{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T09:12:26Z","timestamp":1788340346367,"version":"build-2803163510"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Anal Bioanal Chem"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Untargeted urinary metabolomics represents a promising approach for investigating metabolic alterations associated with oncogenic processes such as breast cancer (BC). However, the stable selection of informative m\/z features remains a central challenge in biomarker-oriented studies, particularly in the context of early BC detection and population-level screening. Urine samples from two independent cohorts (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200950 and\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200975) and analyzed using distinct UHPLC\u2013QTOF\u2013ESI\u207a mass spectrometry workflows, yielded 224 and 129 aligned m\/z features, respectively. Classification and embedded feature selection were implemented within a leakage-controlled Random Forest (RF) framework using Gini index-based importance ranking. Model evaluation incorporated repeated train-test splits and cross-validation to ensure methodological rigor and minimize overfitting. By consistently applying the same RF-based analytical framework to two analytically distinct cohorts generated under different chromatographic separation conditions, we demonstrate that a unified supervised strategy can achieve comparably high classification performance despite differences in feature dimensionality. Further, controlled dimensionality reduction identified compact panels of 25\u00a0m\/z features per cohort while preserving classification performance. Importantly, stability was maintained after feature reduction, with strong accuracy, F1 scores, and receiver operating characteristic and precision\u2013recall characteristics observed in both full and reduced models. This cross-cohort consistency indicates that the discriminative signal captured by the RF approach is not cohort-specific nor dependent on a particular separation workflow, but rather reflects reproducible metabolic patterns associated with BC. The stability of feature selection was further supported by substantial overlap between RF-derived Gini importance rankings and variable importance in projection (VIP) scores obtained from partial least squares discriminant analysis (PLS-DA) in MetaboAnalyst 5.0, indicating concordance across distinct supervised multivariate frameworks. Collectively, these findings highlight the advantage of a unified, supervised tree-based strategy capable of delivering stable classification and interpretable dimensionality reduction across independent untargeted metabolomics platforms, providing a structured and transferable framework for metabolomics-driven biomarker discovery and future clinical validation.\n                  <\/jats:p>","DOI":"10.1007\/s00216-026-06759-w","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T08:12:27Z","timestamp":1788336747000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dimensionality reduction and metabolite panel derivation in urinary metabolomics based on Random Forest with Gini index feature selection"],"prefix":"10.1007","author":[{"given":"Markus","family":"Zetes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vlad","family":"Moisoiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carmen","family":"Socaciu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolae","family":"Leopold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,2]]},"reference":[{"issue":"1","key":"6759_CR1","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1021\/acs.jproteome.7b00595","volume":"17","author":"FM Alakwaa","year":"2018","unstructured":"Alakwaa FM, Chaudhary K, Garmire LX. Deep learning accurately predicts estrogen receptor status in breast cancer metabolomics data. J Proteome Res. 2018;17(1):337\u201347. https:\/\/doi.org\/10.1021\/acs.jproteome.7b00595.","journal-title":"J Proteome Res"},{"issue":"10","key":"6759_CR2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0311810","volume":"19","author":"NK Anh","year":"2024","unstructured":"Anh NK, Lee A, Phat NK, Yen NTH, Thu NQ, Tien NTN, et al. Combining metabolomics and machine learning to discover biomarkers for early-stage breast cancer diagnosis. PLoS ONE. 2024;19(10):e0311810.","journal-title":"PLoS ONE"},{"key":"6759_CR3","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/s10549-019-05330-9","volume":"177","author":"T Murata","year":"2019","unstructured":"Murata T, Yanagisawa T, Kurihara T, Kaneko M, Ota S, Enomoto A, et al. Salivary metabolomics with alternative decision tree-based machine learning methods for breast cancer discrimination. Breast Cancer Res Treat. 