We aimed to demonstrate the relevance of integrative data analysis methods in answering questions in animal production. We also present a case study of heat stress in dairy small ruminants that integrates metabolomic data with physiological data. We used a univariate mixed model to estimate effects of environmental temperature, time of the day, week and period with the productive and physiological variables. Regarding metabolomic data set, we carried out a summary and a quality control in R. Afterwards, data are exported to MetaboAnalyst and a projection to latent structures-discriminant analysis to extract via linear combination of original variables the information that can predict the class membership. The integration method was an unsupervised multiple kernel learning for heterogeneous data integration. The method can combine several kernels into one meta-kernel in an unsupervised framework. On average, BT was greater in HS, depressed DMI, lost BW and decreased milk fat, protein and lactose content compared to TN goats. No differences were observed in blood albumin concentration. HS lowered blood NEFA, and increased BHBA. However, blood insulin concentration was not affected by HS conditions. Regarding metabolomics, the PLS-DA scores plot showed a distinguishable separation between HS and TN datasets. Similarities to productive variables, the most correlated to this kernel are the blood biochemistry and 1HNMR kernels and that, BT and RR provides a different image of the impact of these variables on productive variables. The data integration methods are recommended to detected patterns of correlation between data sets of interest for further processing.