"Benjamin P. Bowen","orcid":"https://orcid.org/0000-0003-1368-3958","observed_orcids":["https://orcid.org/0000-0003-1368-3958"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin P. Bowen","raw_affiliation_strings":["Environmental Genomics and Systems biology, Lawrence Berkeley National Laboratory, Berkeley, CA, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-1368-3958","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems biology, Lawrence Berkeley National Laboratory, Berkeley, CA, United States of America","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044268097","display_name":"Trent R. Northen","orcid":"https://orcid.org/0000-0001-8404-3259","observed_orcids":["https://orcid.org/0000-0001-8404-3259"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trent R. Northen","raw_affiliation_strings":["Environmental Genomics and Systems biology, Lawrence Berkeley National Laboratory, Berkeley, CA, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8404-3259","affiliations":[{"raw_affiliation_string":"Environmental Genomics and Systems biology, Lawrence Berkeley National Laboratory, Berkeley, CA, United States of America","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082720301","display_name":"Pieter C. Dorrestein","orcid":"https://orcid.org/0000-0002-3003-1030","observed_orcids":["https://orcid.org/0000-0002-3003-1030"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter C. Dorrestein","raw_affiliation_strings":["Collaborative Mass Spectrometry Innovation Center, Skaggs School of Pharmacy and Pharmaceutical Sciences, La Jolla, CA, United States"],"raw_orcid":"https://orcid.org/0000-0002-3003-1030","affiliations":[{"raw_affiliation_string":"Collaborative Mass Spectrometry Innovation Center, Skaggs School of Pharmacy and Pharmaceutical Sciences, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058074901","display_name":"Mingxun Wang","orcid":"https://orcid.org/0000-0001-7647-6097","observed_orcids":["https://orcid.org/0000-0001-7647-6097"]},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingxun Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, United States"],"raw_orcid":"https://orcid.org/0000-0001-7647-6097","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California Riverside, Riverside, CA, United States","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058074901"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9731000065803528,"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":0.9731000065803528,"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":0.013000000268220901,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/agentic-ai","display_name":"agentic AI","score":0.9760000109672546},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9599999785423279},{"id":"https://openalex.org/keywords/drug-metabolites","display_name":"drug metabolites","score":0.8410000205039978},{"id":"https://openalex.org/keywords/metabolomics","display_name":"metabolomics","score":0.5429999828338623},{"id":"https://openalex.org/keywords/structure-elucidation","display_name":"structure elucidation","score":0.7200000286102295},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.8539999723434448},{"id":"https://openalex.org/keywords/spectral-alignment","display_name":"spectral alignment","score":0.7699999809265137},{"id":"https://openalex.org/keywords/spectrum-prediction","display_name":"spectral prediction","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5523999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5462999939918518},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.46810001134872437},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C21565614","wikidata":"https://www.wikidata.org/wiki/Q12149006","display_name":"Metabolomics","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C64903051","wikidata":"https://www.wikidata.org/wiki/Q2198549","display_name":"Drug development","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C2777477808","wikidata":"https://www.wikidata.org/wiki/Q407595","display_name":"Metabolite","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2989108626","wikidata":"https://www.wikidata.org/wiki/Q904407","display_name":"Drug target","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25780001282691956}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.06.23.734138","doi":"https://doi.org/10.64898/2026.06.23.734138","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.06.23.734138","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/06/26/2026.06.23.734138.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:42395381","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42395381","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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13320852","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13320852/","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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.64898/2026.06.23.734138","doi":"https://doi.org/10.64898/2026.06.23.734138","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.06.23.734138","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/06/26/2026.06.23.734138.