{"id":"https://openalex.org/W4406259710","doi":"https://doi.org/10.1109/bibm62325.2024.10822742","title":"How to Train Your Neural Network for Molecular Structure Generation from Mass Spectra?","display_name":"How to Train Your Neural Network for Molecular Structure Generation from Mass Spectra?","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259710","doi":"https://doi.org/10.1109/bibm62325.2024.10822742"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100643414","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0002-9369-3410"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["Shandong University,School of Computer Science and Technology,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084905540","display_name":"Yanmin Liu","orcid":"https://orcid.org/0000-0002-1571-5370"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Liu","raw_affiliation_strings":["Shandong University,School of Computer Science and Technology,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060247019","display_name":"Longyang Dian","orcid":"https://orcid.org/0000-0002-0934-0998"},"institutions":[{"id":"https://openalex.org/I4391767886","display_name":"State Key Laboratory of Microbial Technology","ror":"https://ror.org/03x08qn04","country_code":null,"type":"facility","lineage":["https://openalex.org/I154099455","https://openalex.org/I4391767886"]},{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Dian","raw_affiliation_strings":["Shandong University,State Key Laboratory of Microbial Technology,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,State Key Laboratory of Microbial Technology,Qingdao,China","institution_ids":["https://openalex.org/I154099455","https://openalex.org/I4391767886"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108903761","display_name":"Shiwei Sun","orcid":"https://orcid.org/0000-0002-0351-3720"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwei Sun","raw_affiliation_strings":["Chinese Academy of Sciences,Key Lab of Intelligent Information Processing Institute of Computing Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Lab of Intelligent Information Processing Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101906222","display_name":"Xuefeng Cui","orcid":"https://orcid.org/0000-0002-8816-3482"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Cui","raw_affiliation_strings":["Shandong University,School of Computer Science and Technology,Qingdao,China"],"affiliations":[{"raw_affiliation_string":"Shandong University,School of Computer Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100643414"],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":0.4052,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68668787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"817","last_page":"822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9351000189781189,"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":0.9351000189781189,"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":0.9088000059127808,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6614124178886414},{"id":"https://openalex.org/keywords/mass-spectrum","display_name":"Mass spectrum","score":0.6084291338920593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5784316658973694},{"id":"https://openalex.org/keywords/spectral-line","display_name":"Spectral line","score":0.43866145610809326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3122909665107727},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2876487970352173},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"Mass spectrometry","score":0.27808523178100586},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19576862454414368},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.09512144327163696}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6614124178886414},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.6084291338920593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5784316658973694},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.43866145610809326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3122909665107727},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2876487970352173},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.27808523178100586},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19576862454414368},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.09512144327163696},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2004496597","https://openalex.org/W2028421938","https://openalex.org/W2064675550","https://openalex.org/W2084375915","https://openalex.org/W2101394823","https://openalex.org/W2179948434","https://openalex.org/W2504691963","https://openalex.org/W2622236128","https://openalex.org/W2767683865","https://openalex.org/W2788277448","https://openalex.org/W2900694120","https://openalex.org/W2921388451","https://openalex.org/W2922522932","https://openalex.org/W2945551948","https://openalex.org/W2980166393","https://openalex.org/W2982596783","https://openalex.org/W3030363843","https://openalex.org/W3036061391","https://openalex.org/W3108604517","https://openalex.org/W3217248762","https://openalex.org/W4281688302","https://openalex.org/W4313525610","https://openalex.org/W4390992168","https://openalex.org/W4392208003","https://openalex.org/W6640963894"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Mass":[0],"spectrometry":[1,100,155],"serves":[2,189],"as":[3],"a":[4,87,132,183,206,213],"pivotal":[5],"tool":[6],"for":[7,91],"the":[8,28,35,43,49,55,92,107,111,115,120,129,168,174,201,224,235],"analysis":[9,29],"of":[10,16,30,37,45,51,58,94,114,122,131,167,177,182,186,210],"small":[11,39],"molecules":[12],"through":[13],"an":[14,75],"examination":[15],"their":[17],"mass-to-charge":[18],"ratios.":[19],"Recent":[20],"advancements":[21],"in":[22,173,231],"deep":[23],"learning":[24],"have":[25],"markedly":[26],"enhanced":[27],"mass":[31,99,154],"spectrometric":[32],"data,":[33],"facilitating":[34],"prediction":[36,208],"novel":[38,103],"molecule":[40],"structures":[41,96],"without":[42],"necessity":[44],"extensive":[46],"databases.":[47],"Nonetheless,":[48],"paucity":[50],"annotated":[52],"datasets":[53],"impedes":[54],"efficacious":[56],"training":[57,108,236],"molecular":[59,95,138],"generation":[60,93],"models":[61,241],"predicated":[62],"on":[63],"MS<sup":[64],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[65],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[66],"spectra.":[67],"To":[68],"mitigate":[69],"this":[70,232],"limitation,":[71],"we":[72],"introduce":[73],"ctMSNovelist,":[74],"avant-garde":[76],"method":[77],"that":[78,223],"amalgamates":[79],"pre-training,":[80],"fine-tuning,":[81],"and":[82,110,194,204,229,240],"co-training":[83],"techniques":[84],"to":[85,136,148,190,221],"construct":[86],"more":[88],"precise":[89],"model":[90,192],"from":[97,141,153],"tandem":[98],"data.":[101,124,157],"This":[102],"approach":[104],"augments":[105],"both":[106],"regimen":[109],"predictive":[112],"accuracy":[113,193,209],"MSNovelist":[116,159,230],"model,":[117],"thereby":[118],"surmounting":[119],"obstacle":[121],"limited":[123],"The":[125,180,238],"methodology":[126],"commences":[127],"with":[128],"pretraining":[130],"Variational":[133],"Autoencoder":[134],"(VAE)":[135],"generate":[137],"fingerprints":[139,151],"derived":[140],"SMILES":[142,207],"strings.":[143],"Subsequently,":[144],"it":[145],"undergoes":[146],"fine-tuning":[147],"emulate":[149],"noisy":[150,170,187],"originating":[152],"(MS)":[156],"Concurrently,":[158],"is":[160,219],"co-trained":[161],"utilizing":[162],"these":[163],"simulated":[164],"fingerprints,":[165],"inclusive":[166],"highly":[169],"variants":[171],"produced":[172],"early":[175],"stages":[176],"VAE":[178],"training.":[179],"incorporation":[181],"substantial":[184],"volume":[185],"data":[188],"enhance":[191],"avert":[195],"overfitting.":[196],"We":[197],"evaluated":[198],"ctMSNovelist":[199,228],"using":[200],"GNPS":[202],"dataset":[203],"attained":[205],"48.8%,":[211],"representing":[212],"4.1%":[214],"enhancement":[215],"over":[216],"MSNovelist.":[217],"It":[218],"pertinent":[220],"note":[222],"sole":[225],"distinction":[226],"between":[227],"experiment":[233],"was":[234],"process.":[237],"code":[239],"are":[242],"publicly":[243],"available":[244],"at":[245],"https://github.com/xfcui/ctMSNovelist.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}