{"id":"https://openalex.org/W4411708403","doi":"https://doi.org/10.1093/bioinformatics/btaf354","title":"JESTR: Joint Embedding Space Technique for Ranking candidate molecules for the annotation of untargeted metabolomics data","display_name":"JESTR: Joint Embedding Space Technique for Ranking candidate molecules for the annotation of untargeted metabolomics data","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411708403","doi":"https://doi.org/10.1093/bioinformatics/btaf354","pmid":"https://pubmed.ncbi.nlm.nih.gov/40574677"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf354","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf354","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf354/63508085/btaf354.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf354/63508085/btaf354.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002724808","display_name":"Apurva Kalia","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apurva Kalia","raw_affiliation_strings":["Department of Computer Science, Tufts University , Medford, MA 02155,","Department of Computer Science, Tufts University, Medford, MA 02155, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University , Medford, MA 02155,","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA 02155, United States","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107503581","display_name":"Yan Zhou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Zhou Chen","raw_affiliation_strings":["Department of Computer Science, Tufts University , Medford, MA 02155,","Department of Computer Science, Tufts University, Medford, MA 02155, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University , Medford, MA 02155,","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA 02155, United States","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103083233","display_name":"Dilip Krishnan","orcid":"https://orcid.org/0000-0002-9183-2886"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilip Krishnan","raw_affiliation_strings":["Google DeepMind , Mountain View, CA 94043,","Google DeepMind, Mountain View, CA 94043, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind , Mountain View, CA 94043,","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google DeepMind, Mountain View, CA 94043, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048817284","display_name":"Soha Hassoun","orcid":"https://orcid.org/0000-0001-9477-2199"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soha Hassoun","raw_affiliation_strings":["Department of Chemical and Biological Engineering, Tufts University , Medford, MA 02155,","Department of Computer Science, Tufts University , Medford, MA 02155,","Department of Chemical and Biological Engineering, Tufts University, Medford, MA 02155, United States"],"raw_orcid":"https://orcid.org/0000-0001-9477-2199","affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, Tufts University , Medford, MA 02155,","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University , Medford, MA 02155,","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Chemical and Biological Engineering, Tufts University, Medford, MA 02155, United States","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048817284"],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.4378,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89100391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"41","issue":"7","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":0.8835999965667725,"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":0.8835999965667725,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.045499999076128006,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.02500000037252903,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7930724620819092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6553129553794861},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.5315625071525574},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.44233161211013794},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.351302832365036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3367588520050049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2732398211956024},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18175014853477478}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7930724620819092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6553129553794861},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.5315625071525574},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44233161211013794},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.351302832365036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3367588520050049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2732398211956024},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18175014853477478},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf354","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf354","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf354/63508085/btaf354.