Due to the strong scattering and low absorption of light in biological tissues, the inverse problem of bioluminescence tomography (BLT) is ill-posed. Hybrid regularization constraints can effectively alleviate the inherent ill-posedness of the BLT inverse problem. However, the hybrid regularization of traditional algorithms involves multiple parameter determinations, and it is difficult to select parameters manually. This paper proposes deep unfolding based on U-Net graph-guided hybrid regularization (DUnet-GGHR) method for BLT. The gradient update step in the traditional GGHR algorithm is reformulated as a flexible gradient descent update module for automatic learning. At the same time, the soft threshold calculation step in the traditional GGHR algorithm solution process is expanded into a proximal mapping module for training. A series of reconstruction experiments have verified that the proposed DUnet-GGHR model performs better than other end-to-end deep unrolling comparison methods in tumor localization, morphology restoration, and energy recovery. At the same time, the mathematical process is combined with the deep neural network to improve the interpretability and generalization of the network, reduce training data, and speed up the calculation.