RNApred: SVM-Based Prediction of RNA-Binding Proteins Using Binding Residues and Evolutionary Information

RNApred: SVM-Based Prediction of RNA-Binding Proteins Using Binding Residues and Evolutionary Information

RNApred is a computational tool developed for predicting RNA-binding proteins from amino acid sequences.

RNA-binding proteins play important roles in transcription, RNA processing, gene regulation, RNA stability, RNA transport, and cellular localization. RNApred uses support vector machine-based models, RNA-binding residue information, and evolutionary profiles to classify proteins as RNA-binding or non-RNA-binding proteins.

Web Server: https://webs.iiitd.edu.in/raghava/rnapred

Citation

Kumar, M., Gromiha, M. M., and Raghava, G. P. S. SVM based prediction of RNA-binding proteins using binding residues and evolutionary information. Journal of Molecular Recognition, 24, 303-313, 2011.

https://doi.org/10.1002/jmr.1061

About the Research

RNA-binding proteins are proteins that interact with RNA molecules and regulate many essential biological processes. They are involved in ribosome function, spliceosome activity, RNA catalysis, transcriptional regulation, RNA processing, and gene expression control.

Experimental identification of RNA-binding proteins can be difficult and time-consuming. Therefore, RNApred was developed as a sequence-based computational method to predict whether a protein is likely to bind RNA.

Data Compilation: The main dataset contained 377 RNA-binding proteins and an equal number of non-RNA-binding proteins. The study also used independent datasets to evaluate the real-life performance of the prediction models.

Methodology: RNApred uses support vector machine models trained on amino acid composition, dipeptide composition, four-part amino acid composition, and evolutionary information in the form of PSSM profiles. The final hybrid method combines RNA-binding residue prediction using PPRINT with PSSM-400-based SVM prediction.