The scientific enterprise enriches the debate about models. In particular, in the field of structural biology, the deep-learning neural network system called AlphaFold has been applied for many purposes. It allows us to predict a protein’s structure with high accuracy. I will present the system's output, namely the proteins' models, in light of the discussion of structure representation and argue for a specific kind of representational relation holding between the predicted model structure and its target-system. By doing so, I will criticise the artifactual approach advanced by Knuuttila (2021) and present the features that characterise the predicted structures of AlphaFold as representational models.
