Protein Function Prediction with Deep Neural Learning

Background: The function of protein is directly related to its structure, and plays a pivotal role in the entire life process. The protein interaction network controls almost all biological cell processes while fulfilling most of the biological functions. In fact, protein function prediction can be regarded as a multi-label classification problem to fill the gap between a huge number of protein sequences and known functions. It is not only a key issue in related research fields, but also a long-standing challenge. Protein function prediction with Deep Neural Network (DNN) almost study data set with small scale proteins based on Gene Ontology (GO). They usually dig relationships between protein features and function tags. It still needs further study for large-scale protein to find useful prediction approaches.Methods: This paper proposed a protein function prediction approach with DNN which used Grasshopper Optimization Algorithm (GOA), Intuitionistic Fuzzy c-Means (IFCM), Kernel Principal Component Analysis (KPCA) and DNN (IGP-DNN). The features in protein function modules were extracted by combining GOA and IFCM. The KPCA was used to reduce the dimensions of features in protein properties. Both features were integrated to enrich the features information and the integrated features were input into the DNN model. The protein function modules were classified to predict function by computing in hiding level of DNN.Results and conclusion: IGP-DNN combines the advantages of IFCM-GOA and DNN. The combination of IFCM and GOA not only avoids falling into local optimal when extracting function module feature and reduces the over-sensitivity of IFCM for clustering center, but also improves the precision of the protein function module feature extraction. This paper proposes a protein function prediction approach based on DNN. In the model, protein features are composed of the protein function module features that are extracted by using IFCM-GOA and the protein property features that are reduced dimensions by using KPCA to address the noise sensitivity and the other problems during predicting protein function.