{"id":"https://openalex.org/W7213594103","doi":"https://doi.org/10.64898/2026.09.12.751192","title":"OpenLipid: a large language model workflow for targeted analysis of DIA mass spectrometry data in lipidomics","display_name":"OpenLipid: a large language model workflow for targeted analysis of DIA mass spectrometry data in lipidomics","publication_year":2026,"publication_date":"2026-09-18","ids":{"openalex":"https://openalex.org/W7213594103","doi":"https://doi.org/10.64898/2026.09.12.751192"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.12.751192","doi":"https://doi.org/10.64898/2026.09.12.751192","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.12.751192","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.12.751192.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.12.751192.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126034494","display_name":"Jiayi Li","orcid":"https://orcid.org/0009-0009-4256-1483","observed_orcids":["https://orcid.org/0009-0009-4256-1483"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4405287053","display_name":"Donnelly Centre for Cellular and Biomolecular Research","ror":"https://ror.org/0400kyd42","country_code":"CA","type":"facility","lineage":["https://openalex.org/I185261750","https://openalex.org/I4405287053"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiayi Li","raw_affiliation_strings":["Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0009-4256-1483","affiliations":[{"raw_affiliation_string":"Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4405287053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058994478","display_name":"Hannes Luc R\u00f6st","orcid":"https://orcid.org/0000-0003-0990-7488","observed_orcids":["https://orcid.org/0000-0003-0990-7488"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4405287053","display_name":"Donnelly Centre for Cellular and Biomolecular Research","ror":"https://ror.org/0400kyd42","country_code":"CA","type":"facility","lineage":["https://openalex.org/I185261750","https://openalex.org/I4405287053"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hannes R\u00f6st","raw_affiliation_strings":["Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0990-7488","affiliations":[{"raw_affiliation_string":"Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4405287053"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058994478"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4405287053"],"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":0.9643999934196472,"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":0.9643999934196472,"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":0.028300000354647636,"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":0.004699999932199717,"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/large-language-models","display_name":"large language models","score":0.9440000057220459},{"id":"https://openalex.org/keywords/data-independent-acquisition","display_name":"data-independent acquisition","score":0.9480000138282776},{"id":"https://openalex.org/keywords/targeted-lipidomics","display_name":"targeted lipidomics","score":0.7990000247955322},{"id":"https://openalex.org/keywords/lipid-identification","display_name":"lipid identification","score":0.9490000009536743},{"id":"https://openalex.org/keywords/extracted-ion-chromatograms","display_name":"extracted ion chromatograms","score":0.9350000023841858},{"id":"https://openalex.org/keywords/human-plasma-lipids","display_name":"human plasma lipids","score":0.7480000257492065},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"false discovery rate","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C58017582","wikidata":"https://www.wikidata.org/wiki/Q6556376","display_name":"Lipidomics","level":2,"score":0.8464999794960022},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7810999751091003},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48260000348091125},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.41929998993873596},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.4007999897003174},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C113196181","wikidata":"https://www.wikidata.org/wiki/Q485223","display_name":"Analytical Chemistry (journal)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C3020134792","wikidata":"https://www.wikidata.org/wiki/Q79749","display_name":"Human plasma","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C135870905","wikidata":"https://www.wikidata.org/wiki/Q903667","display_name":"Metabolome","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C198291218","wikidata":"https://www.wikidata.org/wiki/Q190382","display_name":"Ionization","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.12.751192","doi":"https://doi.org/10.64898/2026.09.12.751192","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.12.751192","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.12.751192.