Study Of RNA Pseudoknotted Secondary Structure Prediction Based On Multi-objective Optimization

RNA was considered to play an important role in expressing inherited information as proteins.To understand how RNA sequences perform their functions,we need to know their structure.Pseudoknot is a kind of important structure in RNA,which is more difficult to be predicted due to modeling difficulties.This paper is mainly about RNA pseudoknotted secondary structure prediction based on multi-objective optimization.ProbKnot algorithm possesses a high accuracy by predicting the secondary structure of pseudoknotted RNA through base-pair probabilities.However,this algorithm only applies base-pair probabilities as a predictable object,which leads to a large number of negative pairs and lower specificity.Experiments predict the secondary structure of RNA by using multi-objective genetic algorithm.Therefore,we can obtain higher specificity by combining the probabilistic model of base pairing in ProbKnot algorithm to improve the overall accuracy.In the experiments,we will first calculate the single-stranded probability as a new predictable object.Next,we use genetic algorithm to cross,mutate and iterate the secondary structure of RNA.Then,we use parallel processing to reduce the running time of genetic algorithms.Finally,we can get the Pareto optimal solutions and higher maximum expected accuracy.The experiment results showed that in the RNA cases,applying this method could achieve an average increase of 4% in the accuracy compared with the current method.This paper provides a new and effective method for predicting RNA secondary structures with pseudoknots.