{"id":"https://openalex.org/W4412421069","doi":"https://doi.org/10.1016/j.chroma.2025.466216","title":"MASSISTANT: A deep learning model for De Novo molecular structure prediction from EI\u2011MS spectra via SELFIES encoding","display_name":"MASSISTANT: A deep learning model for De Novo molecular structure prediction from EI\u2011MS spectra via SELFIES encoding","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W4412421069","doi":"https://doi.org/10.1016/j.chroma.2025.466216","pmid":"https://pubmed.ncbi.nlm.nih.gov/40706264"},"language":"en","primary_location":{"id":"doi:10.1016/j.chroma.2025.466216","doi":"https://doi.org/10.1016/j.chroma.2025.466216","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.chroma.2025.466216","pdf_url":null,"source":{"id":"https://openalex.org/S176136234","display_name":"Journal of Chromatography A","issn_l":"0021-9673","issn":["0021-9673","1873-3778"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chromatography A","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.chroma.2025.466216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036785506","display_name":"John H. M. Mommers","orcid":"https://orcid.org/0000-0001-5583-9477","observed_orcids":["https://orcid.org/0000-0001-5583-9477"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"John Mommers","raw_affiliation_strings":["Envalior, Engineering Materials, Urmonderbaan 22, 6167 RD Geleen, the Netherlands. Electronic address: John.Mommers@envalior.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Envalior, Engineering Materials, Urmonderbaan 22, 6167 RD Geleen, the Netherlands. Electronic address: John.Mommers@envalior.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116701440","display_name":"Lazar Barta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lazar Barta","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, the Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038564154","display_name":"Marcin Pietrasik","orcid":"https://orcid.org/0000-0001-7559-8658","observed_orcids":["https://orcid.org/0000-0001-7559-8658"]},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marcin Pietrasik","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, the Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011946737","display_name":"Anna Wilbik","orcid":"https://orcid.org/0000-0002-1989-0301","observed_orcids":["https://orcid.org/0000-0002-1989-0301"]},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Anna Wilbik","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, 6229 EN Maastricht, the Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036785506"],"corresponding_institution_ids":[],"apc_list":{"value":4040,"currency":"USD","value_usd":4040},"apc_paid":{"value":4040,"currency":"USD","value_usd":4040},"fwci":0.7555,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62192098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1759","issue":null,"first_page":"466216","last_page":"466216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.7285000085830688,"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":0.7285000085830688,"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":0.195700004696846,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.017400000244379044,"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/electron-impact-mass-spectrometry","display_name":"electron impact mass spectrometry","score":0.9549999833106995},{"id":"https://openalex.org/keywords/gc-ei-ms","display_name":"GC-EI-MS","score":0.8970000147819519},{"id":"https://openalex.org/keywords/low-resolution-mass-spectra","display_name":"low resolution mass spectra","score":0.6549999713897705},{"id":"https://openalex.org/keywords/fragmentation-patterns","display_name":"fragmentation patterns","score":0.6159999966621399},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.7590000033378601},{"id":"https://openalex.org/keywords/molecular-structure-elucidation","display_name":"chemical structure elucidation","score":0.5519999861717224}],"concepts":[{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.8900416493415833},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.5043638944625854},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4214039444923401},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008401","descriptor_name":"Gas Chromatography-Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D008970","descriptor_name":"Molecular Weight","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021241","descriptor_name":"Spectrometry, Mass, Electrospray Ionization","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1016/j.chroma.2025.466216","doi":"https://doi.org/10.1016/j.chroma.2025.466216","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.chroma.2025.466216","pdf_url":null,"source":{"id":"https://openalex.org/S176136234","display_name":"Journal of Chromatography A","issn_l":"0021-9673","issn":["0021-9673","1873-3778"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chromatography