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40574677","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40574677","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,"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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12233093","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12233093","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf354","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf354","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf354/63508085/btaf354.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G362080672","display_name":null,"funder_award_id":"R35GM148219","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3803196217","display_name":null,"funder_award_id":"R35GM148219","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411708403.pdf","grobid_xml":"https://content.openalex.org/works/W4411708403.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2015503332","https://openalex.org/W2025944550","https://openalex.org/W2107183338","https://openalex.org/W2285468881","https://openalex.org/W2504691963","https://openalex.org/W2609624643","https://openalex.org/W2777416523","https://openalex.org/W2899070097","https://openalex.org/W2921388451","https://openalex.org/W2922522932","https://openalex.org/W2972554015","https://openalex.org/W3023343624","https://openalex.org/W3108604517","https://openalex.org/W3129424480","https://openalex.org/W3194841450","https://openalex.org/W3213822864","https://openalex.org/W4281688302","https://openalex.org/W4381615239","https://openalex.org/W4381804451","https://openalex.org/W4385246048","https://openalex.org/W4385955529","https://openalex.org/W4393981121","https://openalex.org/W4401842436","https://openalex.org/W4403380203","https://openalex.org/W4403402307","https://openalex.org/W4407128387","https://openalex.org/W4407270847","https://openalex.org/W4410621552","https://openalex.org/W6776700526","https://openalex.org/W6874320013"],"related_works":["https://openalex.org/W878150521","https://openalex.org/W2008941207","https://openalex.org/W2373662841","https://openalex.org/W1970478390","https://openalex.org/W1533638723","https://openalex.org/W294916044","https://openalex.org/W2014546971","https://openalex.org/W4248631090","https://openalex.org/W2131667412","https://openalex.org/W2019959197"],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1],"major":[2],"challenge":[3],"in":[4,19,22,34,74],"metabolomics":[5],"is":[6],"annotation:":[7],"assigning":[8],"molecular":[9,49],"structures":[10,79],"to":[11,145],"mass":[12],"spectral":[13],"fragmentation":[14],"patterns.":[15],"Despite":[16],"recent":[17],"advances":[18],"molecule-to-spectra":[20],"and":[21,59,69,92,101,140,149,165,179,204],"spectra-to-molecular":[23],"fingerprint":[24],"(FP)":[25],"prediction,":[26],"annotation":[27,104],"rates":[28],"remain":[29],"low.":[30],"RESULTS:":[31],"We":[32,95,119],"introduce":[33],"this":[35],"article":[36],"a":[37,75,186],"novel":[38,187],"tool":[39],"(JESTR)":[40],"for":[41,111],"annotation.":[42],"Unlike":[43],"prior":[44],"approaches":[45],"that":[46,57,157],"\"explicitly\"":[47],"construct":[48],"FPs":[50],"or":[51],"spectra,":[52],"JESTR":[53,97,113,173],"leverages":[54],"the":[55,66,87,122,142,198],"insight":[56],"molecules":[58,129],"their":[60,72],"corresponding":[61],"spectra":[62],"are":[63,80],"views":[64],"of":[65,89,125,158,163,170],"same":[67],"data":[68],"effectively":[70],"embeds":[71],"representations":[73],"joint":[76],"space.":[77],"Candidate":[78],"ranked":[81],"based":[82],"on":[83,106,167],"cosine":[84],"similarity":[85],"between":[86,147],"embeddings":[88],"query":[90],"spectrum":[91],"each":[93],"candidate.":[94],"evaluate":[96],"against":[98,156],"mol-to-spec,":[99],"spec-to-FP,":[100],"spec-mol":[102],"matching":[103],"tools":[105,116,176],"four":[107],"datasets.":[108],"On":[109],"average,":[110],"rank@[1-20],":[112],"outperforms":[114,174],"other":[115],"by":[117,135,177],"55.5%-302.6%.":[118],"further":[120],"demonstrate":[121],"strong":[123],"value":[124],"regularization":[126],"with":[127],"candidate":[128,150],"during":[130],"training,":[131],"boosting":[132],"rank@1":[133],"performance":[134,155],"5.72%":[136],"across":[137],"all":[138],"datasets":[139],"enhancing":[141],"model's":[143],"ability":[144],"discern":[146],"target":[148],"molecules.":[151],"When":[152],"comparing":[153],"JESTR's":[154],"publicly":[159],"available":[160,206],"pretrained":[161],"models":[162],"SIRIUS":[164],"CFM-ID":[166],"appropriate":[168],"subsets":[169],"MassSpecGym":[171],"dataset,":[172],"these":[175],"31%":[178],"238%,":[180],"respectively.":[181],"Through":[182],"JESTR,":[183],"we":[184],"offer":[185],"promising":[188],"avenue":[189],"toward":[190],"accurate":[191],"annotation,":[192],"therefore":[193],"unlocking":[194],"valuable":[195],"insights":[196],"into":[197],"metabolome.":[199],"AVAILABILITY":[200],"AND":[201],"IMPLEMENTATION:":[202],"Code":[203],"dataset":[205],"at":[207],"https://github.com/HassounLab/JESTR1/.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-06-27T00:00:00"}
