Hierarchical Classification using a Competitive Neural Network for Protein Function Prediction

摘要

Classification is a common task in Machine Learning and Data Mining. The protein Junction prediction can be treated as a classification problem. As protein's functions may be arranged in a hierarchy of classes, predicting the protein function is treated as a problem of hierarchical classification. This paper presents an algorithm for hierarchical classification using the global approach, called Hierarchical Classification using a Competitive Neural Network (HC-CNN) for Protein Function Prediction. This algorithm is based on a Competitive Neural Network. It was tested in eight datasets based on Funcat and compared with algorithms from literature. The results show that the HC-CNN is an alternative in problems of hierarchical classification.