{"id":"https://openalex.org/W4390986140","doi":"https://doi.org/10.1186/s13321-024-00804-5","title":"IDSL_MINT: a deep learning framework to predict molecular fingerprints from mass spectra","display_name":"IDSL_MINT: a deep learning framework to predict molecular fingerprints from mass spectra","publication_year":2024,"publication_date":"2024-01-18","ids":{"openalex":"https://openalex.org/W4390986140","doi":"https://doi.org/10.1186/s13321-024-00804-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/38238779","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10797927"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00804-5","doi":"https://doi.org/10.1186/s13321-024-00804-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00804-5","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00804-5","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,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00804-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041704779","display_name":"\u202aSadjad Fakouri Baygi\u202c","orcid":"https://orcid.org/0000-0002-6864-6911","observed_orcids":["https://orcid.org/0000-0002-6864-6911"]},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sadjad Fakouri Baygi","raw_affiliation_strings":["Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, CAM Building, 3rd Floor, 17 E 102 St, New York, NY, 10029, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, CAM Building, 3rd Floor, 17 E 102 St, New York, NY, 10029, USA","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051330408","display_name":"Dinesh Kumar Barupal","orcid":"https://orcid.org/0000-0002-9954-8628","observed_orcids":["https://orcid.org/0000-0002-9954-8628"]},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dinesh Kumar Barupal","raw_affiliation_strings":["Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, CAM Building, 3rd Floor, 17 E 102 St, New York, NY, 10029, USA. dinesh.barupal@mssm.edu","Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, CAM Building, 3rd Floor, 17 E 102 St, New York, NY, 10029, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, CAM Building, 3rd Floor, 17 E 102 St, New York, NY, 10029, USA. dinesh.barupal@mssm.edu","institution_ids":["https://openalex.org/I98704320"]},{"raw_affiliation_string":"Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, CAM Building, 3rd Floor, 17 E 102 St, New York, NY, 10029, USA","institution_ids":["https://openalex.org/I98704320"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051330408"],"corresponding_institution_ids":["https://openalex.org/I98704320"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":2.7108,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91536471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"8","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.975600004196167,"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":0.975600004196167,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.01979999989271164,"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":0.0020000000949949026,"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/tandem-mass-spectrometry","display_name":"tandem mass spectrometry","score":0.8669999837875366},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.8240000009536743},{"id":"https://openalex.org/keywords/mass-spectral-library","display_name":"mass spectral library","score":0.7170000076293945},{"id":"https://openalex.org/keywords/untargeted-metabolomics","display_name":"untargeted metabolomics","score":0.9819999933242798},{"id":"https://openalex.org/keywords/exposomics","display_name":"exposomics","score":0.9990000128746033},{"id":"https://openalex.org/keywords/compound-annotation","display_name":"compound annotation","score":0.699999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481246948242188},{"id":"https://openalex.org/C40325409","wikidata":"https://www.wikidata.org/wiki/Q2360668","display_name":"Mass spectrum","level":3,"score":0.47774237394332886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41081559658050537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37671807408332825},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.3710578680038452},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.2783014476299286},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2754385471343994}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00804-5","doi":"https://doi.org/10.1186/s13321-024-00804-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00804-5","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00804-5","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,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"pmh:oai:pubmedcentral.nih.gov:10797927","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10797927","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10797927/pdf/13321_2024_Article_804.pdf","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmid:38238779","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38238779","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 cheminformatics","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:d00a6942bcdc4b22a65db7300ff705fd","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/d00a6942bcdc4b22a65db7300ff705fd","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,"listed_in":[],"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 16, Iss 1, Pp 1-8 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00804-5","doi":"https://doi.org/10.1186/s13321-024-00804-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00804-5","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00804-5","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,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2273737070","display_name":null,"funder_award_id":"U24 