{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T06:18:02Z","timestamp":1787811482558,"version":"build-2784847793"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011359","name":"State Tobacco Monopoly Administration","doi-asserted-by":"publisher","award":["2021B038"],"award-info":[{"award-number":["2021B038"]}],"id":[{"id":"10.13039\/501100011359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008862","name":"China National Tobacco Corporation","doi-asserted-by":"publisher","award":["110202402005"],"award-info":[{"award-number":["110202402005"]}],"id":[{"id":"10.13039\/501100008862","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008862","name":"China National Tobacco Corporation","doi-asserted-by":"publisher","award":["452025CR0190"],"award-info":[{"award-number":["452025CR0190"]}],"id":[{"id":"10.13039\/501100008862","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Mol. Biosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The geographic origin of premium tobacco extracts fundamentally shapes their sensory profiles and commercial value, but authenticating these complex matrices remains a formidable analytical challenge. Conventional nontargeted analysis workflows typically rely on a minute fraction of structurally annotated metabolites, thereby discarding the vast majority of unannotated yet highly specific chemical markers. To address this limitation, this study introduces a geographic authentication framework utilizing machine learning models trained on characteristic ion feature (CIF) fingerprints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A large-scale dataset of 1,697 tobacco samples was analyzed using liquid chromatography-high resolution mass spectrometry coupled with a data-independent acquisition strategy. Rigorous statistical filtering was applied to isolate CIFs and strip away the shared background metabolome. To evaluate the samples, univariate thresholding based on pattern similarity (dot product) and marker intensity ratios (R score) was initially tested. To overcome the vulnerability of univariate methods to batch effects and overlapping chemical profiles, optimized multivariate machine learning models were also deployed. The models were evaluated under a strict Leave-One-Batch-Out cross-validation framework to ensure robust cross-batch generalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Statistical filtering effectively stripped away over 90% of the shared background metabolome, isolating 47,543 CIFs for Zimbabwe tobacco and 3,646 CIFs for Yunnan tobacco. Univariate thresholding achieved a maximum balanced accuracy of 77.9% but proved too rigid. Under cross-validation, the multivariate Random Forest (RF) classifier demonstrated strong predictive performance, achieving a balanced accuracy of 74.6% for Zimbabwe tobacco and successfully detecting economically motivated adulteration across a wide dilution range (0\u20131,000 ppm). Conversely, both univariate and multivariate methods failed to achieve robust authentication for the Yunnan extracts. This underperformance was driven by severe intra-group heterogeneity stemming from diverse suppliers and heterogeneous processing treatments, which heavily diluted universal characteristic features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Ultimately, this hybrid strategy provides a scalable tool for the industrial verification of consistent premium extracts. Furthermore, the challenges encountered with the Yunnan samples underscore the necessity of cohort-specific modeling when dealing with highly diverse agricultural products that are subjected to varied processing treatments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmolb.2026.1898152","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T05:33:28Z","timestamp":1787808808000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Geographic authentication of premium tobacco extracts using machine learning models trained on LC-HRMS fingerprints"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiu-Juan","family":"Xu","sequence":"first","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Food and Biological Engineering, Shaanxi University of Science and Technology","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Jiangsu Xinyuan Reconstituted Tobacco Co., Ltd.","place":["Huai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Tong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing-Zhao","family":"Shi","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Wei","family":"Ma","sequence":"additional","affiliation":[{"name":"Jiangsu Xinyuan Reconstituted Tobacco Co., Ltd.","place":["Huai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin-Bin","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding-Zhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ren-Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Food and Biological Engineering, Shaanxi University of