{"id":"https://openalex.org/W4381334298","doi":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","title":"MS2Mol: A transformer model for illuminating dark chemical space from mass spectra","display_name":"MS2Mol: A transformer model for illuminating dark chemical space from mass spectra","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381334298","doi":"https://doi.org/10.26434/chemrxiv-2023-vsmpx"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv-2023-vsmpx","doi":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/648dead54f8b1884b77082da/original/ms2mol-a-transformer-model-for-illuminating-dark-chemical-space-from-mass-spectra.pdf","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/engage/api-gateway/chemrxiv/assets/orp/resource/item/648dead54f8b1884b77082da/original/ms2mol-a-transformer-model-for-illuminating-dark-chemical-space-from-mass-spectra.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113907792","display_name":"Thomas Butler","orcid":"https://orcid.org/0000-0003-2863-0808","observed_orcids":["https://orcid.org/0000-0003-2863-0808"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Butler","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025383494","display_name":"Abraham Frandsen","orcid":"https://orcid.org/0000-0002-4891-2362","observed_orcids":["https://orcid.org/0000-0002-4891-2362"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abraham Frandsen","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052891524","display_name":"Rose Lightheart","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rose Lightheart","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065833710","display_name":"Brian Bargh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Bargh","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092224798","display_name":"TJ Bollerman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"TJ Bollerman","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Kerby","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Kerby","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066236566","display_name":"Kiana West","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiana West","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018318324","display_name":"Gennady Voronov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gennady Voronov","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kevin Moon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Moon","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030581253","display_name":"Tobias Kind","orcid":"https://orcid.org/0000-0002-1908-4916","observed_orcids":["https://orcid.org/0000-0002-1908-4916"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Kind","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082720301","display_name":"Pieter C. Dorrestein","orcid":"https://orcid.org/0000-0002-3003-1030","observed_orcids":["https://orcid.org/0000-0002-3003-1030"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Dorrestein","raw_affiliation_strings":["Enveda Biosciences","University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015485079","display_name":"August Allen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"August Allen","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003250302","display_name":"Viswa Colluru","orcid":"https://orcid.org/0000-0002-6208-9288","observed_orcids":["https://orcid.org/0000-0002-6208-9288"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viswa Colluru","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089107006","display_name":"David Healey","orcid":"https://orcid.org/0000-0002-9584-9757","observed_orcids":["https://orcid.org/0000-0002-9584-9757"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Healey","raw_affiliation_strings":["Enveda Biosciences"],"raw_orcid":"https://orcid.org/0000-0002-9584-9757","affiliations":[{"raw_affiliation_string":"Enveda Biosciences","institution_ids":[]}]}],"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":10,"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":0.6445000171661377,"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":0.6445000171661377,"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":0.2142000049352646,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.1160999983549118,"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/de-novo-structure-prediction","display_name":"de novo structure prediction","score":0.7329999804496765},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"mass spectrometry","score":0.7910000085830688},{"id":"https://openalex.org/keywords/natural-products","display_name":"natural products","score":0.6880000233650208},{"id":"https://openalex.org/keywords/unknown-metabolites","display_name":"unknown metabolites","score":0.7179999947547913},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.5},{"id":"https://openalex.org/keywords/sequence-to-sequence-models","display_name":"sequence-to-sequence models","score":0.6549999713897705},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5830000042915344},{"id":"https://openalex.org/keywords/confidence-scores","display_name":"confidence scores","score":0.7289999723434448},{"id":"https://openalex.org/keywords/molecular-structure-elucidation","display_name":"chemical structure