دانلود رایگان مقاله انگلیسی شبکه عصبی مصنوعی پیشرفته برای شناخت رشته پروتئین و پیش بینی کلاس ساختاری - الزویر 2018

ABSTRACT

In Bioinformatics Protein Fold Recognition (PFR) and Structural Class Prediction (SCP) is a significant problem in predicting protein with a three dimensional structure. Extraction of valuable features of protein that consists of 20 amino acids to acquire more desirable classifiers is fundamental to this PFR and SCP. Feature extraction technique predominantly exploits Forward Consecutive Search Scheme (FCS) that supplements syntacticalbased, evolutionary-based and physicochemical-based information. In this research work, a classifier known as Enhanced Artificial Neural Network (ANN) is employed as it is more efficient than Forward Consecutive Search scheme in order to improve the performance of PFR and SCP. The Enhanced ANN algorithm is an improved version of Artificial Neural Network when compared with various existing algorithms such as Support Vector Machine (SVM), ANN, K-Nearest Neighbor (KNN) and the Bayesian. The experiments are conducted on four datasets namely DD, EDD, TG and RDD. Ultimately, the statistical imputation of Enhanced ANN algorithm hypothesizes gives better results than other algorithms to improve the performance of PFR and SCP.

Conclusion

In Structural Bioinformatics the prediction of three dimensional structure of protein without using these PFR and SCP becomes a very difficult task. Sometimes not correctly folded or structured proteins produce many diseases in living organisms. Predicting the protein structure is mainly used to avoid the diseases that arise in the living cells. Several methods have been introduced to overcome this problem but still some issues persist. In this research work, to improve the performance of PFR and SCP the existing feature extraction techniques such as syntactical-based information and evolutionary-based information are not sufficient. In addition, here we are extracting the features from protein sequence by combining existing techniques with physico-chemical based information using FCS. To classify these extracted features efficiently the Enhanced Artificial Neural Network Algorithm has been introduced. The real protein sequences with unique length are used to test the enhanced algorithm. The results are compared with four existing algorithms such as DD, EDD, TG and RDD. The Enhanced Artificial Neural Network provides higher accuracy than others. In future, classification can be done with the more syntactical and evolutionary features and a new feature extraction method can be introduced to supplement existing feature techniques efficiently. Divergent objectives may be advanced to find better solutions for PFR and SCP.