Sherlock Lee, Martin Brendan R, Behsangar Sinah, Mok K H
Meta-Flux Ltd., Dublin, Ireland.
Trinity Biomedical Sciences Institute (TBSI), School of Biochemistry and Immunology, Trinity College Dublin, The University of Dublin, Dublin, Ireland.
Front Med (Lausanne). 2023 Jul 13;10:1162808. doi: 10.3389/fmed.2023.1162808. eCollection 2023.
We independently analyzed two large public domain datasets that contain H-NMR spectral data from lung cancer and sex studies. The biobanks were sourced from the Karlsruhe Metabolomics and Nutrition (KarMeN) study and Bayesian Automated Metabolite Analyzer for NMR data (BATMAN) study. Our approach of applying novel artificial intelligence (AI)-based algorithms to NMR is an attempt to globalize metabolomics and demonstrate its clinical applications. The intention of this study was to analyze the resulting spectra in the biobanks via AI application to demonstrate its clinical applications. This technique enables metabolite mapping in areas of localized enrichment as a measure of true activity while also allowing for the accurate categorization of phenotypes.
我们独立分析了两个大型公共领域数据集，这些数据集包含来自肺癌和性别研究的氢核磁共振（H-NMR）光谱数据。生物样本库来源于卡尔斯鲁厄代谢组学与营养（KarMeN）研究以及用于核磁共振数据的贝叶斯自动代谢物分析仪（BATMAN）研究。我们将基于新型人工智能（AI）的算法应用于核磁共振的方法，是为了使代谢组学全球化并展示其临床应用。本研究的目的是通过应用人工智能来分析生物样本库中的所得光谱，以展示其临床应用。这项技术能够在局部富集区域进行代谢物图谱绘制，作为真实活性的一种度量，同时还能对表型进行准确分类。
