EFFICIENT PROTEIN STRUCTURAL CLASS PREDICTION VIA CHAOS GAME REPRESENTATION AND RECURRENT NEURAL NETWORKS

Predicting the structural class of a protein from its amino acid sequence is among the most significant problems in bioinformatics, especially when proteins with low sequence similarity are met. While prior works achieved notable accuracy in this task with recurrent neural networks, their approach mostly relies on extracting a large quantity of features, impacting the efficiency and reliability of the prediction. Thus, the herein work introduces an efficient and accurate classification scheme based on chaos game representation and recurrent neural networks. The proposed scheme achieves comparable results with the related work based on a significantly low-dimensional representation of the feature space.