Designing RNA Sequences by Self-play

Stephen Obonyo, Nicolas Jouandeau, Dickson Owuor

2022

Abstract

Self-play (SP) is a method in Reinforcement Learning (RL) where an agent learns from the environment by playing against itself until the policy and value functions converge. The SP-based methods have recorded state-of-the-art results in playing different computer games such as Chess, Go and Othello. In this paper, we show how the RNA sequence design problem where a sequence is designed to match a given target structure can be modelled through the SP while performing the state-value evaluation using a deep value network. Our model dubbed RNASP recorded the best and very competitive results on the benchmark RNA design datasets. This work also motivates the application of the self-play to other Computational Biology problems.

Download


Paper Citation


in Harvard Style

Obonyo S., Jouandeau N. and Owuor D. (2022). Designing RNA Sequences by Self-play. In Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA; ISBN 978-989-758-611-8, SciTePress, pages 305-312. DOI: 10.5220/0011550300003332


in Bibtex Style

@conference{ncta22,
author={Stephen Obonyo and Nicolas Jouandeau and Dickson Owuor},
title={Designing RNA Sequences by Self-play},
booktitle={Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA},
year={2022},
pages={305-312},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011550300003332},
isbn={978-989-758-611-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2022) - Volume 1: NCTA
TI - Designing RNA Sequences by Self-play
SN - 978-989-758-611-8
AU - Obonyo S.
AU - Jouandeau N.
AU - Owuor D.
PY - 2022
SP - 305
EP - 312
DO - 10.5220/0011550300003332
PB - SciTePress