Protein Structural Classes Prediction Based On Convolutional Neural Network Classifier with Feature Selection of Hybrid PSO-FA Optimization Approach
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 10, Pages 252-265
AbstractProtein can be classified in different classes like A (All α), B (All β), C (α+β), and D (α/β). A lot of work has been performed for analyzing the Sub-cellular localization of protein structure. The visualization of protein folding into compact conformation is evaluated. In the present work different algorithms like particle swarm optimization (PSO), Firefly algorithm (FFA) and K-Mean clustering algorithms are used to classify different structures of protein. A Conventional neural network (CNN) classifier is utilized for analyzing and comparing different protein classes in terms of SVM classifier available conventionally in terms of various performance parameters. Near 100 % accuracy, sensitivity, specificity, and MCC values are obtained for class A & class B protein structures. However, somewhat lower values of these parameters are obtained for class C and class D protein structures. CNN classifier proved better than SVM classifier and can be helpful in predicting the protein structures. A hybrid PSO-FFA algorithm is used to extract the features for different classes of protein. Structures of four classes of protein are evaluated in terms of scoring spaces and fitnessvalues.
- Article View: 228
- PDF Download: 353