قالب وردپرس درنا توس
Home / Science / New AI tool captures the strategies of the top players in the RNA video game

New AI tool captures the strategies of the top players in the RNA video game



  New AI tool captures the strategies of top players in RNA video game
Solving a RNA design problem. The predicted fold of an RNA chain as an Eterna video game player changes its sequence to eventually reach a target fold. Picture credits: Koodli et al.

A new artificial intelligence tool captures strategies used by top players of an Internet-based video game to design new RNA molecules. Rohan Koodli and colleagues from the massive open Eterna lab present the tool EternaBrain in PLOS Computational Biology . Eterna is headed by the laboratory of Prof. Rhiju Das at the Stanford University School of Medicine in California.

RNA molecules occur naturally in all living cells and fulfill important biological functions. In recent years, there has been a strong interest in the development of new RNA structures for cancer treatment, CRISPR gene editing and much more. However, each RNA structure consists of a long sequence of four building blocks, and the determination of the exact sequence required to construct a particular structure can be computationally difficult.

In the new study, Koodli, Das, and colleagues examined the Eterna Internet-based video game, a civic science initiative to tackle the computational challenges of RNA design. Eterna presents each player with a target RNA structure and the player tries to find an RNA sequence that allows the finished molecule to fold into the desired shape. Some players outperform the best computer-automated methods to solve these challenges.

Using a record of 1

.8 million designs selected by Eterna players, the researchers discovered an artificial neural network that captures some of the preferences and strategies of these experts. This approach, called EternaBrain, can predict the selection of the best players with a much more accurate accuracy than is possible with random rates. An advanced EternaBrain algorithm provides similar or better performance than previously developed algorithms for solving Eterna challenges.

"Our results suggest that it should be possible to create automated algorithms for computer RNA design that emulate or outperform human RNA designers," says Das. "But we are not there yet, we still have much to learn from players and AI researchers."

Next, researchers will see if they can outperform top players by integrating EternaBrain with other computer-aided approaches to RNA design. "We also hope to be able to apply EternaBrain to more complicated issues that Eterna players solve, including the design of RNA computers and 3-D machines, as well as learning design rules from actual wet laboratory data," says Das.


Magazine for publishing an article by video gamers based on Stanford's online RNA game


Further information:
Rohan V. Koodli et al., Eterna Brain: Automated RNA Design Through Move Sets and Strategies of an RNA Video Game on the Internet, PLOS Computational Biology (2019). DOI: 10.1371 / journal.pcbi.1007059

Provided by
Public Science Library




Quote :
New AI tool captures the strategies of the top players in the RNA video game (2019, 27 June)
retrieved on June 28, 2019
from https://phys.org/news/2019-06-ai-tool-captures-players-strategies.html

This document is subject to copyright. Apart from any fair dealings for the purposes of private study or research, no
Part may be reproduced without written permission. The content is provided for informational purposes only.


Source link