A","raw_type":"journal-article"},{"id":"doi:10.26434/chemrxiv-2025-qchjl","doi":"https://doi.org/10.26434/chemrxiv-2025-qchjl","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv-2025-qchjl","pdf_url":null,"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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmid:40706264","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40706264","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chromatography. A","raw_type":"Journal Article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:openaire/8d889634-9def-452f-83d3-7c5c0283c29f","doi":null,"is_oa":true,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/8d889634-9def-452f-83d3-7c5c0283c29f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mommers, J, Barta, L, Pietrasik, M & Wilbik, A 2025, 'MASSISTANT : A deep learning model for De Novo molecular structure prediction from EI-MS spectra via SELFIES encoding', Journal of Chromatography A, vol. 1759, 466216. https://doi.org/10.1016/j.chroma.2025.466216","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.chroma.2025.466216","doi":"https://doi.org/10.1016/j.chroma.2025.466216","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.chroma.2025.466216","pdf_url":null,"source":{"id":"https://openalex.org/S176136234","display_name":"Journal of Chromatography A","issn_l":"0021-9673","issn":["0021-9673","1873-3778"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chromatography A","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W595492220","https://openalex.org/W1508604947","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W2042950977","https://openalex.org/W2179948434","https://openalex.org/W2626778328","https://openalex.org/W2777416523","https://openalex.org/W2907492528","https://openalex.org/W2921388451","https://openalex.org/W2922522932","https://openalex.org/W2946965984","https://openalex.org/W3009321976","https://openalex.org/W3036061391","https://openalex.org/W3045928028","https://openalex.org/W3126198598","https://openalex.org/W4300907493","https://openalex.org/W4303423760","https://openalex.org/W4310895557","https://openalex.org/W4317938055","https://openalex.org/W4320728073","https://openalex.org/W4320857994","https://openalex.org/W4361989906","https://openalex.org/W4381804451","https://openalex.org/W4383613927","https://openalex.org/W4407310549","https://openalex.org/W6854557166"],"related_works":["https://openalex.org/W3036061391","https://openalex.org/W4362655656","https://openalex.org/W7128018130","https://openalex.org/W7220432906","https://openalex.org/W4407310549","https://openalex.org/W4317938055","https://openalex.org/W4213347734","https://openalex.org/W7129100187","https://openalex.org/W7112423255","https://openalex.org/W7204211576"],"abstract_inverted_index":{"Gas":[0],"chromatography":[1],"coupled":[2],"with":[3,99],"electron":[4],"impact":[5],"mass":[6,166],"spectrometry":[7,167],"(GC\u2011EI\u2011MS)":[8],"is":[9,35,56,107],"a":[10,77,127,169],"widely":[11],"used":[12],"analytical":[13],"technique":[14],"for":[15],"identifying":[16],"volatile":[17],"and":[18,58,160,176,185],"semi\u2011volatile":[19],"compounds":[20,98],"in":[21,37,188],"applications":[22],"ranging":[23],"from":[24,49,89],"pharmaceutical":[25],"research":[26],"to":[27,43,66,109,136,155,172],"material":[28],"science.":[29],"However,":[30],"since":[31],"not":[32],"every":[33],"molecule":[34],"included":[36],"EI\u2011MS":[38,51,91],"databases,":[39],"scientists":[40,168],"often":[41,64],"have":[42],"identify":[44],"unknown":[45],"chromatographic":[46],"peaks":[47],"solely":[48],"their":[50],"spectra.":[52],"This":[53],"manual":[54],"interpretation":[55,175],"time-consuming":[57],"depends":[59],"heavily":[60],"on":[61,97,114],"expert":[62],"knowledge,":[63],"leading":[65],"ambiguous":[67],"or":[68],"inconclusive":[69],"results.":[70],"In":[71],"this":[72,134],"work,":[73],"we":[74],"introduce":[75],"MASSISTANT,":[76],"novel":[78],"deep":[79,152],"learning":[80],"model":[81],"that":[82],"directly":[83],"predicts":[84],"de":[85],"novo":[86],"molecular":[87,100,180],"structures":[88,181],"low\u2011resolution":[90],"spectra":[92],"using":[93],"SELFIES":[94],"encoding.":[95],"Trained":[96],"weights":[101],"below":[102],"600":[103],"Da,":[104],"MASSISTANT's":[105],"performance":[106],"sensitive":[108],"dataset":[110,118],"curation;":[111],"while":[112],"training":[113],"the":[115,149,174],"full":[116],"NIST":[117],"(180k":[119],"spectra)":[120],"yields":[121],"approximately":[122],"10":[123],"%":[124,141],"exact":[125],"predictions,":[126],"more":[128],"focused,":[129],"chemically":[130,162],"homogeneous":[131],"subset":[132],"boosts":[133],"rate":[135],"as":[137,139],"high":[138],"54":[140],"(Tanimoto":[142],"score":[143],"=":[144],"1).":[145],"These":[146],"results":[147],"highlight":[148],"capability":[150],"of":[151,178],"neural":[153],"networks":[154],"capture":[156],"complex":[157],"fragmentation":[158],"patterns":[159],"generate":[161],"valid":[163],"structures,":[164],"offering":[165],"powerful":[170],"tool":[171],"enhance":[173],"elucidation":[177],"whole":[179],"but":[182],"also":[183],"substructures,":[184],"functional":[186],"groups":[187],"GC\u2011EI\u2011MS":[189],"analyses.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2025-10-10T00:00:00"}