The human blood glucose system is one of the most important systems of the human body, as energy transport is fulfilled through this complex endocrine control process. Because of its great importance, many models were published, most of them with phenomenological approach. The current paper focuses on a new molecular model published recently which is capable of describing the normal blood glucose household. Type 1 diabetes can be modeled by transforming the original model, then soft computing based controller is designed. Rough rule base is generated with subtractive clustering which is later followed by its refinement by parameter tuning. As a result, an Adaptive Neuro-Fuzzy Inference System (ANFIS) is designed. A simple absorption model is presented in order to test the designed controller for different absorption curves. Simulation results are in accordance with the behavior of the healthy human blood glucose system.