An evolutionary algorithm for inverse RNA folding inspired by Lévy flights

A Lévy flight is a random walk with step sizes that follow a heavy-tailed probability distribution. This type of random walk, with many small steps and a few large ones, has inspired many applications in genetic programming and evolutionary algorithms in recent years, but is yet to be applied to RNA design. Here we study the inverse folding problem for RNA, viz. the discovery of sequences that fold into given target secondary structures. We implement a Lévy mutation scheme in an updated version of aRNAque, an evolutionary inverse folding algorithm, and apply it to the design of RNAs with and without pseudoknots. We find that the Lévy mutation scheme increases the diversity of designed RNA sequences and reduces the average number of evaluations of the evolutionary algorithm. The results show improved performance on both Pseudobase++ and the Eterna100 datasets, outperforming existing inverse folding tools. We propose that a Lévy flight offers a better standard mutation scheme for optimizing RNA design.