ES035386","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"},{"id":"https://openalex.org/G5720736604","display_name":"Exposome Correlation and Interpretation Database (ECID)","funder_award_id":"5u24es035386-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G9000870939","display_name":"Research Training Program in Pediatric Exposomics","funder_award_id":"T32HD049311","funder_id":"https://openalex.org/F4320337611","funder_display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development"},{"id":"https://openalex.org/G9000872736","display_name":"Conduits: Mount Sinai Health System Translational Science Hub","funder_award_id":"UL1TR004419","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G9000876201","display_name":"Mount Sinai Center for Health and Environment Across the LifeSpan (HEALS)","funder_award_id":"P30ES023515","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"},{"id":"https://openalex.org/G9000898591","display_name":"Mount Sinai HHEAR Network Targeted Lab Hub","funder_award_id":"U2CES026561","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"},{"id":"https://openalex.org/G9000916225","display_name":"Human Health Exposure Analysis Resource (HHEAR) Data Center","funder_award_id":"U2CES026555","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337361","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63"},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"},{"id":"https://openalex.org/F4320337611","display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","ror":"https://ror.org/04byxyr05"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390986140.pdf","grobid_xml":"https://content.openalex.org/works/W4390986140.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W1988037271","https://openalex.org/W2009453329","https://openalex.org/W2034549041","https://openalex.org/W2059511140","https://openalex.org/W2160592148","https://openalex.org/W2179948434","https://openalex.org/W2320278441","https://openalex.org/W2520784563","https://openalex.org/W2612690371","https://openalex.org/W2765207987","https://openalex.org/W2801991413","https://openalex.org/W2911354688","https://openalex.org/W2922522932","https://openalex.org/W2966357564","https://openalex.org/W2975845070","https://openalex.org/W3007309629","https://openalex.org/W3036061391","https://openalex.org/W3112376181","https://openalex.org/W3123901912","https://openalex.org/W3129424480","https://openalex.org/W3209680996","https://openalex.org/W3216027541","https://openalex.org/W4280530392","https://openalex.org/W4281688302","https://openalex.org/W4296808073","https://openalex.org/W4304092658","https://openalex.org/W4313489214","https://openalex.org/W4322102662","https://openalex.org/W4361292278","https://openalex.org/W4362733319","https://openalex.org/W4380449832","https://openalex.org/W4381334298","https://openalex.org/W4383613927","https://openalex.org/W4390221451"],"related_works":["https://openalex.org/W4389576985","https://openalex.org/W6920694847","https://openalex.org/W4407578183","https://openalex.org/W4405142948","https://openalex.org/W3090156345","https://openalex.org/W4283736688","https://openalex.org/W4412184154","https://openalex.org/W7222448117","https://openalex.org/W7115888107","https://openalex.org/W4383613927"],"abstract_inverted_index":{"The":[0,116],"majority":[1],"of":[2,46,86,133],"tandem":[3],"mass":[4,51,100],"spectrometry":[5,52],"(MS/MS)":[6],"spectra":[7,34,92,135,156,188],"in":[8,110,123,146,162],"untargeted":[9,111,137],"metabolomics":[10,112,138],"and":[11,27,81,113,119,139,173,179],"exposomics":[12,114,140],"studies":[13],"lack":[14],"any":[15,69],"annotation.":[16],"Our":[17],"deep":[18],"learning":[19,152],"framework,":[20],"Integrated":[21],"Data":[22],"Science":[23],"Laboratory":[24],"for":[25,50,90,189],"Metabolomics":[26],"Exposomics-Mass":[28],"INTerpreter":[29],"(IDSL_MINT)":[30],"can":[31,160],"translate":[32],"MS/MS":[33,66,91,134],"into":[35,157],"molecular":[36,71,158,185],"fingerprint":[37,72],"descriptors.":[38,73],"IDSL_MINT":[39,74,103,117],"allows":[40],"users":[41],"to":[42,55,154,177,183],"leverage":[43],"the":[44,47,56,78,83,106,124,163,190],"power":[45],"transformer":[48],"model":[49],"data,":[53],"similar":[54],"large":[57],"language":[58],"models.":[59],"Models":[60],"are":[61,121],"trained":[62],"on":[63],"user-provided":[64],"reference":[65],"libraries":[67],"via":[68],"customizable":[70,174],"was":[75],"benchmarked":[76],"using":[77,98],"LipidMaps":[79],"database":[80],"improved":[82],"annotation":[84,108,132,164,192],"rate":[85],"a":[87,143,170],"test":[88],"study":[89],"that":[93],"were":[94],"not":[95],"originally":[96],"annotated":[97],"existing":[99],"spectral":[101],"libraries.":[102],"may":[104],"improve":[105],"overall":[107],"rates":[109],"studies.":[115],"framework":[118,176],"tutorials":[120],"available":[122],"GitHub":[125],"repository":[126],"at":[127],"https://github.com/idslme/IDSL_MINT":[128],".Scientific":[129],"contribution":[130],"statement.Structural":[131],"from":[136,187],"datasets":[141],"is":[142],"major":[144],"bottleneck":[145],"gaining":[147],"new":[148,181],"biological":[149],"insights.":[150],"Machine":[151],"models":[153,182],"convert":[155],"fingerprints":[159,186],"help":[161],"process.":[165],"Here,":[166],"we":[167],"present":[168],"IDSL_MINT,":[169],"new,":[171],"easy-to-use":[172],"deep-learning":[175],"train":[178],"utilize":[180],"predict":[184],"compound":[191],"workflows.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-01-19T00:00:00"}