Proteindeki düzensiz bölgelerin hesapsal tahmini

Proteins are one of the most important parts of an organism because of their vital tasks. Hence, it is necessary to know the structure of a protein since it is closely related to its biological function. Studies on structural genomics indicate that numerous protein segments remain unfolded in their native states. Currently these proteins are generally referred to as ?natively unfolded? or ?intrinsically disordered?. Upon noticing that many of these proteins play key role in vital functions and also in some diseases, identification of the disordered regions has became a demanding process for structure prediction and functional characterization of proteins. Therefore, many studies have been motivated on accurate prediction of disorder. Mostly, machine learning techniques have been used for dealing with the prediction problem of disorder due to capability of extracting the complex relationships and correlations hidden in large data sets.In the study, a novel method, named Border Vector Detection and Extended Adaptation (BVDEA) was developed for predicting disorder as an alternative accurate classifier. For attesting the performance of the method, three computational learning techniques and eleven specific tools were used for comparison. In order to perform the predictions, firstly the collected data was prepared by choosing a variety of structural features for proteins. Then, training was executed based on the data by 5-fold cross validation. When compared with the three learning methods of GRNN, LVQ and BVDA, the proposed method gives the best accuracy on classification. Here, BDVEA provides more fast and robust learning as compared to the others. Furthermore, comparison with the other existing disorder predictors demonstrates that the method achieves rather good prediction performance in finding disordered regions of proteins. As a conclusion, it has been shown that the new method provides a significant contribution on predicting disorder and order regions of proteins.