Non-canonical Imperfect Base Pair Predictor: The RNA 3D Structure Modeling Process Improvement

RNA is a large group of macromolecules involved in many essential cellular processes. They can form complex secondary and three-dimensional structures, and their biological functions highly rely on their forms. Therefore a high quality RNA structure determination is a key process to address RNA functions and roles in molecular pathways. However, in many cases the structure cannot be experimentally solved or the process is too expensive and laborious. This problem can be avoid using bioinformatics methods of computational RNA structure prediction. Such applications have been developed, however the quality of predictions, especially for large RNA structures, still remains too low. One of the most important aspects in RNA 3D model building is the intramolecular interactions identification and validation. In this work I propose a method which can improve this stage of model building, and should result in creation of better final three-dimensional RNA models. In my work I constructed a predictor that can identify both canonical and non-canonical base pair interactions within a given structure. The main advantages of this predictor are: 1) the ability to work on incomplete input structures, and 2) the ability to correctly predict base pair type even for imperfect (fuzzy) input atoms coordinates. The predictor is based on the set of SVM multi-class classifiers. For each input base pair the classifier chooses one of 18 recognized pair types. The predictor was trained on the experimental high quality data and tested on different, imperfect and incomplete (coarse-grained) structures. The average quality of predictor for tested fuzzy nucleotide pairs is at the level about 96% of correct recognitions.