{"id":"https://openalex.org/W7224867775","doi":"https://doi.org/10.48550/arxiv.2610.40264","title":"From MS/MS evidence to adaptive spectroscopic characterization: Reinforcement learning guided by candidate molecular structures","display_name":"From MS/MS evidence to adaptive spectroscopic characterization: Reinforcement learning guided by candidate molecular structures","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224867775","doi":"https://doi.org/10.48550/arxiv.2610.40264"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.40264","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40264","pdf_url":"https://arxiv.org/pdf/2610.40264","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.40264","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151864572","display_name":"Bowen Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Bowen","raw_affiliation_strings":["State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China","University of Chinese Academy of Sciences , Beijing 100049 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing 100049 , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160217173","display_name":"Lei Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Lei","raw_affiliation_strings":["State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148861396","display_name":"Yiying Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yiying","raw_affiliation_strings":["State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160236190","display_name":"Wenjie Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Wenjie","raw_affiliation_strings":["State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Materials for Integrated Circuits , Shanghai Institute of Microsystem and Information Technology , Chinese Academy of Sciences , Shanghai 200050 , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9340999722480774,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9340999722480774,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.018200000748038292,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.017899999395012856,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"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/small-molecule-identification","display_name":"small molecule identification","score":0.875},{"id":"https://openalex.org/keywords/tandem-mass-spectrometry","display_name":"tandem mass spectrometry","score":0.9769999980926514},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7149999737739563},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.9869999885559082},{"id":"https://openalex.org/keywords/infrared-spectroscopy","display_name":"infrared spectroscopy","score":0.7039999961853027},{"id":"https://openalex.org/keywords/nmr-spectroscopy","display_name":"NMR spectroscopy","score":0.9319999814033508},{"id":"https://openalex.org/keywords/acquisition-cost","display_name":"acquisition cost","score":0.640999972820282},{"id":"https://openalex.org/keywords/syntactic-ambiguity","display_name":"syntactic ambiguity","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5525000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5242999792098999},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C2780841128","wikidata":"https://www.wikidata.org/wiki/Q5073781","display_name":"Characterization (materials science)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.40264","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40264","pdf_url":"https://arxiv.org/pdf/2610.40264","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.40264","doi":"https://doi.org/10.48550/arxiv.2610.40264","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.40264","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.40264","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40264","pdf_url":"https://arxiv.org/pdf/2610.40264","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325413","display_name":"Shanghai Municipal Commission of Economy and Informatization","ror":"https://ror.org/04166ws88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224867775.pdf","grobid_xml":"https://content.openalex.org/works/W7224867775.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1995875735","https://openalex.org/W2051366884","https://openalex.org/W2084007633","https://openalex.org/W2112688502","https://openalex.org/W2145339207","https://openalex.org/W2179948434","https://openalex.org/W2744786961","https://openalex.org/W2746553466","https://openalex.org/W2911087563","https://openalex.org/W2964152520","https://openalex.org/W3082460181","https://openalex.org/W3164367030","https://openalex.org/W3194841450","https://openalex.org/W3212396168","https://openalex.org/W4281695360","https://openalex.org/W4323074645","https://openalex.org/W4378781285","https://openalex.org/W4392566291","https://openalex.org/W4404319083","https://openalex.org/W4404435697","https://openalex.org/W4415795335","https://openalex.org/W4416721757","https://openalex.org/W7130517856","https://openalex.org/W7213250156"],"related_works":["https://openalex.org/W3158187537","https://openalex.org/W7129100187","https://openalex.org/W4383613927","https://openalex.org/W7171534744","https://openalex.org/W3209680996","https://openalex.org/W7213250156","https://openalex.org/W4381512387","https://openalex.org/W3156075822","https://openalex.org/W4410930145","https://openalex.org/W7125792582"],"abstract_inverted_index":{"Small-molecule":[0],"identification":[1,243],"from":[2,77,106,115],"tandem":[3],"mass":[4],"spectrometry":[5],"(MS/MS)":[6],"may":[7],"require":[8],"complementary":[9],"measurements.":[10],"Herein,":[11],"we":[12],"propose":[13],"a":[14,157,238],"structure-informed":[15],"deep":[16],"Q-network":[17],"(SI-DQN)":[18],"that":[19],"uses":[20],"existing":[21],"MS/MS":[22,112,231],"evidence":[23],"to":[24,33,37,108,117,156,179,201,233],"decide":[25],"whether":[26],"further":[27,181,235],"characterization":[28],"is":[29],"needed,":[30],"which":[31],"measurement":[32,126,149,247],"request,":[34],"and":[35,44,55,71,92,114,131,153,169,174],"when":[36],"stop.":[38],"The":[39,58,122],"policy":[40,59],"combines":[41],"spectral":[42],"representations":[43],"candidate":[45,86,228],"rankings":[46],"with":[47,66,141,207],"score-weighted":[48],"descriptors":[49],"of":[50],"the":[51,78,89,147,162,225],"candidates'":[52],"chemical":[53],"features":[54],"structural":[56,177,209],"differences.":[57],"was":[60],"evaluated":[61],"on":[62],"79,462":[63],"held-out":[64],"samples":[65],"simulated":[67],"MS/MS,":[68],"infrared":[69],"(IR),":[70],"nuclear":[72],"magnetic":[73],"resonance":[74],"(NMR)":[75],"spectra":[76],"Multimodal":[79],"Spectroscopic":[80],"Dataset.":[81],"Evaluation":[82],"used":[83],"fixed":[84],"hard":[85],"sets":[87],"containing":[88],"correct":[90],"structure":[91],"equal":[93],"normalized":[94],"acquisition":[95,137,170],"costs.":[96],"Averaged":[97],"across":[98,187],"three":[99,189],"training":[100,190],"runs,":[101],"SI-DQN":[102,145,160,196],"increased":[103,197],"Top-1":[104],"accuracy":[105,140,183],"80.10%":[107],"93.78%":[109],"for":[110,119,241],"positive-ion":[111],"starts":[113],"70.44%":[116],"93.31%":[118],"negative-ion":[120],"starts.":[121],"corresponding":[123],"mean":[124],"additional":[125,148],"counts":[127],"were":[128,217],"only":[129],"0.227":[130],"0.340":[132],"per":[133],"sample,":[134],"respectively.":[135],"Complete":[136],"achieved":[138],"97.72%":[139],"four":[142],"additions,":[143],"whereas":[144],"reduced":[146,161],"count":[150],"by":[151,172],"94.3%":[152],"91.5%.":[154],"Relative":[155],"rule-based":[158],"policy,":[159],"composite":[163,215],"loss":[164,216],"combining":[165],"terminal":[166],"ranking":[167,194],"error":[168],"cost":[171],"19.3%":[173],"25.5%.":[175],"Adding":[176],"information":[178],"DQN":[180,202],"improved":[182],"while":[184],"reducing":[185],"requests":[186],"all":[188],"runs.":[191],"At":[192],"comparable":[193],"uncertainty,":[195],"request":[198],"rates":[199],"relative":[200],"more":[203],"strongly":[204],"in":[205,214],"groups":[206],"high":[208],"disagreement,":[210],"where":[211],"larger":[212],"reductions":[213],"also":[218],"observed.":[219],"Together,":[220],"these":[221],"results":[222],"support":[223],"using":[224],"ambiguity":[226],"among":[227],"structures":[229],"after":[230],"analysis":[232],"guide":[234],"characterization,":[236],"providing":[237],"quantitative":[239],"basis":[240],"balancing":[242],"performance":[244],"against":[245],"subsequent":[246],"effort.":[248]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-31T00:00:00"}