{"id":"https://openalex.org/W7138361766","doi":"https://doi.org/10.1609/aaai.v40i2.37074","title":"De Novo Molecular Generation from Mass Spectra via Many-Body Enhanced Diffusion","display_name":"De Novo Molecular Generation from Mass Spectra via Many-Body Enhanced Diffusion","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138361766","doi":"https://doi.org/10.1609/aaai.v40i2.37074"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i2.37074","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37074","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i2.37074","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xichen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xichen Sun","raw_affiliation_strings":["Sun Yat-sen University\nShenzhen Loop Area Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University\nShenzhen Loop Area Institute","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wentao Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Wei","raw_affiliation_strings":["Sun Yat-sen University\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University\nPengcheng Laboratory","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiahua Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahua Rao","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiancong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancong Xie","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuedong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuedong Yang","raw_affiliation_strings":["Sun Yat-sen University\nGuangdong Provincial Key Laboratory of Computational Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University\nGuangdong Provincial Key Laboratory of Computational Science","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"2","first_page":"1042","last_page":"1050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.6955000162124634,"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":0.6955000162124634,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.06129999831318855,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.03830000013113022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.7050999999046326},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.5259000062942505},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"Mass spectrometry","score":0.4916999936103821},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.45879998803138733},{"id":"https://openalex.org/keywords/tandem-mass-spectrometry","display_name":"Tandem mass spectrometry","score":0.4587000012397766},{"id":"https://openalex.org/keywords/cleavage","display_name":"Cleavage (geology)","score":0.34549999237060547},{"id":"https://openalex.org/keywords/mass-spectrum","display_name":"Mass spectrum","score":0.3386000096797943}],"concepts":[{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.7050999999046326},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.5722000002861023},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.4587000012397766},{"id":"https://openalex.org/C159467904","wikidata":"https://www.wikidata.org/wiki/Q2001702","display_name":"Chemical physics","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C175156509","wikidata":"https://www.wikidata.org/wiki/Q1990218","display_name":"Cleavage (geology)","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3206000030040741},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C2989209122","wikidata":"https://www.wikidata.org/wiki/Q178512","display_name":"Mass transport","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C3017610826","wikidata":"https://www.wikidata.org/wiki/Q5755916","display_name":"High mass","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.26179999113082886},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i2.37074","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37074","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i2.37074","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37074","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Molecular":[0],"structure":[1,76,94],"generation":[2,124],"from":[3,96],"mass":[4,18,97,165],"spectrometry":[5,19],"is":[6],"fundamental":[7],"for":[8,43,75,90,128,164],"understanding":[9],"cellular":[10],"metabolism":[11],"and":[12,41,47,57,65,105,125,136,158,171,182,189],"discovering":[13],"novel":[14,129],"compounds.":[15],"Although":[16],"tandem":[17],"(MS/MS)":[20],"enables":[21],"the":[22,35,67,112,134,155],"high-throughput":[23],"acquisition":[24],"of":[25,38,147,161],"fragment":[26],"fingerprints,":[27],"these":[28,80],"spectra":[29],"often":[30],"reflect":[31],"higher-order":[32,62,106,180],"interactions":[33,64,181],"involving":[34],"concerted":[36],"cleavage":[37],"multiple":[39],"atoms":[40],"bonds-crucial":[42],"resolving":[44],"complex":[45,187],"isomers":[46],"non-local":[48,190],"fragmentation":[49,191],"mechanisms.":[50],"However,":[51],"most":[52],"existing":[53],"methods":[54],"adopt":[55],"atom-centric":[56],"pairwise":[58],"interaction":[59],"modeling,":[60,108],"overlooking":[61],"edge":[63,107],"lacking":[66],"capacity":[68],"to":[69,149,186],"systematically":[70],"capture":[71],"essential":[72],"many-body":[73,102,162],"characteristics":[74],"generation.":[77,168],"To":[78],"overcome":[79],"limitations,":[81],"we":[82],"present":[83],"MBGen,":[84],"a":[85,101],"Many-Body":[86],"enhanced":[87,184],"diffusion":[88],"framework":[89],"de":[91,122],"novo":[92,123],"molecular":[93,167],"Generation":[95],"spectra.":[98],"By":[99],"integrating":[100],"attention":[103],"mechanism":[104],"MBGen":[109,141],"comprehensively":[110],"leverages":[111],"rich":[113],"structural":[114],"information":[115],"encoded":[116],"in":[117],"MS/MS":[118],"spectra,":[119],"enabling":[120],"accurate":[121],"isomer":[126],"differentiation":[127],"molecules.":[130],"Experimental":[131],"results":[132],"on":[133],"NPLIB1":[135],"MassSpecGym":[137],"benchmarks":[138],"demonstrate":[139],"that":[140,175],"achieves":[142],"superior":[143],"performance,":[144],"with":[145],"improvements":[146],"up":[148],"230%":[150],"over":[151],"state-of-the-art":[152],"methods,":[153],"highlighting":[154],"scientific":[156],"value":[157],"practical":[159],"utility":[160],"modeling":[163],"spectrometry-based":[166],"Further":[169],"analysis":[170],"ablation":[172],"studies":[173],"show":[174],"our":[176],"approach":[177],"effectively":[178],"captures":[179],"exhibits":[183],"sensitivity":[185],"isomeric":[188],"information.":[192]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-06T00:00:00"}