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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/G9000856284","display_name":"Mapping Xenobiotic Metabolism by the Human Gut Microbiome","funder_award_id":"K99ES037746","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"},{"id":"https://openalex.org/G9000868323","display_name":"Reverse Metabolomics for the Discovery of Disease Associated Microbial Molecules","funder_award_id":"R01DK136117","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"},{"id":"https://openalex.org/G9000868334","display_name":"Unified Computation Tools for Natural Products research","funder_award_id":"R01GM107550","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G9000868522","display_name":"Collaborative Microbial Metabolite Center","funder_award_id":"U24DK133658","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"},{"id":"https://openalex.org/F4320337361","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166307996.pdf","grobid_xml":"https://content.openalex.org/works/W7166307996.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1960974681","https://openalex.org/W2008420299","https://openalex.org/W2017581392","https://openalex.org/W2059651000","https://openalex.org/W2065104255","https://openalex.org/W2066273100","https://openalex.org/W2178264756","https://openalex.org/W2315852388","https://openalex.org/W2504691963","https://openalex.org/W2997345427","https://openalex.org/W2999579513","https://openalex.org/W3049190563","https://openalex.org/W3209680996","https://openalex.org/W4294782938","https://openalex.org/W4365450264","https://openalex.org/W4386510404","https://openalex.org/W4388735079","https://openalex.org/W4391772345","https://openalex.org/W4398203672","https://openalex.org/W4399281306","https://openalex.org/W4407240787","https://openalex.org/W4409293760","https://openalex.org/W4410309270","https://openalex.org/W4410621552","https://openalex.org/W4410706574","https://openalex.org/W4410930145","https://openalex.org/W4416354948","https://openalex.org/W4416889896","https://openalex.org/W4417272637","https://openalex.org/W4417427749","https://openalex.org/W7127899384","https://openalex.org/W7133198585","https://openalex.org/W7133221075","https://openalex.org/W7160824104"],"related_works":["https://openalex.org/W7155500026","https://openalex.org/W7165189316","https://openalex.org/W4404407658","https://openalex.org/W7124160597","https://openalex.org/W7161637271","https://openalex.org/W4414298206","https://openalex.org/W7092284795","https://openalex.org/W7154980007","https://openalex.org/W7117667002","https://openalex.org/W4416079856"],"abstract_inverted_index":{"The":[0,126],"majority":[1],"of":[2,115],"chemical":[3,124],"signals":[4],"detected":[5],"in":[6],"public":[7,120,148],"metabolomics":[8],"repositories":[9],"remain":[10],"structurally":[11],"undefined.":[12],"Large":[13],"language":[14,101],"models":[15],"(LLMs)":[16],"are":[17],"probabilistic":[18],"systems":[19],"whose":[20],"capacity":[21,60],"to":[22,38,50,66],"generate":[23,164],"outputs":[24],"beyond":[25],"their":[26],"training":[27],"data,":[28],"which":[29],"can":[30,162],"cause":[31],"hallucinations,":[32],"makes":[33],"them":[34],"also":[35],"potentially":[36],"suited":[37],"hypothesize":[39],"structures":[40],"for":[41,169],"molecules":[42],"that":[43,54,80,153],"have":[44],"never":[45],"been":[46],"described.":[47],"We":[48,73,111],"aimed":[49],"build":[51],"a":[52,75,133],"system":[53,79],"could":[55],"harness":[56],"this":[57],"LLM":[58],"generative":[59],"combined":[61,158],"with":[62,159],"domain":[63,104,160],"specific":[64],"tools/framework":[65],"constrain":[67],"hallucination":[68],"and":[69,98,129,140],"produce":[70],"validated":[71],"discoveries.":[72],"developed":[74],"GNPS2":[76],"agentic":[77,155],"AI":[78],"interprets":[81],"LC-MS/MS":[82],"data":[83,121],"by":[84,123],"integrating":[85],"spectral":[86],"alignment,":[87],"molecular":[88],"formula":[89],"inference,":[90],"rule-based":[91],"structural":[92,167],"enumeration,":[93],"machine":[94],"learning-based":[95],"spectrum":[96],"prediction,":[97],"translates":[99],"natural":[100],"hypotheses":[102,168],"from":[103,119,147],"experts":[105],"into":[106],"dynamically":[107],"generated":[108],"analytical":[109],"workflows.":[110],"demonstrate":[112,152],"the":[113],"annotation":[114],"unknown":[116],"drug":[117],"metabolites":[118,172],"guided":[122],"hypotheses.":[125],"agent":[127],"predicted,":[128],"we":[130],"experimentally":[131,165],"confirmed,":[132],"phosphorylated":[134],"hydroxyzine,":[135],"an":[136],"acetaminophen-p-coumaric":[137],"acid":[138],"ester,":[139],"identified":[141],"two":[142],"new":[143],"oxidative":[144],"ibuprofen-carnitine":[145],"conjugates":[146],"repositories.":[149],"These":[150],"results":[151],"LLM-driven":[154],"reasoning,":[156],"when":[157],"expertise,":[161],"indeed":[163],"testable":[166],"previously":[170],"uncharacterized":[171],"leveraging":[173],"pan":[174],"repository":[175],"data.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-06-28T00:00:00"}
