Rab GTPases are the largest family of small GTPases, with 66 members in humans, and play essential roles in membrane trafficking by recruiting effector proteins to the correct membrane at the correct time. Indeed, many proteins involved in membrane trafficking form direct interactions with Rab GTPases as either Rab effectors, or Rab activators and exchange factors; thus, identifying proteins which interact with Rabs can provide useful insights to the mechanisms underlying protein trafficking processes. Recently, AlphaFold2 has emerged as a useful way of not only modelling the structures of proteins, but also for the identification of novel interactions between proteins. We have used AlphaFold2 to triage published proteomics datasets to identify interactors of Rab GTPases. For the 20 Rabs tested thus far, AlphaFold was able to model 121 interactions with high confidence, including both known interactions and those which are unreported in the literature. In vitro validation for several of these interactions confirms that highly confident AlphaFold2 models do indeed correspond to real interaction partners. Notably, our modelling has shown that several syntaxin family proteins (which act as SNAREs in membrane fusion) interact with Rab GTPases. Furthermore, we have found that the BEACH domain—a highly conserved domain of unknown function—interacts with Rab GTPases. Surprisingly, both our AlphaFold2 models and in vitro assays suggest that the BEACH domain is actually functioning as a GTPase activating protein (GAP), rather than an effector. Overall, these findings demonstrate that pairing AlphaFold2 with proteomics datasets is a powerful method for the discovery of novel protein-protein interactions.