Hybrid Cellular Automata with CNN for the Prediction of Secondary Structure of Protein

Secondary structure of protein is the dynamic and real-time problem in bioinformatics. Determining the secondary structure of protein consists of coil, beta-sheet, and alpha-helical regions which is crucial to comprehending their interactions and functions. Recent years have seen encouraging developments in the prediction of protein secondary structure from amino acid sequences using machine learning approaches. In order to improve secondary protein structure prediction accuracy, this work presents a unique method that combines the advantages of convolutional neural networks (CNN) with Hybrid Cellular Automata (HCA). Benchmark protein datasets are used to train and assess the suggested hybrid model, which shows better prediction performance than more conventional techniques. An inventive method for capturing the local and global structural patterns in protein sequences is provided by the combination of CNN and HCA.