Deep learning-based classification model for GPR151 activator activity prediction

Abstract

Background: GPR151 is a kind of protein belonging to G protein-coupled receptor (GPCR) family that is closely associated with a variety of physiological and pathological processes. The potential use of GPR151 as a therapeutic target for the management of metabolic disorders has been demonstrated in severalstudies, highlighting the demand to explore its activators further. Activity prediction serves as a vital preliminary step in drug discovery, which is both costly and time-consuming. Thus, the development of reliable activity classification model has become an essential way in the process of drug discovery, aiming to enhance the efficiency of virtual screening. Results: We propose a learning-based method based on feature extractor and deep neural network to predict the activity of GPR151 activators. We first introduce a new molecular feature extraction algorithm which utilizes abag-of-words model in natural language processing to densify the sparse fingerprint vector. Mol2vec method is also used to extract diverse features. Then, we construct three types of deep learning model to enhance the representational capacity of molecules and predicted activity label by five different classifiers. Our method is evaluated on the GPR151 activator dataset built in this paper. The results demonstrate high classification accuracy and stability, with the optimal model Mol2vec-CNN significantly improving performance across multiple classifiers. The svm classifier achieves the best accuracy of 0.92 and F1 score of 0.76 which indicates promising applications for our method in the field of activity prediction. Conclusion: All the experimental results show that the performance of feature extraction algorithm is better than that of the traditional classifiers and the proposed method is appropriately designed.