{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T13:15:48Z","timestamp":1792588548013,"version":"4.5.0"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002383","name":"King Saud University","doi-asserted-by":"publisher","award":["RSP 2024R378"],"award-info":[{"award-number":["RSP 2024R378"]}],"id":[{"id":"10.13039\/501100002383","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Mol. Biosci."],"abstract":"<jats:p>Objective: This study aims to develop an explainable artificial intelligence (XAI) model integrated with machine learning (ML) to comprehensively investigate metabolic differences between individuals with Down syndrome (T21) and healthy controls (D21) and to identify novel\/pathway-specific biomarkers. In this study, ML classifiers including AdaBoost, LightGBM, Random Forest, KTBoost, and XGBoost are applied to metabolomics data obtained from metabolomic analyses by high-resolution liquid chromatography-mass spectrometry (LC-MS) using blood plasma samples of 316 T21 and 103 D21 individuals, and the importance of metabolites is evaluated by XAI-based SHAP analysis. The KTBoost model shows the highest classification performance with an accuracy of 90.4% and area under the curve (AUC) of 95.9%, outperforming AdaBoost, LightGBM, Random Forest, and XGBoost. Significant downregulation and upregulation of some metabolites were observed in the T21 group compared to the D21 group. Metabolites such as vitamin C, taurolithocholic acid, sphingosine, and prostaglandin A2\/B2\/J2 are observed at low levels in the T21 group. In contrast, metabolites such as thymidine, tau-roursodeoxycholic acid, serine, and nervonic acid are elevated. SHAP analysis revealed that L-Citrulline, Kynurenin, Prostaglandin A2\/B2\/J2, Urate, and Pantothenate metabolites could be novel\/pathway-specific biomarkers to differentiate the T21 group. This study revealed significant metabolic alterations in individuals with T21 and demonstrated the effectiveness of the combination of ML and XAI methods to identify novel\/pathway-specific biomarkers. The findings may contribute to a better understanding of Down syndrome\u2019s molecular mechanisms and the development of future diagnostic and therapeutic strategies.<\/jats:p>","DOI":"10.3389\/fmolb.2025.1567199","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T08:01:27Z","timestamp":1744185687000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Identification of metabolomics-based biomarker discovery in individuals with down syndrome utilizing kernel-tree model-enhanced explainable artificial intelligence methodology"],"prefix":"10.3389","volume":"12","author":[{"given":"Cemil","family":"Colak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatma Hilal","family":"Yagin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Burak","family":"Yagin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abedalrhman","family":"Alkhateeb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmood Basil A.","family":"Al-Rawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moulay A.","family":"Akhloufi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammadreza","family":"Aghaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"608","DOI":"10.3390\/toxins15100608","article-title":"Ensemble machine learning of gradient boosting (XGBoost, LightGBM, CatBoost) and attention-based CNN-lstm for harmful algal blooms forecasting","volume":"15","author":"Ahn","year":"2023","journal-title":"forecasting"},{"key":"B2","first-page":"82","volume-title":"Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","author":"Arrieta","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e0208626","DOI":"10.1371\/journal.pone.0208626","article-title":"Identifying disease genes using machine learning and gene functional similarities, assessed through Gene Ontology","volume":"13","author":"Asif","year":"2018","journal-title":"PloS one"},{"key":"B4","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1097\/01.aoa.0000460405.80294.32","article-title":"Metabolomic analysis for first trimester down syndrome prediction","volume":"35","author":"Bahado-Singh","year":"2015","journal-title":"Obstet. Anesth. Dig."},{"key":"B5","doi-asserted-by":"publisher","first-page":"371. e1","DOI":"10.1016\/j.ajog.2012.12.035","article-title":"Metabolomic analysis for first-trimester Down syndrome prediction","volume":"208","author":"Bahado-Singh","year":"2013","journal-title":"Am. J. obstetrics Gynecol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"e453","DOI":"10.1016\/S2468-2667(23)00057-9","article-title":"Multiple morbidity across the lifespan in people with Down syndrome or intellectual disabilities: a population-based cohort study using electronic health records","volume":"8","author":"Baksh","year":"2023","journal-title":"Lancet Public Health"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1145\/3411764.3445717","article-title":"Does the whole exceed its parts? the effect of ai explanations on complementary team performance","volume-title":"Proceedings of the 2021 CHI conference on human factors in computing systems","author":"Bansal","year":"2021"},{"key":"B8","doi-asserted-by":"publisher","first-page":"62","DOI":"10.24869\/psyd.2023.62","article-title":"Interpretable estimation of suicide risk and severity from complete blood count parameters with explainable artificial intelligence methods","volume":"35","author":"Cansel","year":"2023","journal-title":"Psychiatr. Danub."