RNA Flexibility Prediction With Sequence Profile And Predicted Solvent Accessibility

Structural flexibility plays an essential role in many biological processes,it is essential for protein catalysis and allostery and for secondary structure formation and the folding of RNA catalysts as well as protein-RNA recognition.B-factor is an important indicator to measure the flexibility of protein or RNA structures.Determining the flexibility of structured biomolecules is important for understanding their biological functions.B-factor was widely used in the analysis of protein disorder region,protein folding rate,protein active sites,and protein thermal stability.Since the experimental methods to determine B-factor are too time consuming,the design of B-factor prediction algorithm is a challenging and significant project.At present,Many methods have been developed to predict protein B-factors,but few studies have been done for RNA B-factor prediction.There are only two studies before our method.In this paper,we proposed a new method RNAbval to predict RNAB-factors using random forest.The method was developed using a comprehensive set of features,including the one hot vector,sequence profile,predicted solvent accessibility and secondary structure.RNAbval yields Pearson's correction coefficient at 0.5904 for fivefold cross validation and 0.6061 for the first independent test.RNAbval achieved an improvement of 9.2-20.5%over the state-of-the-art method on two benchmark test datasets.It shows the superiority of our method.Finally,we built a webserver for the convenience of people to use.The input is the RNA sequence and the output is predicted RNA B-factor for each base.The proposed method is available at:http://yanglab.nankai.edu.cn/RNAbval/.