2019;177:591\u2013601.","journal-title":"Breast Cancer Res Treat"},{"key":"6759_CR4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3389\/fbioe.2015.00023","volume":"3","author":"A Alonso","year":"2015","unstructured":"Alonso A, Marsal S, Juli\u00e0 A. Analytical methods in untargeted metabolomics: state of the art in 2015. Front Bioeng Biotechnol. 2015;3:23.","journal-title":"Front Bioeng Biotechnol"},{"issue":"13","key":"6759_CR5","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.1007\/s00216-025-05867-3","volume":"417","author":"Y Bai","year":"2025","unstructured":"Bai Y, Capriotti AL. Metabolomics for clinical applications. Anal Bioanal Chem. 2025;417(13):2751\u20132. https:\/\/doi.org\/10.1007\/s00216-025-05867-3.","journal-title":"Anal Bioanal Chem"},{"issue":"23","key":"6759_CR6","doi-asserted-by":"publisher","first-page":"5827","DOI":"10.1007\/s00216-020-02807-1","volume":"412","author":"J Nizio\u0142","year":"2020","unstructured":"Nizio\u0142 J, Ossoli\u0144ski K, Tripet BP, Copi\u00e9 V, Arendowski A, Ruman T. Nuclear magnetic resonance and surface-assisted laser desorption\/ionization mass spectrometry-based serum metabolomics of kidney cancer. Anal Bioanal Chem. 2020;412(23):5827\u201341. https:\/\/doi.org\/10.1007\/s00216-020-02807-1.","journal-title":"Anal Bioanal Chem"},{"issue":"7","key":"6759_CR7","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1007\/s00216-011-4789-6","volume":"401","author":"W Struck","year":"2011","unstructured":"Struck W, Waszczuk-Jankowska M, Kaliszan R, Markuszewski MJ. The state-of-the-art determination of urinary nucleosides using chromatographic techniques \u201chyphenated\u201d with advanced bioinformatic methods. Anal Bioanal Chem. 2011;401(7):2039\u201350. https:\/\/doi.org\/10.1007\/s00216-011-4789-6.","journal-title":"Anal Bioanal Chem"},{"issue":"16","key":"6759_CR8","doi-asserted-by":"publisher","first-page":"3137","DOI":"10.1007\/s00216-023-04715-6","volume":"415","author":"L Naumann","year":"2023","unstructured":"Naumann L, Haun A, H\u00f6chsmann A, Mohr M, Nov\u00e1k M, Flottmann D, et al. Augmented region of interest for untargeted metabolomics mass spectrometry (AriumMS) of multi-platform-based CE-MS and LC-MS data. Anal Bioanal Chem. 2023;415(16):3137\u201354. https:\/\/doi.org\/10.1007\/s00216-023-04715-6.","journal-title":"Anal Bioanal Chem"},{"issue":"12","key":"6759_CR9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0225129","volume":"14","author":"J Park","year":"2019","unstructured":"Park J, Shin Y, Kim TH, Kim DH, Lee A. Plasma metabolites as possible biomarkers for diagnosis of breast cancer. PLoS ONE. 2019;14(12):e0225129.","journal-title":"PLoS ONE"},{"key":"6759_CR10","unstructured":"Romanciuc F, Eniu D, Staicu A, Rachieru C, Buiga R, Socaciu C. HPLC\/MS-based metabolic profiling and quantification of urine free amino acids as potential biomarkers for breast cancer diagnosis and progression. [Internet]. 2015 [cited 2025 Aug 13]. Available from: https:\/\/www.cabidigitallibrary.org\/doi\/full\/10.5555\/20163032834. Accessed 14.03.2026"},{"issue":"1","key":"6759_CR11","doi-asserted-by":"publisher","first-page":"e189","DOI":"10.1038\/oncsis.2015.49","volume":"5","author":"S Beloribi-Djefaflia","year":"2016","unstructured":"Beloribi-Djefaflia S, Vasseur S, Guillaumond F. Lipid metabolic reprogramming in cancer cells. Oncogenesis. 2016;5(1):e189\u2013e189.","journal-title":"Oncogenesis"},{"issue":"W1","key":"6759_CR12","doi-asserted-by":"publisher","first-page":"W388","DOI":"10.1093\/nar\/gkab382","volume":"49","author":"Z Pang","year":"2021","unstructured":"Pang Z, Chong J, Zhou G, de Lima Morais DA, Chang L, Barrette M, et al. MetaboAnalyst 5.0: narrowing the gap between raw spectra and functional insights. Nucleic Acids Res. 2021;49(W1):W388-96.","journal-title":"Nucleic Acids Res"},{"key":"6759_CR13","doi-asserted-by":"publisher","unstructured":"Kabiraj S, Raihan M, Alvi N, Afrin M, Akter L, Sohagi SA, et al. Breast Cancer Risk Prediction using XGBoost and Random Forest Algorithm. In: 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT) [Internet]. 