{"id":"https://openalex.org/W7160846717","doi":"https://doi.org/10.1021/acs.jcim.6c00727","title":"Reliable Molecular Retrieval from Mass Spectra Using Conformal Prediction","display_name":"Reliable Molecular Retrieval from Mass Spectra Using Conformal Prediction","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160846717","doi":"https://doi.org/10.1021/acs.jcim.6c00727","pmid":"https://pubmed.ncbi.nlm.nih.gov/42113637"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.6c00727","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6c00727","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001030142","display_name":"Morteza Rakhshaninejad","orcid":"https://orcid.org/0000-0001-5250-9165"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Morteza Rakhshaninejad","raw_affiliation_strings":["Department of Data Analysis and Mathematical Modeling, Ghent University, Coupure Links 653, Ghent 9000, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-5250-9165","affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Mathematical Modeling, Ghent University, Coupure Links 653, Ghent 9000, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052622361","display_name":"Gaetan De Waele","orcid":"https://orcid.org/0000-0003-0367-9699"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210111370","display_name":"ZNA Middelheim Hospital","ror":"https://ror.org/01z5jvj74","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I4210111370"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Gaetan De Waele","raw_affiliation_strings":["Department of Computer Science, University of Antwerp, Middelheimlaan 1, Antwerp 2020, Belgium"],"raw_orcid":"https://orcid.org/0000-0003-0367-9699","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Antwerp, Middelheimlaan 1, Antwerp 2020, Belgium","institution_ids":["https://openalex.org/I4210111370","https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129564375","display_name":"Mira J\u00fcrgens","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mira J\u00fcrgens","raw_affiliation_strings":["Department of Data Analysis and Mathematical Modeling, Ghent University, Coupure Links 653, Ghent 9000, Belgium"],"raw_orcid":"https://orcid.org/0009-0004-9898-4833","affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Mathematical Modeling, Ghent University, Coupure Links 653, Ghent 9000, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028945060","display_name":"Willem Waegeman","orcid":"https://orcid.org/0000-0002-5950-3003"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Willem Waegeman","raw_affiliation_strings":["Department of Data Analysis and Mathematical Modeling, Ghent University, Coupure Links 653, Ghent 9000, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-5950-3003","affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Mathematical Modeling, Ghent University, Coupure Links 653, Ghent 9000, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028945060"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60442894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"10","first_page":"5788","last_page":"5800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12748","display_name":"Molecular spectroscopy and chirality","score":0.14830000698566437,"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"}},"topics":[{"id":"https://openalex.org/T12748","display_name":"Molecular spectroscopy and chirality","score":0.14830000698566437,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.09769999980926514,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.08789999783039093,"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/conformal-map","display_name":"Conformal map","score":0.49720001220703125},{"id":"https://openalex.org/keywords/mass-spectrum","display_name":"Mass spectrum","score":0.4268999993801117},{"id":"https://openalex.org/keywords/spectral-line","display_name":"Spectral line","score":0.4180000126361847},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34850001335144043}],"concepts":[{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.4932999908924103},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.4268999993801117},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C30475298","wikidata":"https://www.wikidata.org/wiki/Q909554","display_name":"Computational physics","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3407000005245209},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.30239999294281006},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.25429999828338623}],"mesh":[{"descriptor_ui":"D000097922","descriptor_name":"Liquid Chromatography-Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000097922","descriptor_name":"Liquid Chromatography-Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008968","descriptor_name":"Molecular Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008968","descriptor_name":"Molecular Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.6c00727","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6c00727","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:42113637","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42113637","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1499689786","https://openalex.org/W2151697120","https://openalex.org/W2179948434","https://openalex.org/W2514278201","https://openalex.org/W2594573597","https://openalex.org/W2922522932","https://openalex.org/W3167215506","https://openalex.org/W4235145261","https://openalex.org/W4281688302","https://openalex.org/W4295016733","https://openalex.org/W4361012985","https://openalex.org/W4380490520","https://openalex.org/W4381615239","https://openalex.org/W4382239193","https://openalex.org/W4385955529","https://openalex.org/W4391993349","https://openalex.org/W4392383780","https://openalex.org/W4396547507","https://openalex.org/W4400176958","https://openalex.org/W4404346391","https://openalex.org/W4404576493","https://openalex.org/W4407274812","https://openalex.org/W4408178946","https://openalex.org/W4410621552","https://openalex.org/W4411708403","https://openalex.org/W4413506311","https://openalex.org/W4417023081","https://openalex.org/W4417163219","https://openalex.org/W6903460679","https://openalex.org/W7083172238","https://openalex.org/W7133231721"],"related_works":[],"abstract_inverted_index":{"A":[0,23],"key":[1],"task":[2],"in":[3],"the":[4,16,49,77,104,117,161],"computational":[5],"analysis":[6],"of":[7,157],"liquid":[8],"chromatography\u2013tandem":[9],"mass":[10],"spectrometry":[11],"(LC\u2013MS/MS)":[12],"data":[13,50,111],"is":[14],"identifying":[15],"molecular":[17,68],"structure":[18],"underlying":[19],"a":[20,81],"measured":[21],"spectrum.":[22],"common":[24],"approach":[25],"ranks":[26],"candidate":[27,122,172,177],"molecules":[28],"retrieved":[29],"from":[30],"chemical":[31],"databases":[32],"using":[33,165],"predicted":[34],"fingerprint":[35],"similarities,":[36],"yet":[37],"standard":[38],"metrics":[39],"such":[40],"as":[41,134],"top-":[42],"k":[43],"accuracy":[44],"summarize":[45],"performance":[46],"only":[47],"at":[48],"set":[51],"level":[52],"and":[53,87,99,109],"provide":[54],"no":[55],"spectrum-specific":[56,72,176],"reliability":[57,154],"statement.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"apply":[63],"conformal":[64,89,114,150,169],"prediction":[65,73,90,115,130,151,170],"to":[66,70],"candidate-based":[67],"retrieval":[69],"construct":[71],"sets":[74,123,131,178],"that":[75],"contain":[76],"true":[78],"molecule":[79],"with":[80,120,160,179],"user-specified":[82],"probability.":[83],"We":[84],"evaluate":[85],"marginal":[86],"conditional":[88],"across":[91,155],"three":[92],"experimental":[93],"scenarios":[94],"representing":[95],"in-distribution,":[96],"partially":[97],"shifted,":[98],"fully":[100],"out-of-distribution":[101],"settings":[102],"on":[103],"MassSpecGym":[105],"benchmark.":[106],"When":[107],"calibration":[108,146],"test":[110],"are":[112],"aligned,":[113],"attains":[116],"target":[118],"coverage":[119],"small":[121],"for":[124],"most":[125],"spectra.":[126],"Under":[127],"distribution":[128],"shift,":[129],"become":[132],"larger":[133],"rankings":[135,173],"grow":[136],"more":[137],"ambiguous,":[138],"although":[139],"candidates":[140],"can":[141],"still":[142],"be":[143],"reduced":[144],"when":[145],"remains":[147],"representative.":[148],"Conditional":[149],"improves":[152],"subgroup":[153],"spectra":[156],"different":[158],"difficulty,":[159],"best":[162],"gains":[163],"obtained":[164],"confidence-based":[166],"grouping.":[167],"Overall,":[168],"turns":[171],"into":[174],"reliable,":[175],"an":[180],"explicit":[181],"reliability\u2013efficiency":[182],"trade-off.":[183]},"counts_by_year":[],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2026-05-12T00:00:00"}