Volatile organic compounds (VOC) emitted by food products are decisive for the perception of their aroma and taste. The analysis of these gaseous matrices is traditionally done by detection and quantification of few dozens of characteristic markers. Emerging direct injection mass spectrometry (DIMS) technologies, such as PTR-MS or SIFT-MS, offer rapid analysis of complex gas matrices based on a soft ionization of volatile compounds without previous separation. The increase of selectivity offers by the use of several precursor ions coupled with untargeted analysis increases the potential power of these instruments. However, the analysis of complex gaseous matrix by DIMS results on the one hand in a large number of ion conflicts, making the quantification of markers very difficult, and on the other hand a large volume of data for every sample. A solution based on the shift toward the omics domains of these analyses, where the number of variables is much higher than the number of samples, requires the use of adapted extraction and statistical analysis tools. In this work, we used SIFT-MS to determine the volatile fingerprints of Ossau-Iraty PDO sheep milk cheeses and applied mixOmics statistical methods for results exploitation. This methodology allowed to illustrated the typicality brought by each producer, the reproducibility of the manufacturing processes and the impact of the animals' diet on the final product.