Artificial Intelligence for mRNA Sequence optimisation : Reinforcement learning and genetic algorithm for synonymous mRNA codon optimisation

Mbengue, Khaly
(2026)

Files

Mbengue_61822100_2026.pdf
  • UCLouvain restricted access
  • Adobe PDF
  • 2.89 MB

Details

Supervisors
Macq, Benoît
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] : ingénieur civil en science des données, à finalité spécialisée: analyse de données
Abstract
enThis thesis studies the computational optimisation of mRNA sequences for therapeutic applications. Since the genetic code is degenerate, the same protein can be encoded by an exponentially large number of synonymous sequences. Three approaches are implemented and compared: a greedy baseline, a genetic algorithm and a reinforcement learning agent. A hybrid strategy combining both methods is also explored.