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/SIU.2017.7960496","article-title":"Detection and estimation of down syndrome genes by machine learning techniques","volume-title":"2017 25th signal processing and communications applications conference (SIU)","author":"\u00c7elik","year":"2017"},{"key":"B10","doi-asserted-by":"publisher","first-page":"383170","DOI":"10.1155\/2012\/383170","article-title":"Oxidative stress and mitochondrial dysfunction in Down\u2019s syndrome: relevance to aging and dementia","volume":"2012","author":"Coskun","year":"2012","journal-title":"Curr. gerontology geriatrics Res."},{"key":"B11","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B12","doi-asserted-by":"publisher","first-page":"670","DOI":"10.3389\/fnins.2020.00670","article-title":"Down syndrome is a metabolic disease: altered insulin signaling mediates peripheral and brain dysfunctions","volume":"14","author":"Dierssen","year":"2020","journal-title":"Front. Neurosci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"B14","doi-asserted-by":"publisher","first-page":"22189","DOI":"10.1038\/s41598-023-49673-2","article-title":"A proposed tree-based explainable artificial intelligence approach for the prediction of angina pectoris","volume":"13","author":"Guldogan","year":"2023","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3233\/trd-200090","article-title":"Opportunities, barriers, and recommendations in Down syndrome research","volume":"5","author":"Hendrix","year":"2021","journal-title":"Transl. Sci. rare Dis."},{"key":"B16","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.3390\/biomedicines10123219","article-title":"Pediatric population with down syndrome: obesity and the risk of cardiovascular disease and their assessment using omics techniques\u2014review","volume":"10","author":"Hetman","year":"","journal-title":"Biomedicines"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.3390\/biomedicines10123219","article-title":"Pediatric population with down syndrome: obesity and the risk of cardiovascular disease and their assessment using omics techniques-review","volume":"10","author":"Hetman","year":"","journal-title":"Biomedicines"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1049\/gtd2.12386","article-title":"Electric theft detection in advanced metering infrastructure using Jaya optimized combined Kernel\u2010Tree boosting classifier\u2014a novel sequentially executed supervised machine learning approach","volume":"16","author":"Hussain","year":"2022","journal-title":"IET Generation, Transm. and Distribution"},{"key":"B19","doi-asserted-by":"publisher","first-page":"27522","DOI":"10.1109\/access.2022.3146312","article-title":"A survey of machine learning approaches applied to gene expression analysis for cancer prediction","volume":"10","author":"Khalsan","year":"2022","journal-title":"IEEE Access"},{"key":"B20","doi-asserted-by":"publisher","first-page":"920","DOI":"10.3390\/atmos14060920","article-title":"Turbulence along the runway glide path: the invisible Hazard Assessment based on a wind tunnel study and interpretable TPE-Optimized KTBoost Approach","volume":"14","author":"Khattak","year":"2023","journal-title":"Atmosphere"},{"key":"B21","doi-asserted-by":"publisher","first-page":"2484","DOI":"10.3390\/jcm10112484","article-title":"Crosstalk between tryptophan metabolism via kynurenine pathway and carbohydrate metabolism in the context of cardio-metabolic risk-review","volume":"10","author":"Kiluk","year":"2021","journal-title":"J. Clin. Med."},{"key":"B22","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s13347-019-00372-9","article-title":"Against interpretability: a critical examination of the interpretability problem in machine learning","volume":"33","author":"Krishnan","year":"2020","journal-title":"Mach. Learn."},{"key":"B23","doi-asserted-by":"publisher","first-page":"2794","DOI":"10.3390\/nu13082794","article-title":"Citrulline, biomarker of enterocyte functional mass and dietary supplement. Metabolism, transport, and current evidence for clinical use","volume":"13","author":"Maric","year":"2021","journal-title":"Nutrients"},{"key":"B24","doi-asserted-by":"publisher","first-page":"214","DOI":"10.2174\/18715222113139990008","article-title":"Effects of oral L-citrulline supplementation on lipoprotein oxidation and endothelial dysfunction in humans with vasospastic angina","volume":"13","author":"Morita","year":"2013","journal-title":"Immunol. Endocr. and Metabolic Agents Med. Chem. Former. Curr. Med. Chemistry-Immunology, Endocr. Metabolic Agents"},{"key":"B25","first-page":"535","article-title":"Oxidative stress and Down syndrome","volume":"63","author":"Muchov\u00e1","year":"2014","journal-title":"Do antioxidants play a role therapy? Physiological Res."},{"key":"B26","article-title":"Low consumption of fruit and vegetables, and markers of oxidative stress in children with Down syndrome","volume":"13","author":"Nachvak","year":"2010","journal-title":"Downs Syndr. Res. Pract."},{"key":"B27","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1186\/s10020-020-00225-8","article-title":"Meta-analysis of metabolites involved in bioenergetic pathways reveals a pseudohypoxic state in Down syndrome","volume":"26","author":"Pecze","year":"2020","journal-title":"Mol. Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.mito.2020.12.017","article-title":"Meta-analysis of gene expression patterns in Down syndrome highlights significant alterations in mitochondrial and bioenergetic pathways","volume":"57","author":"Pecze","year":"2021","journal-title":"Mitochondrion"},{"key":"B29","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1002\/dneu.22714","article-title":"Blood\u2010based biomarkers for Down syndrome and Alzheimer's disease: a systematic review","volume":"79","author":"Petersen","year":"2019","journal-title":"Dev. Neurobiol."},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-61377-8_25","article-title":"A computational tool for automated detection of genetic syndrome using facial images","volume-title":"Intelligent systems: 9th Brazilian conference, BRACIS 2020, rio grande, Brazil, october 20\u201323, 2020, proceedings, Part I 9","author":"Pooch","year":"2020"},{"key":"B31","doi-asserted-by":"publisher","first-page":"4766","DOI":"10.1038\/s41467-019-12739-9","article-title":"Trisomy 21 activates the kynurenine pathway via increased dosage of interferon receptors","volume":"10","author":"Powers","year":"2019","journal-title":"Nat. Commun."},{"key":"B32","volume-title":"Analysis of defect associated with powder bed fusion with deep learning and explainable AI. 2023 15th International Conference on Knowledge and Smart Technology (KST)","author":"Pratap","year":"2023"},{"key":"B33","volume-title":"Why should i trust you? Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","author":"Ribeiro","year":"2016"},{"key":"B34","doi-asserted-by":"publisher","first-page":"692","DOI":"10.3390\/antiox9080692","article-title":"Antioxidants in down syndrome: from preclinical studies to clinical trials","volume":"9","author":"Rueda","year":"2020","journal-title":"Antioxidants"},{"key":"B35","first-page":"5","article-title":"RJEAi explaining, learning vd","volume-title":"Towards explainable artificial intelligence","author":"Samek","year":"2019"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1007\/s11063-021-10434-9","article-title":"KTBoost: combined kernel and tree boosting","volume":"53","author":"Sigrist","year":"2021","journal-title":"Neural process. Lett."},{"key":"B37","volume-title":"AIX implementation in image-based PM2. 5 estimation: toward an AI model for better understanding. 2023 15th International Conference on Knowledge and Smart Technology (KST)","author":"Utomo","year":"2023"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.3390\/nu16101537","article-title":"Pilot-study to explore metabolic signature of type 2 diabetes: a pipeline of tree-based machine learning and bioinformatics techniques for biomarkers discovery","volume":"16","author":"Yagin","year":"","journal-title":"Nutrients"},{"key":"B39","doi-asserted-by":"publisher","first-page":"3495","DOI":"10.3390\/diagnostics13233495","article-title":"An explainable artificial intelligence model proposed for the prediction of myalgic encephalomyelitis\/chronic fatigue syndrome and the identification of distinctive metabolites","volume":"13","author":"Yagin","year":"","journal-title":"Diagn. (Basel)."},{"key":"B40","doi-asserted-by":"publisher","first-page":"5002","DOI":"10.3390\/jcm13175002","article-title":"Platelet metabolites as candidate biomarkers in sepsis diagnosis and management using the proposed explainable artificial intelligence approach","volume":"13","author":"Yagin","year":"","journal-title":"J. Clin. Med."},{"key":"B41","doi-asserted-by":"publisher","first-page":"106619","DOI":"10.1016\/j.compbiomed.2023.106619","article-title":"Explainable artificial intelligence model for identifying COVID-19 gene biomarkers","volume":"154","author":"Yagin","year":"","journal-title":"Comput. Biol. Med."},{"key":"B42","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1111\/bph.14530","article-title":"Prostaglandin\u2010cytokine crosstalk in chronic inflammation","volume":"176","author":"Yao","year":"2019","journal-title":"Br. J. Pharmacol."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1021\/acscentsci.2c01468","article-title":"Interpretable machine learning on metabolomics data reveals biomarkers for Parkinson\u2019s disease","volume":"9","author":"Zhang","year":"2023","journal-title":"ACS Central Sci."},{"key":"B44","doi-asserted-by":"publisher","first-page":"53","DOI":"10.36255\/exonpublications.bioinformatics.2021.ch4","article-title":"Machine learning approaches for biomarker discovery using gene expression data","author":"Zhang","year":"2021","journal-title":"Bioinformatics"},{"key":"B45","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3390\/diagnostics12020237","article-title":"Applications of explainable artificial intelligence in diagnosis and surgery","volume":"12","author":"Zhang","year":"2022","journal-title":"Diagn. (Basel)."}],"container-title":["Frontiers in Molecular Biosciences"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2025.1567199\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T08:01:31Z","timestamp":1744185691000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2025.1567199\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":45,"alternative-id":["10.3389\/fmolb.2025.1567199"],"URL":"https:\/\/doi.org\/10.3389\/fmolb.2025.1567199","relation":{},"ISSN":["2296-889X"],"issn-type":[{"value":"2296-889X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,9]]},"article-number":"1567199"}}