{"id":"https://openalex.org/W7213890203","doi":"https://doi.org/10.5281/zenodo.22854373","title":"Fragment-Grounded Neural Simulation of Electron Ionization Mass Spectra at Library Scale \u2013 Supplementary Data","display_name":"Fragment-Grounded Neural Simulation of Electron Ionization Mass Spectra at Library Scale \u2013 Supplementary Data","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7213890203","doi":"https://doi.org/10.5281/zenodo.22854373"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22854373","doi":"https://doi.org/10.5281/zenodo.22854373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22854373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22854373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114987474","display_name":"Magdalena Lederbauer","orcid":"https://orcid.org/0009-0008-0665-1839","observed_orcids":["https://orcid.org/0009-0008-0665-1839"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lederbauer, Magdalena","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":"https://orcid.org/0009-0008-0665-1839","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069477050","display_name":"Runzhong Wang","orcid":"https://orcid.org/0000-0002-9566-738X","observed_orcids":["https://orcid.org/0000-0002-9566-738X"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Runzhong","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-9566-738X","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076162644","display_name":"Connor W. Coley","orcid":"https://orcid.org/0000-0002-8271-8723","observed_orcids":["https://orcid.org/0000-0002-8271-8723"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Coley, Connor","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-8271-8723","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.9448000192642212,"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":0.9448000192642212,"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":0.02239999920129776,"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":0.015699999406933784,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/electron-ionization-mass-spectra","display_name":"electron ionization mass spectra","score":0.8840000033378601},{"id":"https://openalex.org/keywords/gc-ei-ms","display_name":"GC-EI-MS","score":0.7409999966621399},{"id":"https://openalex.org/keywords/icicles","display_name":"icicles","score":0.8240000009536743},{"id":"https://openalex.org/keywords/pubchem","display_name":"PubChem","score":0.6420000195503235},{"id":"https://openalex.org/keywords/spectral-library-search","display_name":"spectral library search","score":0.9079999923706055}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.7858999967575073},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7114999890327454},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4196999967098236},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.41190001368522644},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C2778861254","wikidata":"https://www.wikidata.org/wiki/Q912034","display_name":"Spectrograph","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.32850000262260437},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C30475298","wikidata":"https://www.wikidata.org/wiki/Q909554","display_name":"Computational physics","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C198291218","wikidata":"https://www.wikidata.org/wiki/Q190382","display_name":"Ionization","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C2779265950","wikidata":"https://www.wikidata.org/wiki/Q22906137","display_name":"Absolute scale","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C124967146","wikidata":"https://www.wikidata.org/wiki/Q3457898","display_name":"Spectral resolution","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22854373","doi":"https://doi.org/10.5281/zenodo.22854373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22854373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22854374","doi":"https://doi.org/10.5281/zenodo.22854374","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22854374","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22854373","doi":"https://doi.org/10.5281/zenodo.22854373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22854373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204924000","https://openalex.org/W4328030928","https://openalex.org/W6968740279","https://openalex.org/W6931370203","https://openalex.org/W6949863996","https://openalex.org/W2462785116","https://openalex.org/W3094318061","https://openalex.org/W4394105374","https://openalex.org/W4317938055","https://openalex.org/W2921388451"],"abstract_inverted_index":{"Predicted":[0],"electron-ionization":[1],"mass":[2,60],"spectra":[3],"(GC-EI-MS)":[4],"for":[5,50,82],"87,260,988":[6],"molecules":[7],"from":[8],"a":[9,39],"filtered":[10],"PubChem":[11,85],"library,":[12],"generated":[13],"with":[14],"ICICLE":[15],"(fragment-grounded":[16],"neural":[17],"EI-MS":[18],"simulator;":[19],"model":[20],"trained":[21],"on":[22],"the":[23,76,83],"NIST":[24],"2023":[25],"GC-MS":[26],"random":[27],"split).":[28],"Each":[29],"entry":[30],"includes":[31],"canonical":[32],"SMILES,":[33],"InChIKey-14,":[34],"nominal":[35],"molecular":[36],"weight,":[37],"and":[38,88],"predicted":[40],"spectrum":[41],"binned":[42],"at":[43],"1":[44],"Da":[45],"resolution":[46],"(0\u2013750":[47],"m/z).":[48],"Intended":[49],"large-scale":[51],"spectral":[52],"library":[53],"search":[54],"/":[55],"retrieval":[56],"benchmarking":[57],"in":[58,72],"small-molecule":[59],"spectrometry.":[61],"Data":[62],"is":[63],"split":[64],"into":[65],"10":[66],"row-range":[67],"HDF5":[68],"parts":[69],"(part00\u2013part09);":[70],"concatenate":[71],"order":[73],"to":[74],"reconstruct":[75],"full":[77],"dataset.":[78],"See":[79],"accompanying":[80],"README":[81],"exact":[84],"filtering":[86],"funnel":[87],"provenance.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-22T00:00:00"}
