{"id":"https://openalex.org/W7224021174","doi":"https://doi.org/10.26434/chemrxiv.15011102/v1","title":"Direct molecular formula prediction from tandem mass spectra with a multi-task-trained encoder and deterministic stoichiometric correction","display_name":"Direct molecular formula prediction from tandem mass spectra with a multi-task-trained encoder and deterministic stoichiometric correction","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224021174","doi":"https://doi.org/10.26434/chemrxiv.15011102/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15011102/v1","doi":"https://doi.org/10.26434/chemrxiv.15011102/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011102/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011102/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011102/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159896860","display_name":"Shang Zhang","orcid":"https://orcid.org/0009-0000-8177-2886","observed_orcids":["https://orcid.org/0009-0000-8177-2886"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang Zhang","raw_affiliation_strings":["MoloGPI"],"raw_orcid":"https://orcid.org/0009-0000-8177-2886","affiliations":[{"raw_affiliation_string":"MoloGPI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018222199","display_name":"Zhenlin Dong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenlin Dong","raw_affiliation_strings":["Dalian Customs District Technology Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Customs District Technology Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033621287","display_name":"Ming Yu Gao","orcid":"https://orcid.org/0000-0002-8502-1155","observed_orcids":["https://orcid.org/0000-0002-8502-1155"]},"institutions":[{"id":"https://openalex.org/I130480701","display_name":"Dongbei University of Finance and Economics","ror":"https://ror.org/05db1pj03","country_code":"CN","type":"education","lineage":["https://openalex.org/I130480701"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Gao","raw_affiliation_strings":["Dongbei University of Finance and Economics"],"raw_orcid":"https://orcid.org/0000-0002-8502-1155","affiliations":[{"raw_affiliation_string":"Dongbei University of Finance and Economics","institution_ids":["https://openalex.org/I130480701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.5717999935150146,"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":0.5717999935150146,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.4025999903678894,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.006300000008195639,"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/tandem-mass-spectra","display_name":"tandem mass spectra","score":0.9419999718666077},{"id":"https://openalex.org/keywords/mass-conservation","display_name":"mass conservation","score":0.6779999732971191},{"id":"https://openalex.org/keywords/metabolite-identification","display_name":"metabolite identification","score":0.7549999952316284},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6320000290870667},{"id":"https://openalex.org/keywords/fourier-features","display_name":"Fourier features","score":0.5630000233650208}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6182000041007996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6039000153541565},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.4156999886035919},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3569999933242798},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C144082473","wikidata":"https://www.wikidata.org/wiki/Q213185","display_name":"Stoichiometry","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2815999984741211},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15011102/v1","doi":"https://doi.org/10.26434/chemrxiv.15011102/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011102/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011102/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15011102/v1","doi":"https://doi.org/10.26434/chemrxiv.15011102/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011102/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011102/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224021174.pdf","grobid_xml":"https://content.openalex.org/works/W7224021174.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2065104255","https://openalex.org/W2127360645","https://openalex.org/W2179948434","https://openalex.org/W2901476322","https://openalex.org/W2922522932","https://openalex.org/W3016970897","https://openalex.org/W3094361883","https://openalex.org/W3163993681","https://openalex.org/W4284961832","https://openalex.org/W4365450264","https://openalex.org/W4386863955","https://openalex.org/W4402926919","https://openalex.org/W4404346391","https://openalex.org/W4410621552","https://openalex.org/W4410966262","https://openalex.org/W4417272637","https://openalex.org/W7125651593","https://openalex.org/W7131874278","https://openalex.org/W7160535779","https://openalex.org/W7164398792","https://openalex.org/W7164831878"],"related_works":["https://openalex.org/W4386863955","https://openalex.org/W4417272637","https://openalex.org/W2005127231","https://openalex.org/W7102403334","https://openalex.org/W4318620627","https://openalex.org/W3213127212","https://openalex.org/W7133221075","https://openalex.org/W2312480201","https://openalex.org/W7167630757","https://openalex.org/W4286859046"],"abstract_inverted_index":{"Molecular":[0],"formula":[1,58],"assignment":[2],"is":[3,76,95,154,173],"the":[4,60,68,93,110,126,143,170,212],"first":[5],"step":[6],"of":[7,82],"metabolite":[8],"identification":[9],"from":[10,105],"tandem":[11],"mass":[12,37,62,184],"spectra,":[13],"yet":[14],"deep-learning":[15],"methods":[16],"have":[17],"repeatedly":[18],"underperformed":[19],"classical":[20],"enumeration,":[21],"reaching":[22],"usable":[23],"accuracy":[24,193],"only":[25],"through":[26],"candidate":[27,70],"generation":[28],"and":[29,45,88,92,123,135],"learned":[30],"reranking.":[31],"Here":[32],"we":[33],"present":[34],"MStoic,":[35],"a":[36,49,56,147,155,187],"spectrum":[38],"encoder":[39,94],"that":[40,54,151,159,169,198],"predicts":[41],"molecular":[42],"formulas":[43,178],"directly":[44],"finalizes":[46],"them":[47],"with":[48,97,179],"deterministic,":[50],"zero-parameter":[51],"stoichiometric":[52],"correction":[53,145,153],"selects":[55],"mass-consistent":[57],"against":[59],"precursor":[61],"(20":[63],"ppm;":[64],"falling":[65],"back":[66],"to":[67,146],"closest-mass":[69],"when":[71],"none":[72],"qualifies).":[73],"Every":[74],"peak":[75],"embedded":[77],"by":[78],"soft":[79,188],"Gaussian":[80],"binning":[81],"log(m/z),":[83],"Fourier":[84],"features,":[85],"pairwise-difference":[86],"embeddings":[87],"an":[89],"intensity":[90],"embedding,":[91],"trained":[96],"chemically":[98],"grounded":[99],"auxiliary":[100],"tasks,":[101],"including":[102],"fragment-level":[103],"supervision":[104],"computational":[106],"fragmentation":[107],"trees.":[108],"On":[109],"multi-source":[111],"Spectraverse":[112],"benchmark":[113,140],"(48,622":[114],"held-out":[115],"spectra)":[116],"MStoic":[117],"achieves":[118],"77.8%":[119],"top-1":[120],"exact-match":[121],"accuracy,":[122],"79.6%":[124],"on":[125,138],"CASMI-2022":[127],"challenge,":[128],"matching":[129],"or":[130],"exceeding":[131],"specialized":[132],"deep-learning,":[133],"candidate-ranking,":[134],"rule-based":[136],"baselines":[137],"every":[139],"evaluated.":[141],"Applying":[142],"same":[144],"competing":[148],"model":[149,164],"shows":[150,168],"mass-based":[152],"portable":[156],"physical":[157,199],"prior":[158],"amplifies":[160],"rather":[161,209],"than":[162,195,210],"substitutes":[163],"capability.":[165],"Factorial":[166],"ablation":[167],"hybrid":[171],"encoding":[172],"selectively":[174],"beneficial":[175],"for":[176],"rare-element-bearing":[177],"information-dense":[180],"spectra.":[181],"And":[182],"imposing":[183],"conservation":[185],"as":[186],"training":[189,213],"loss":[190],"reduces":[191],"direct":[192],"more":[194],"seven-fold,":[196],"indicating":[197],"constraints":[200],"in":[201,206,211],"discrete":[202],"chemical":[203],"spaces":[204],"belong":[205],"hard":[207],"post-processing":[208],"objective.":[214]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-28T00:00:00"}