Prediction of Protein Thermostability by an Efficient Neural Network Approach
Journal Title: Journal of Health Management and Informatics - Year 2016, Vol 3, Issue 4
Abstract
Introduction: Manipulation of protein stability is important for understanding the principles that govern protein thermostability, both in basic research and industrial applications. Various data mining techniques exist for prediction of thermostable proteins. Furthermore, ANN methods have attracted significant attention for prediction of thermostability, because they constitute an appropriate approach to mapping the non-linear input-output relationships and massive parallel computing. Method: An Extreme Learning Machine (ELM) was applied to estimate thermal behavior of 1289 proteins. In the proposed algorithm, the parameters of ELM were optimized using a Genetic Algorithm (GA), which tuned a set of input variables, hidden layer biases, and input weights, to and enhance the prediction performance. The method was executed on a set of amino acids, yielding a total of 613 protein features. A number of feature selection algorithms were used to build subsets of the features. A total of 1289 protein samples and 613 protein features were calculated from UniProt database to understand features contributing to the enzymes’ thermostability and find out the main features that influence this valuable characteristic. Results:At the primary structure level, Gln, Glu and polar were the features that mostly contributed to protein thermostability. At the secondary structure level, Helix_S, Coil, and charged_Coil were the most important features affecting protein thermostability. These results suggest that the thermostability of proteins is mainly associated with primary structural features of the protein. According to the results, the influence of primary structure on the thermostabilty of a protein was more important than that of the secondary structure. It is shown that prediction accuracy of ELM (mean square error) can improve dramatically using GA with error rates RMSE=0.004 and MAPE=0.1003. Conclusion: The proposed approach for forecasting problem significantly improves the accuracy of ELM in prediction of thermostable enzymes. ELM tends to require more neurons in the hidden-layer than conventional tuning-based learning algorithms. To overcome these, the proposed approach uses a GA which optimizes the structure and the parameters of the ELM. In summary, optimization of ELM with GA results in an efficient prediction method; numerical experiments proved that our approach yields excellent results.
Authors and Affiliations
Jalal Rezaeenour, Mansoureh Yari Eili, Zahra Roozbahani, Mansour Ebrahimi
Keywords
Related Articles
- EP ID EP306755
- DOI -
- Views 80
- Downloads 0
Real-data comparison of data mining methods in prediction of coronary artery disease in Iran
Introduction: Cardiovascular diseases are currently of broad prevalence and constitute one of the major causes of mortality in different societies. Angiography is one of the most accurate methods to diagnose heart diseas...
The impact of organizational culture on employees’ organizational silence In Shiraz University of Medical Sciences
Introduction: Organizational Culture is one of the most important factors that can change the climate of silence. The main aim of this research was to investigate the influence of organizational culture on employees’ org...
Evaluation of the structure of websites of educational hospitals of Fars province in 2016
Introduction: In the recent years, evaluation of websites has become one of the main organizational instruments for the relationship between provision of services for customers and beneficiaries. Despite the high costs f...
Assessment of private hospital portals: A conceptual model
Introduction: Hospital portals, as the first virtual entry, play an important role in connecting people with hospital and also presenting hospital virtual services. The main purpose of this article was to suggest a conce...
Evaluating Physicians and Nurses’ Satisfaction with Computerized Physician Order Entry System in Iran
Background: An important application in health care system is computerized physician order entry system (CPOE) which improves the quality of patient’s care. Given that the users’ satisfaction is necessary in predicting t...