{"id":"https://openalex.org/W3209680996","doi":"https://doi.org/10.1186/s13321-021-00558-4","title":"MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra","display_name":"MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W3209680996","doi":"https://doi.org/10.1186/s13321-021-00558-4","mag":"3209680996","pmid":"https://pubmed.ncbi.nlm.nih.gov/34715914"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-021-00558-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00558-4","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00558-4","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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 Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00558-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068532928","display_name":"Florian Huber","orcid":"https://orcid.org/0000-0002-3535-9406"},"institutions":[{"id":"https://openalex.org/I4210095242","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800991832","https://openalex.org/I4210090210","https://openalex.org/I4210095242"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Florian Huber","raw_affiliation_strings":["Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands. florian.huber@hs-duesseldorf.de","Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-3535-9406","affiliations":[{"raw_affiliation_string":"Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands. florian.huber@hs-duesseldorf.de","institution_ids":["https://openalex.org/I4210095242"]},{"raw_affiliation_string":"Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I4210095242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014623878","display_name":"Sven van der Burg","orcid":"https://orcid.org/0000-0003-1250-6968"},"institutions":[{"id":"https://openalex.org/I4210095242","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800991832","https://openalex.org/I4210090210","https://openalex.org/I4210095242"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sven van der Burg","raw_affiliation_strings":["Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1250-6968","affiliations":[{"raw_affiliation_string":"Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I4210095242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075156076","display_name":"Justin J. J. van der Hooft","orcid":"https://orcid.org/0000-0002-9340-5511"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Justin J. J. van der Hooft","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, 6708 PB, Wageningen, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9340-5511","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, 6708 PB, Wageningen, The Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012277204","display_name":"Lars Ridder","orcid":"https://orcid.org/0000-0002-7635-9533"},"institutions":[{"id":"https://openalex.org/I4210095242","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800991832","https://openalex.org/I4210090210","https://openalex.org/I4210095242"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lars Ridder","raw_affiliation_strings":["Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-7635-9533","affiliations":[{"raw_affiliation_string":"Netherlands eScience Center, 1098 XG, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I4210095242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068532928"],"corresponding_institution_ids":["https://openalex.org/I4210095242"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":7.9938,"has_fulltext":true,"cited_by_count":192,"citation_normalized_percentile":{"value":0.98623321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"84","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6261371374130249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5940780639648438},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5590721368789673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153850317001343},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.49940967559814453},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.48077958822250366},{"id":"https://openalex.org/keywords/mass-spectrum","display_name":"Mass spectrum","score":0.47283703088760376},{"id":"https://openalex.org/keywords/spectral-line","display_name":"Spectral line","score":0.4592132568359375},{"id":"https://openalex.org/keywords/chemical-similarity","display_name":"Chemical similarity","score":0.42699021100997925},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4113695025444031},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.33757132291793823},{"id":"https://openalex.org/keywords/structural-similarity","display_name":"Structural similarity","score":0.26092466711997986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2578917443752289},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"Mass spectrometry","score":0.2182515561580658},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21672090888023376},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.215040385723114},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11121046543121338}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6261371374130249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5940780639648438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5590721368789673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153850317001343},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.49940967559814453},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.48077958822250366},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.47283703088760376},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.4592132568359375},{"id":"https://openalex.org/C24259465","wikidata":"https://www.wikidata.org/wiki/Q2272153","display_name":"Chemical similarity","level":3,"score":0.42699021100997925},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4113695025444031},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.33757132291793823},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.26092466711997986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2578917443752289},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.2182515561580658},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21672090888023376},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.215040385723114},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11121046543121338},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-021-00558-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00558-4","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00558-4","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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 Cheminformatics","raw_type":"journal-article"},{"id":"pmid:34715914","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34715914","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,"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 cheminformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:ec463e46886740b1b44fb5d7afbdec59","is_oa":true,"landing_page_url":"https://doaj.org/article/ec463e46886740b1b44fb5d7afbdec59","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 13, Iss 1, Pp 1-14 (2021)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:7449655","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8556919","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8556919","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8556919","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:wur:oai:library.wur.nl:wurpubs/589301","is_oa":true,"landing_page_url":"https://research.wur.nl/en/publications/ms2deepscore-a-novel-deep-learning-similarity-measure-to-compare-","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, 13(1)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s13321-021-00558-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00558-4","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00558-4","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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 Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4368164343","display_name":null,"funder_award_id":"ASDI.2017.030","funder_id":"https://openalex.org/F4320314239","funder_display_name":"Netherlands eScience Center"}],"funders":[{"id":"https://openalex.org/F4320314239","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3209680996.pdf","grobid_xml":"https://content.openalex.org/works/W3209680996.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1975147762","https://openalex.org/W1978312864","https://openalex.org/W1988909822","https://openalex.org/W2033079433","https://openalex.org/W2101234009","https://openalex.org/W2119512897","https://openalex.org/W2125069590","https://openalex.org/W2144803530","https://openalex.org/W2151697120","https://openalex.org/W2174991771","https://openalex.org/W2179948434","https://openalex.org/W2187089797","https://openalex.org/W2472803348","https://openalex.org/W2504691963","https://openalex.org/W2548357532","https://openalex.org/W2557283755","https://openalex.org/W2756902045","https://openalex.org/W2770501663","https://openalex.org/W2786394271","https://openalex.org/W2802909948","https://openalex.org/W2806190360","https://openalex.org/W2895061638","https://openalex.org/W2897178933","https://openalex.org/W2899070097","https://openalex.org/W2902548064","https://openalex.org/W2911293880","https://openalex.org/W2922522932","https://openalex.org/W2938756926","https://openalex.org/W2947129631","https://openalex.org/W2964059111","https://openalex.org/W2964121744","https://openalex.org/W3025883815","https://openalex.org/W3035302862","https://openalex.org/W3036061391","https://openalex.org/W3042998478","https://openalex.org/W3081878206","https://openalex.org/W3090156345","https://openalex.org/W3099074835","https://openalex.org/W3108604517","https://openalex.org/W3129424480","https://openalex.org/W3143828703","https://openalex.org/W3158187537","https://openalex.org/W3173289526","https://openalex.org/W3202344023","https://openalex.org/W3206742358","https://openalex.org/W4229530126","https://openalex.org/W4238781491","https://openalex.org/W4281911083","https://openalex.org/W6665890657","https://openalex.org/W6944581743"],"related_works":["https://openalex.org/W4292296636","https://openalex.org/W1987966112","https://openalex.org/W2384995271","https://openalex.org/W2412446857","https://openalex.org/W2090768198","https://openalex.org/W1576126133","https://openalex.org/W4249871115","https://openalex.org/W22579956","https://openalex.org/W630734576","https://openalex.org/W2482675266"],"abstract_inverted_index":{"Mass":[0,21],"spectrometry":[1],"data":[2,291],"is":[3,66,140,161],"one":[4],"of":[5,9,31,106,111,156,175,188,203,211,264,289],"the":[6,18,32,39,49,88,145,149,192,268],"key":[7],"sources":[8],"information":[10],"in":[11,14,224],"many":[12],"workflows":[13],"medicine":[15],"and":[16,147,168],"across":[17],"life":[19],"sciences.":[20],"fragmentation":[22,100],"spectra":[23,110,155,181],"are":[24,55],"generally":[25,71],"considered":[26],"to":[27,86,120,142,163,169,199,249,260,267],"be":[28,45,197,247,258],"characteristic":[29],"signatures":[30],"chemical":[33,40,93],"compound":[34,228],"they":[35],"originate":[36],"from,":[37],"yet":[38],"structure":[41],"itself":[42],"usually":[43],"cannot":[44],"easily":[46],"deduced":[47],"from":[48,230],"spectrum.":[50],"Often,":[51],"spectral":[52,221,233,240,254,280],"similarity":[53,62,90,123,222,281],"measures":[54,223,282],"used":[56,141,198,248,259],"as":[57],"a":[58,70,81,103,183,201,206,287],"proxy":[59],"for":[60,125,173,239,286],"structural":[61,89,122,166],"but":[63],"this":[64],"approach":[65],"strongly":[67],"limited":[68],"by":[69],"poor":[72],"correlation":[73],"between":[74,91],"both":[75],"metrics.":[76],"Here,":[77],"we":[78,117,215,274],"propose":[79],"MS2DeepScore:":[80],"novel":[82],"Siamese":[83],"neural":[84],"network":[85],"predict":[87,121,170],"two":[92],"structures":[94],"solely":[95],"based":[96,177],"on":[97,178],"their":[98,179],"MS/MS":[99],"spectra.":[101,265],"Using":[102],"cleaned":[104],"dataset":[105],">":[107],"100,000":[108],"mass":[109,232,253,279],"about":[112,189,212],"15,000":[113],"unique":[114],"known":[115],"compounds,":[116,159],"trained":[118],"MS2DeepScore":[119,160,218,244],"scores":[124,172],"spectrum":[126],"pairs":[127,174,229],"with":[128,182,205],"high":[129],"accuracy.":[130],"In":[131],"addition,":[132],"sampling":[133],"different":[134],"model":[135],"varieties":[136],"through":[137],"Monte-Carlo":[138],"Dropout":[139],"further":[143],"improve":[144],"predictions":[146,204],"assess":[148],"model's":[150],"prediction":[151,193],"uncertainty.":[152],"On":[153],"3600":[154],"500":[157],"unseen":[158],"able":[162],"identify":[164],"highly-reliable":[165],"matches":[167],"Tanimoto":[171],"molecules":[176],"fragment":[180],"root":[184,207],"mean":[185,208],"squared":[186,209],"error":[187,210],"0.15.":[190],"Furthermore,":[191,214],"uncertainty":[194],"estimate":[195],"can":[196,245],"select":[200],"subset":[202],"0.1.":[213],"demonstrate":[216],"that":[217,256,276],"outperforms":[219],"classical":[220],"retrieving":[225],"chemically":[226,251],"related":[227],"large":[231,262],"datasets,":[234],"thereby":[235],"illustrating":[236],"its":[237],"potential":[238,285],"library":[241],"matching.":[242],"Finally,":[243],"also":[246],"create":[250],"meaningful":[252],"embeddings":[255],"could":[257],"cluster":[261],"numbers":[263],"Added":[266],"recently":[269],"introduced":[270],"unsupervised":[271],"Spec2Vec":[272],"metric,":[273],"believe":[275],"machine":[277],"learning-supported":[278],"have":[283],"great":[284],"range":[288],"metabolomics":[290],"processing":[292],"pipelines.":[293]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":51},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}