Predicting and Learning RNA Secondary Structures

It is of great signicance to develop an ecient software system for higher-level structural prediction in RNA/protein sequences. Speaking of RNA secondary structure prediction, it is inevitably required that a prediction system must have an ability to deal with so-called "pseudoknot " structures, one of the most typical and important constructs found in vivo, while no eective system is yet reported for predicting RNA secondary structures involving in pseudoknots. We are developing prediction systems for RNA secondary structures that can handle pseudo-knots in an elegant manner, where the developing systems are constructed based on the following two ways. Prediction System Using Tree Grammars: In the previous work[3], we developed a parsing algorithm for RNA modeling grammars, and applied it to some computational problems concerning RNA secondary structures. In this work, we prototype a prediction system for RNA secondary struc-tures which is based on minimizing the free-energy change associated with base pairings and loop structures. One of the major advantages of this system is its capability of predicting structures which include pseudoknots. We evaluate the system by presenting how long sequences it can process and how long and ho