Science and Technology","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Hu","sequence":"additional","affiliation":[{"name":"Zhengzhou Tobacco Research Institute of China National Tobacco Corporation","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1557190","DOI":"10.3389\/fpls.2025.1557190","article-title":"Analysis of differences in cigar tobacco leaves from different regions based on GC-IMS and LC-MS metabolomics techniques","volume":"16","author":"Chen","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B2","doi-asserted-by":"publisher","first-page":"12549","DOI":"10.1073\/pnas.1516878112","article-title":"Illuminating the dark matter in metabolomics","volume":"112","author":"da Silva","year":"2015","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"B3","doi-asserted-by":"publisher","first-page":"22","DOI":"10.19998\/j.cnki.2095-1795.202512304","article-title":"Tobacco origin and quality grade identification based on GC-IMS spectral data and machine learning","volume":"15","author":"Dawei","year":"2025","journal-title":"Agric. Eng."},{"key":"B4","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.crfs.2022.01.026","article-title":"Identification of new glycosidic terpenols and norisoprenoids (aroma precursors) in C. arabica L. green coffee by using a high-resolution mass spectrometry database developed in grape metabolomics","volume":"5","author":"De Rosso","year":"2022","journal-title":"Curr. Res. Food Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.aca.2014.03.039","article-title":"A comparative investigation of modern feature selection and classification approaches for the analysis of mass spectrometry data","volume":"829","author":"Gromski","year":"2014","journal-title":"Anal. Chim. Acta"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1537924","DOI":"10.3389\/fpls.2025.1537924","article-title":"Microstructure observation and flavor substances excavation of yunyan 87 tobacco leaves with different oil contents","volume":"16","author":"Hu","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/0031-3203(86)90030-0","article-title":"Minimum error thresholding","volume":"19","author":"Kittler","year":"1986","journal-title":"Pattern Recognit."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1721371","DOI":"10.3389\/fchem.2026.1721371","article-title":"Rapid discrimination of geographical origin and analysis of chemical characterization of tobacco leaves from multiple countries","volume":"14","author":"Kou","year":"2026","journal-title":"Front. Chem."},{"key":"B9","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1186\/1471-2105-9-375","article-title":"Critical assessment of alignment procedures for LC-MS proteomics and metabolomics measurements","volume":"9","author":"Lange","year":"2008","journal-title":"BMC Bioinform"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1002\/jssc.201100106","article-title":"Gas chromatography-mass spectrometric method for metabolic profiling of tobacco leaves","volume":"34","author":"Li","year":"2011","journal-title":"J. Sep. Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"e70082","DOI":"10.1111\/1541-4337.70082","article-title":"Recent advances of machine learning in the geographical origin traceability of food and agro-products: a review","volume":"24","author":"Li","year":"2024","journal-title":"Compr. Rev. Food Sci. Food Saf."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1016\/j.talanta.2010.07.053","article-title":"A random forest of combined features in the classification of cut tobacco based on gas chromatography fingerprinting","volume":"82","author":"Lin","year":"2010","journal-title":"Talanta"},{"key":"B13","doi-asserted-by":"publisher","first-page":"33295","DOI":"10.1021\/acsomega.2c03877","article-title":"Proteomic and metabolomic revealed differences in the distribution and synthesis mechanism of aroma precursors in yunyan 87 tobacco leaf, stem, and root at the seedling stage","volume":"7","author":"Liu","year":"2022","journal-title":"ACS Omega"},{"key":"B14","doi-asserted-by":"publisher","first-page":"107644","DOI":"10.1016\/j.plaphy.2023.107644","article-title":"Priming crop plants with rosemary (Salvia rosmarinus spenn, syn rosmarinus officinalis L.) extract triggers protective defense response against pathogens","volume":"197","author":"Martin","year":"2023","journal-title":"Plant Physiol. biochem."},{"key":"B15","doi-asserted-by":"publisher","first-page":"e70067","DOI":"10.1111\/tpj.70067","article-title":"Excessive leaf oil modulates the plant abiotic stress response via reduced stomatal aperture in tobacco (Nicotiana tabacum)","volume":"121","author":"Murphy","year":"2025","journal-title":"Plant J."