elucidation","score":0.6539999842643738}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.8555580377578735},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6385588645935059},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6062976717948914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5353897213935852},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46784743666648865},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4449373483657837},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.4425103962421417},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.44228291511535645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42670485377311707},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3329177796840668},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.26703059673309326},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.24756169319152832},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2287600040435791},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22065207362174988},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15056383609771729},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv-2023-vsmpx","doi":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/648dead54f8b1884b77082da/original/ms2mol-a-transformer-model-for-illuminating-dark-chemical-space-from-mass-spectra.pdf","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-2023-vsmpx","doi":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2023-vsmpx","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/648dead54f8b1884b77082da/original/ms2mol-a-transformer-model-for-illuminating-dark-chemical-space-from-mass-spectra.pdf","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":[],"sustainable_development_goals_aurora":[{"display_name":"Life on land","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/15"},{"display_name":"Responsible consumption and production","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/12"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381334298.pdf","grobid_xml":"https://content.openalex.org/works/W4381334298.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1678356000","https://openalex.org/W1816313093","https://openalex.org/W1975147762","https://openalex.org/W1997386061","https://openalex.org/W2015503332","https://openalex.org/W2016589492","https://openalex.org/W2034549041","https://openalex.org/W2059327215","https://openalex.org/W2066273100","https://openalex.org/W2069870183","https://openalex.org/W2070072705","https://openalex.org/W2097998348","https://openalex.org/W2114688451","https://openalex.org/W2125069590","https://openalex.org/W2160592148","https://openalex.org/W2177317049","https://openalex.org/W2179948434","https://openalex.org/W2504691963","https://openalex.org/W2551876238","https://openalex.org/W2769423117","https://openalex.org/W2883265831","https://openalex.org/W2895677720","https://openalex.org/W2962784628","https://openalex.org/W2979826702","https://openalex.org/W2980282514","https://openalex.org/W2982399380","https://openalex.org/W3081878206","https://openalex.org/W3094640617","https://openalex.org/W3118695441","https://openalex.org/W3119952098","https://openalex.org/W3129424480","https://openalex.org/W3139516621","https://openalex.org/W3170291525","https://openalex.org/W3194841450","https://openalex.org/W3201481795","https://openalex.org/W3206742358","https://openalex.org/W3206878019","https://openalex.org/W3209680996","https://openalex.org/W3216027541","https://openalex.org/W3217248762","https://openalex.org/W4229590462","https://openalex.org/W4281658583","https://openalex.org/W4281688302","https://openalex.org/W4284961832","https://openalex.org/W4299416872","https://openalex.org/W4304092658","https://openalex.org/W4318620627","https://openalex.org/W4381804451","https://openalex.org/W4385245566","https://openalex.org/W4385955529","https://openalex.org/W4391772345","https://openalex.org/W7133221075"],"related_works":["https://openalex.org/W2973074952","https://openalex.org/W2594328795","https://openalex.org/W2006607885","https://openalex.org/W3183930479","https://openalex.org/W135095951","https://openalex.org/W4320732452","https://openalex.org/W3199987505","https://openalex.org/W4385760073","https://openalex.org/W4286980196","https://openalex.org/W2600435468"],"abstract_inverted_index":{"The":[0],"ability":[1,24],"to":[2,22,51,73,117,158,164,172,214],"identify":[3],"small":[4],"molecules":[5,55],"in":[6,59,145],"complex":[7],"samples":[8],"from":[9,138],"their":[10],"mass":[11,136],"spectra":[12,63,137],"is":[13,43,156],"among":[14],"the":[15,75,92,183,207,220],"grand":[16],"challenges":[17],"of":[18,61,78,81,94,161,177],"analytical":[19],"chemistry.":[20],"Improvements":[21],"this":[23,98,151],"could":[25],"significantly":[26],"advance":[27],"fields":[28],"as":[29,31],"diverse":[30],"drug":[32],"discovery,":[33],"diagnostics,":[34],"environmental":[35],"science,":[36],"and":[37,67,170,205,211,216],"synthetic":[38],"biology.":[39],"A":[40],"primary":[41],"bottleneck":[42],"that":[44,56,154,197],"standard":[45,188],"structure":[46,109],"elucidation":[47],"technologies":[48],"are":[49,57,68,86,179],"limited":[50],"identifying":[52,74],"only":[53],"those":[54],"contained":[58],"databases":[60],"known":[62],"or":[64],"molecular":[65,95,162],"structures":[66,85,96,163],"therefore":[69],"not":[70,87,142],"well":[71],"suited":[72],"vast":[76,99],"majority":[77],"potentially":[79],"billions":[80],"natural":[82,140],"metabolites,":[83],"whose":[84],"yet":[88],"catalogued.":[89],"To":[90],"improve":[91],"identification":[93,128],"within":[97,165,173],"dark":[100],"chemical":[101],"space,":[102],"we":[103],"present":[104,193],"MS2Mol,":[105],"a":[106,114,124,166,194],"\\textit{de":[107],"novo}":[108],"prediction":[110],"model":[111],"based":[112],"on":[113,130,150,209],"generative":[115],"sequence":[116,118],"transformer.":[119],"We":[120,148,191],"also":[121],"release":[122],"EnvedaDark,":[123],"first-of-its-kind":[125],"for":[126,201,219],"benchmarking":[127],"performance":[129],"unknown":[131],"metabolites.":[132],"EnvedaDark":[133],"contains":[134],"experimental":[135],"226":[139],"products":[141],"currently":[143],"found":[144],"major":[146],"databases.":[147],"demonstrate":[149],"challenging":[152],"dataset":[153],"MS2Mol":[155],"able":[157],"predict":[159],"21\\%":[160],"close-match":[167,212],"accuracy":[168,208],"threshold":[169],"62\\%":[171],"meaningful":[174],"similarity,":[175],"both":[176],"which":[178],"significant":[180],"improvements":[181],"over":[182],"closest":[184],"match":[185],"retrieved":[186],"using":[187],"database":[189],"methods.":[190],"further":[192],"confidence":[195],"scorer":[196],"enables":[198],"practical":[199],"usage":[200],"novel":[202],"molecule":[203],"discovery":[204],"enriches":[206],"meaningfully-similar":[210],"thresholds":[213],"98\\%":[215],"63\\%,":[217],"respectively,":[218],"top":[221],"10\\%":[222],"most":[223],"confident":[224],"predictions.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