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.12.751192","doi":"https://doi.org/10.64898/2026.09.12.751192","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.12.751192","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.12.751192.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213594103.pdf","grobid_xml":"https://content.openalex.org/works/W7213594103.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7128910616"],"related_works":["https://openalex.org/W2954609940","https://openalex.org/W2902859004","https://openalex.org/W4293051673","https://openalex.org/W2583344557","https://openalex.org/W4248882859","https://openalex.org/W7211907213","https://openalex.org/W2140211274","https://openalex.org/W7213552950","https://openalex.org/W2940557234","https://openalex.org/W4285677483"],"abstract_inverted_index":{"Abstract":[0],"Mass":[1],"spectrometry":[2],"has":[3],"become":[4],"a":[5,37,67,139],"central":[6],"technology":[7],"for":[8,43,79,226,248],"lipidomics,":[9],"with":[10,229],"data-independent":[11],"acquisition":[12,53],"(DIA)":[13],"enabling":[14],"broad":[15],"and":[16,75,96,102,117,133,150,157,160,167,186,192,205,221],"reproducible":[17],"sampling":[18],"of":[19,181,197,235,252],"lipid":[20,31,73,81],"signals.":[21],"However,":[22],"the":[23,189,208],"multiplexed":[24],"fragment-ion":[25],"spectra":[26],"in":[27,66,100,114,119,130,135,155,163,165],"DIA":[28,45,64,200,253],"data":[29,65],"complicate":[30],"identification.":[32],"Here,":[33],"we":[34],"introduce":[35],"OpenLipid,":[36],"large":[38],"language":[39],"model":[40],"(LLM)-based":[41],"workflow":[42,247],"targeted":[44,250],"lipidomics.":[46],"Using":[47],"assay":[48,108,124],"libraries":[49,109,125],"built":[50],"from":[51,63],"data-dependent":[52],"(DDA)":[54],"results,":[55],"OpenLipid":[56,86,146,172,242],"directly":[57],"evaluates":[58],"extracted":[59],"ion":[60],"chromatograms":[61],"(XICs)":[62],"zero-shot":[68],"setting":[69],"to":[70,179],"identify":[71],"target":[72,112,128,227],"peaks":[74],"generate":[76],"human-readable":[77],"rationales":[78],"individual":[80],"identification":[82,176],"decisions.":[83],"We":[84],"benchmarked":[85],"against":[87],"manual":[88],"annotations":[89],"across":[90,188],"four":[91],"datasets":[92],"comprising":[93],"human":[94],"plasma":[95,107,156],"mouse":[97],"feces":[98],"analyzed":[99],"positive":[101,115,131,166],"negative":[103,120,136,168],"ionization":[104,169],"modes.":[105],"The":[106,122],"contained":[110,126],"199":[111],"lipids":[113,129],"mode":[116,132],"147":[118],"mode.":[121,137],"fecal":[123],"181":[127],"264":[134],"At":[138],"5%":[140],"false":[141],"discovery":[142],"rate":[143,177],"(FDR)":[144],"threshold,":[145],"identified":[147],"110":[148],"(55.3%)":[149],"28":[151],"(19.0%)":[152],"library":[153],"targets":[154],"130":[158],"(71.8%)":[159],"84":[161],"(31.8%)":[162],"feces,":[164],"modes,":[170],"respectively.":[171],"achieved":[173],"an":[174,244],"overall":[175],"comparable":[178],"that":[180,196,241],"DIAMetAlyzer":[182],"(57.8%,":[183],"19.7%,":[184],"89.0%,":[185],"17.8%":[187],"corresponding":[190],"datasets)":[191],"substantially":[193],"higher":[194],"than":[195],"untargeted":[198],"MS-DIAL":[199],"analysis":[201,251],"(12.6%,":[202],"0.0%,":[203],"47.5%,":[204],"0.0%)":[206],"on":[207],"same":[209],"assay-library":[210],"targets.":[211],"LLM-derived":[212],"chromatographic":[213],"features":[214],"also":[215],"enabled":[216],"supervised":[217],"discrimination":[218],"between":[219],"correct":[220],"incorrect":[222],"candidate":[223],"peak":[224],"groups":[225],"lipids,":[228],"median":[230],"cross-validation":[231],"average":[232],"precision":[233],"values":[234],"0.838-0.912.":[236],"Together,":[237],"these":[238],"results":[239],"demonstrate":[240],"is":[243],"effective":[245],"LLM-based":[246],"FDR-controlled":[249],"lipidomics":[254],"data.":[255]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-19T00:00:00"}