Fig. 4From: Accurate classification of membrane protein types based on sequence and evolutionary information using deep learningThe flow of the stacking algorithm. Model_1 refers to the sequence information model, and Model_2 refers to the evolutionary information model. The class probability outputs of two models are combined to serve as a new training set to train the meta-classifier (MLR). When testing unknown membrane protein samples, we take the result of the meta-classifier as the final outputBack to article page