Portela, F. | bioRxiv Science

bioRxiv2018

An unexpectedly effective Monte Carlo technique for the RNA inverse folding problem

Solving the RNA inverse folding problem, also known as the RNA design problem, is critical to advance several scientific fields like bioengineering, yet existing approaches have had limited success. The problem has several features that resist traditional computational techniques, such as its exponential complexity and the chaotic behavior of its cost function. Although some state-of-the-art AI approaches have reported promising results, all existing computational methods substantially underperform expert human designers. I combine a different technique, Nested Monte Carlo Search (NMCS), with domain-specific knowledge to create an algorithm that outperforms all prior published methods by wide margins and solves 95 of the 100 puzzles listed in a recently proposed RNA solving difficulty benchmark.

bioinformatics↗

bioRxiv2018

EternaBrain: Automated RNA design through move sets from an Internet-scale RNA videogame

Emerging RNA-based approaches to disease detection and gene therapy require RNA sequences that fold into specific base-pairing patterns, but computational algorithms generally remain inadequate for these secondary structure design tasks. The Eterna project has crowdsourced RNA design to human video game players in the form of puzzles that reach extraordinary difficulty. Here, we present an eternamoves-large repository consisting of 1.8 million of player moves on 12 of the most-played Eterna puzzles as well as an eternamoves-select repository of 30,477 moves from the top 72 players on a select set of more advanced puzzles. On eternamoves-select, a multilayer convolutional neural network (CNN) EternaBrain achieves test accuracies of 51% and 34% in base prediction and location prediction, respectively, suggesting that top players moves are partially stereotyped. We then show that while this CNNs move predictions are not enough to solve numerous new puzzles, inclusion of six additional strategies compiled by human players solves 61 out of 100 independent puzzles in the Eterna100 benchmark. This EternaBrain-SAP performance is better than previously published methods and in the middle of the performance range of newer algorithms developed by Eterna participants and other groups. Our study provides useful lessons for efforts to achieve human-competitive performance with automated RNA design algorithms.

bioinformatics↗