2020 [cited 2025 Apr 23]. p. 1\u20134. Available from: https:\/\/ieeexplore.ieee.org\/abstract\/document\/9225451https:\/\/doi.org\/10.1109\/ICCCNT49239.2020.9225451. Accessed 14.03.2026","DOI":"10.1109\/ICCCNT49239.2020.9225451"},{"key":"6759_CR14","doi-asserted-by":"crossref","unstructured":"Han H, Guo X, Yu H. Variable selection using mean decrease accuracy and mean decrease gini based on random forest. In: 2016 7th ieee international conference on software engineering and service science (icsess) [Internet]. IEEE; 2016 [cited 2025 Mar 10]. p. 219\u201324. Available from: https:\/\/ieeexplore.ieee.org\/abstract\/document\/7883053\/. Accessed 14.03.2026","DOI":"10.1109\/ICSESS.2016.7883053"},{"key":"6759_CR15","doi-asserted-by":"crossref","unstructured":"Rohan TI, Siddik AB, Islam M, Yusuf MSU. A precise breast cancer detection approach using ensemble of random forest with AdaBoost. In: 2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2) [Internet]. IEEE; 2019 [cited 2025 May 14]. p. 1\u20134. Available from: https:\/\/ieeexplore.ieee.org\/abstract\/document\/9036697\/. Accessed 14.03.2026","DOI":"10.1109\/IC4ME247184.2019.9036697"},{"issue":"73","key":"6759_CR16","doi-asserted-by":"publisher","first-page":"58952","DOI":"10.1039\/C5RA10130A","volume":"5","author":"JH Huang","year":"2015","unstructured":"Huang JH, Fu L, Li B, Xie HL, Zhang X, Chen Y, et al. Distinguishing the serum metabolite profiles differences in breast cancer by gas chromatography mass spectrometry and random forest method. RSC Adv. 2015;5(73):58952\u20138.","journal-title":"RSC Adv"},{"key":"6759_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.molstruc.2021.131369","volume":"1247","author":"DT Eniu","year":"2022","unstructured":"Eniu DT, Chiorean AR, Socaciu AI, Staicu A, Rachieriu C, Goidescu I, et al. Blood and urine biomarkers in invasive ductal breast cancer: mass spectrometry applied to identify metabolic alterations. J Mol Struct. 2022;1247:131369.","journal-title":"J Mol Struct"},{"issue":"4","key":"6759_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/app9040806","volume":"9","author":"V Moisoiu","year":"2019","unstructured":"Moisoiu V, Socaciu A, Stefancu A, Iancu SD, Boros I, Alecsa CD, et al. Breast cancer diagnosis by surface-enhanced Raman scattering (SERS) of urine. Appl Sci. 2019;9(4):806.","journal-title":"Appl Sci"},{"key":"6759_CR19","unstructured":"Janecek A, Gansterer W, Demel M, Ecker G. On the relationship between feature selection and classification accuracy. In: New challenges for feature selection in data mining and knowledge discovery [Internet]. PMLR; 2008 [cited 2025 Mar 10]. p. 90\u2013105. Available from: https:\/\/proceedings.mlr.press\/v4\/janecek08a. Accessed 14.03.2026"}],"container-title":["Analytical and Bioanalytical Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00216-026-06759-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00216-026-06759-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00216-026-06759-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T08:12:28Z","timestamp":1788336748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00216-026-06759-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"references-count":19,"alternative-id":["6759"],"URL":"https:\/\/doi.org\/10.1007\/s00216-026-06759-w","relation":{},"ISSN":["1618-2642","1618-2650"],"issn-type":[{"value":"1618-2642","type":"print"},{"value":"1618-2650","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,2]]},"assertion":[{"value":"20 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The study was conducted in strict adherence to ethical guidelines approved by the institutional ethics committee, and in accordance with the Declaration of Helsinki and its subsequent amendments.","order":1,"name":"Ethics","label":"Ethics approval statement","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Urine samples from Cohort A were collected from patients recruited at the Ion Chiricu\u021b\u0103 Oncologic Institute, Cluj-Napoca, Romania, and the Oncosurg Surgical Oncology Clinic, Cluj-Napoca, Romania. Urine samples from Cohort B were collected from patients at the Ion Chiricu\u021b\u0103 Oncologic Institute, Cluj-Napoca, Romania.","order":2,"name":"Ethics","label":"Source of biological material","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}