Identification of SNARE Proteins Through a Novel Hybrid Model

SNARE proteins are a large family of membrane fusion proteins. As a lot of human diseases are related to the SNARE proteins, they have attracted people to study them. Traditionally, the SNARE proteins can be identified through bioinformatics techniques, which are expensive and time-consuming. Some researchers attempt to identify the SNARE proteins by the machine learning algorithms. A deep learning model called SNARE-CNN is proposed to predict SNARE proteins. A 2D convolutional neural network is constructed and the Position-Specific Scoring Matrix (PSSM) profile is used to distinguish the SNARE proteins from the other kinds of proteins. Although the SNARE-CNN can achieve high accuracy, the performance of the model still has room to improve. In this paper, a novel hybrid model, that combines the random forest algorithm with the oversampling filter and 188D feature extraction method, is proposed. By trying different combinations of feature extraction methods, filtering methods and classification algorithms, the hybrid model, we proposed, can achieve the best performance among all combinations. Experiments show that the performance of our hybrid model is better than that of the SNARE-CNN model.