A novel predicting algorithm for Thermostable Proteins based on Hurst exponent and Maximized L-measure

Establishing a good algorithm for predicting temperature of thermostable proteins is an important issue. In this study, a new thermostable proteins prediction method by using Hurst exponent and Choquet integral regression model with respect to maximized L-measure is proposed. The main idea of this method is to integrate the physicochemical properties, long term memory property and Choquet integral regression model with respect to maximized L-measure for amino symbolic sequences of different lengths. For evaluating the performance of this new algorithm, a 5-fold Cross-Validation MSE is conducted. Experimental result shows that this new prediction algorithm is better than the Choquet integral regression model with respect to other well known fuzzy measure, Lambda-measure, P-measure, and L-measure, respectively and the traditional prediction models, ridge regression and multiple linear regression models, respectively. Key-Words: Hurst exponent, Lambda-measure, P-measure, L-measure, Maximized L-measure