{"id":"https://openalex.org/W7138143393","doi":"https://doi.org/10.1609/aaai.v40i2.37132","title":"Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra","display_name":"Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138143393","doi":"https://doi.org/10.1609/aaai.v40i2.37132"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i2.37132","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37132","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37132/41094","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37132/41094","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129677557","display_name":"Yiwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Zhang","raw_affiliation_strings":["The Polytechnic Institute, Zhejiang University\nZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Polytechnic Institute, Zhejiang University\nZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129715447","display_name":"Keyan Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyan Ding","raw_affiliation_strings":["ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129707696","display_name":"Yihang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Wu","raw_affiliation_strings":["The Polytechnic Institute, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Polytechnic Institute, Zhejiang University","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129729856","display_name":"Xiang Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Zhuang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693635","display_name":"Yi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662465","display_name":"Qiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158570","display_name":"Zhejiang University-University of Edinburgh Institute","ror":"https://ror.org/04jth1r26","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210158570","https://openalex.org/I76130692","https://openalex.org/I98677209"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["ZJU-UIUC Institute, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-UIUC Institute, Zhejiang University","institution_ids":["https://openalex.org/I4210158570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129706422","display_name":"Huajun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huajun Chen","raw_affiliation_strings":["ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University\nCollege of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University\nCollege of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160","https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.3684,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9815997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"40","issue":"2","first_page":"1561","last_page":"1569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.3698999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.3698999881744385,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.2079000025987625,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.10339999943971634,"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/generative-grammar","display_name":"Generative grammar","score":0.6456999778747559},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5120999813079834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46639999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866999864578247},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6456999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589900016784668},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5120999813079834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47279998660087585},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i2.37132","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37132","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37132/41094","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.v40i2.37132","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37132","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37132/41094","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4217013418674469}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138143393.pdf","grobid_xml":"https://content.openalex.org/works/W7138143393.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieving":[0],"molecular":[1,113,125],"structures":[2],"from":[3,26],"tandem":[4],"mass":[5,21,88,103],"spectra":[6],"is":[7],"a":[8,55,67,74,107],"crucial":[9],"step":[10],"in":[11,42,110,147],"rapid":[12],"compound":[13],"identification.":[14],"Existing":[15],"retrieval":[16,44,93],"methods,":[17,142],"such":[18],"as":[19,82],"traditional":[20],"spectral":[22,28],"library":[23,29],"matching,":[24],"suffer":[25],"limited":[27],"coverage,":[30],"while":[31],"recent":[32],"cross-modal":[33,64],"representation":[34],"learning":[35],"frameworks":[36],"often":[37],"encounter":[38],"modality":[39],"misalignment,":[40],"resulting":[41],"suboptimal":[43],"accuracy":[45,149],"and":[46,131,150],"generalization.":[47],"To":[48],"address":[49],"these":[50,95],"limitations,":[51],"we":[52],"propose":[53],"GLMR,":[54],"Generative":[56],"Language":[57],"Model-based":[58],"Retrieval":[59],"framework":[60],"that":[61,137],"mitigates":[62],"the":[63,71,86,91,101,121,132],"misalignment":[65],"through":[66],"two-stage":[68],"process.":[69],"In":[70,90],"pre-retrieval":[72],"stage,":[73,94],"contrastive":[75],"learning-based":[76],"model":[77,109],"identifies":[78],"top":[79],"candidate":[80,96],"molecules":[81,97],"contextual":[83],"priors":[84],"for":[85],"input":[87,102],"spectrum.":[89],"generative":[92,108],"are":[98,116],"integrated":[99],"with":[100],"spectrum":[104],"to":[105,119],"guide":[106],"producing":[111],"refined":[112],"structures,":[114],"which":[115],"then":[117],"used":[118],"re-rank":[120],"candidates":[122],"based":[123],"on":[124,128],"similarity.":[126],"Experiments":[127],"both":[129],"MassSpecGym":[130],"proposed":[133],"MassRET-20k":[134],"dataset":[135],"demonstrate":[136],"GLMR":[138],"significantly":[139],"outperforms":[140],"existing":[141],"achieving":[143],"over":[144],"40%":[145],"improvement":[146],"top-1":[148],"exhibiting":[151],"strong":[152],"generalizability.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}