},{"key":"B16","doi-asserted-by":"publisher","first-page":"141","DOI":"10.3390\/foods12010141","article-title":"Development of non-targeted mass spectrometry method for distinguishing spelt and wheat","volume":"12","author":"Nichani","year":"2023","journal-title":"Foods"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3001","DOI":"10.3390\/s26103001","article-title":"Integrating metabolomics and machine learning for advanced chemical detection","volume":"26","author":"Picone","year":"2026","journal-title":"Sensors"},{"key":"B18","doi-asserted-by":"publisher","first-page":"144078","DOI":"10.1016\/j.foodchem.2025.144078","article-title":"Machine learning-guided Orbitrap-HRAMS-based metabolomic fingerprinting for geographical origin, variety and tissue specific authentication, and adulteration detection of turmeric and ashwagandha","volume":"482","author":"Ratnasekhar","year":"2025","journal-title":"Food Chem."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.3390\/molecules27041198","article-title":"Metabolite fingerprinting based on 1H-NMR spectroscopy and liquid chromatography for the authentication of herbal products","volume":"27","author":"Riswanto","year":"2022","journal-title":"Molecules"},{"key":"B20","doi-asserted-by":"publisher","first-page":"101755","DOI":"10.1016\/j.atech.2025.101755","article-title":"Discrimination of vineyard origin and grape cultivars using rapid mass spectrometry and machine learning","volume":"13","author":"Saha","year":"2026","journal-title":"Smart Agric. Technol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"e32417","DOI":"10.1016\/j.heliyon.2024.e32417","article-title":"Study of metabolite differences of flue-cured tobacco from Canada (CT157) and Yunnan (yunyan 87)","volume":"10","author":"Tie","year":"2024","journal-title":"Heliyon"},{"key":"B22","doi-asserted-by":"publisher","first-page":"8004","DOI":"10.1021\/acs.est.4c13026","article-title":"Prioritization of unknown LC-HRMS features based on predicted toxicity categories","volume":"59","author":"Turkina","year":"2025","journal-title":"Environ. Sci. and Technol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"12273","DOI":"10.1021\/acs.analchem.1c01841","article-title":"CRB-SWATH: a method for enhancing untargeted precursor ion extraction and automatically constructing their tandem mass spectra from swath datasets by chromatographic retention behaviors","volume":"93","author":"Wang","year":"2021","journal-title":"Anal. Chem."},{"key":"B24","doi-asserted-by":"publisher","first-page":"7503","DOI":"10.1021\/acs.analchem.2c05480","article-title":"Biogenic solution map based on the definition of the metabolic correlation distance between 4-dimensional fingerprints","volume":"95","author":"Wang","year":"2023","journal-title":"Anal. Chem."},{"key":"B25","doi-asserted-by":"publisher","first-page":"23204","DOI":"10.1021\/acs.analchem.5c03451","article-title":"CRB-FCC: a standardized nontargeted analysis for formula assignment and structure annotation","volume":"97","author":"Wang","year":"2025","journal-title":"Anal. Chem."},{"key":"B26","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3389\/fpls.2025.1644472","article-title":"Light regulates the synthesis and accumulation of plant secondary metabolites","volume":"16","author":"Wu","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1703429","DOI":"10.3389\/fpls.2025.1703429","article-title":"Metabolomic analysis of Yunnan cigar tobacco leaves: impact of geography and climate on flavor characteristics and machine learning-based origin traceability","volume":"16","author":"Wu","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B28","doi-asserted-by":"publisher","first-page":"465554","DOI":"10.1016\/j.chroma.2024.465554","article-title":"Nontarget analysis of natural flavor metabolites in tobacco extracts","volume":"1740","author":"Xu","year":"2025","journal-title":"J. Chromatogr. A"},{"key":"B29","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2\u20133","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1021\/jf400428t","article-title":"Metabolic profiling of Chinese tobacco leaf of different geographical origins by GC-MS","volume":"61","author":"Zhang","year":"2013","journal-title":"J. Agric. Food Chem."},{"key":"B31","doi-asserted-by":"publisher","first-page":"102461","DOI":"10.1016\/j.bbrep.2026.102461","article-title":"Comparative metabolomic of cigar tobacco leaves: a preliminary investigation of potential discriminatory metabolites between Yunnan and foreign","volume":"45","author":"Zhao","year":"2026","journal-title":"Biochem. Biophys. Rep."}],"container-title":["Frontiers in Molecular Biosciences"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2026.1898152\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T05:33:30Z","timestamp":1787808810000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2026.1898152\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":31,"alternative-id":["10.3389\/fmolb.2026.1898152"],"URL":"https:\/\/doi.org\/10.3389\/fmolb.2026.1898152","relation":{},"ISSN":["2296-889X"],"issn-type":[{"value":"2296-889X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]},"article-number":"1898152"}}