Send to

Choose Destination
PLoS Comput Biol. 2018 Jun 21;14(6):e1006176. doi: 10.1371/journal.pcbi.1006176. eCollection 2018 Jun.

Solving the RNA design problem with reinforcement learning.

Author information

Department of Bioengineering, Stanford University, Stanford, CA, United States of America.
Department of Chemistry, Stanford University, Stanford, CA, United States of America.
Department of Computer Science, Stanford University, Stanford, CA, United States of America.


We use reinforcement learning to train an agent for computational RNA design: given a target secondary structure, design a sequence that folds to that structure in silico. Our agent uses a novel graph convolutional architecture allowing a single model to be applied to arbitrary target structures of any length. After training it on randomly generated targets, we test it on the Eterna100 benchmark and find it outperforms all previous algorithms. Analysis of its solutions shows it has successfully learned some advanced strategies identified by players of the game Eterna, allowing it to solve some very difficult structures. On the other hand, it has failed to learn other strategies, possibly because they were not required for the targets in the training set. This suggests the possibility that future improvements to the training protocol may yield further gains in performance.

[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center