Plant responses to environmental change are mediated via changes in cellular metabolomes. However, <5% of signals obtained from tandem liquid chromatography mass spectrometry (LC-MS/MS) can be identified, limiting our understanding of how different metabolite classes change under biotic/abiotic stress. To address this challenge, we performed untargeted LC-MS/MS of leaves, roots and other organs of Brachypodium distachyon, a model Poaceae species, under 17 different organ-condition combinations, including copper deficiency, heat stress, low phosphate and arbuscular mycorrhizal symbiosis (AMS). We used a combination of information theory-based metrics and machine learning-based identification of metabolite structural classes to assess metabolomic changes. Both leaf and root metabolomes were significantly affected by the growth medium. Leaf metabolomes were more diverse than root metabolomes, but the latter were more specialized and more responsive to environmental change. We also found that one week of copper deficiency shielded the root metabolome, but not the leaf metabolome, from perturbation due to heat stress. Using a recently published deep learning based method for metabolite class predictions, we analyzed the responsiveness of each metabolite class to environmental change, which revealed significant perturbations of various lipid classes and phenylpropanoids such as cinnamic acids and flavonoids. Co-accumulation analysis further identified condition-specific metabolic biomarkers. Finally, to make these results publicly accessible, we developed a novel visualization platform on the Bioanalytical Resource website, where significantly perturbed metabolic classes can be readily visualized. Overall, our study illustrates how emerging chemoinformatic methods can be applied to reveal novel insights into the dynamic plant metabolome and plant stress adaptation.