Studying perturbations in the gut ecosystem using animal models of disease continues to provide valuable insights into the role of the microbiome in various physiological conditions. However, understanding which of these changes are consistent across different animal models, and hence potentially translatable to human populations remains a major unmet challenge in the field. Nonetheless, in relatively limited cases have the same interventions been studied in two animal models in the same laboratory. Moreover, such studies typically examine only one data layer and one-time point. Here we show the power of integrating microbiome (measured by 16S rRNA amplicon profiling) and metabolome (measured by untargeted LC-MS/MS) data over time in identifying features that relate two different mouse models of atherosclerosis: ApoE and Ldlr knockouts (ApoE-/-; Ldlr-/-), under conditions of intermittent hypoxia and hypercapnia (IHH), a model for human obstructive sleep apnea. Using Random Forest classifiers trained on each data layer, we show excellent accuracy values in predicting IHH-exposure within ApoE and Ldlr knockout models, and in cross-applying predictive features found in one animal model to the other. Some of the key microbes and metabolites that were top predictors of IHH-exposure across animal models included bacterial species from the order Clostridiales, alpha-muricholic acid (bile acid) and vaccenic acid (fatty acid), providing a refined set of biomarkers reproducibly associated with this intervention. The results highlight that different animal models of disease can be related to one another using supervised machine learning techniques, especially when time series multi-omics data are available and provide a pathway towards identifying robust microbiome and metabolome features that underpin translation from animal models to understanding human disease.