Séminaire virtuel: vendredi 10 janvier 2025
Denis Pallez (Université Côte d’Azur / CNRS / I3S)

Lien Zoom

  • Meeting ID: 867 6409 6440
  • passcode: 149120

13h00 - 13h50 – Denis Pallez

Hybrid GRNs parametrization with Artificial Evolution & Reinforcement Learning

Genetic regulatory network (GRN) modelling aims at studying and understanding the molecular mechanisms that enable the organism to perform essential functions ranging from metabolism to environmental disturbance adaptation. Studying the dynamics of these systems opens new perspectives with crucial applications in fundamental biology, pharmacology, medicine, or chronotherapy for instance, which tries to choose the best time of day to administer the medication in order to limit the side effects while preserving the therapeutic effects. Numerous modelling frameworks have been proposed for representing GRN such as differential frameworks, stochastic ones, or discrete ones. The bottleneck in the modelling approach is the search for model parametrisations that are consistent with the available biological knowledge, often represented as irregularly spaced time series of observable events. In this work, we have chosen hybrid frameworks (hGRN), which add to the discrete ones the time spent in each of the discrete states leading to the search of piecewise linear trajectories in a multidimensional space. These trajectories, each governed by a parametrisation, must respect the observed biological data, which have been previously and manually interpreted as a set of constraints based on Hoare logic. A previous work logically applied continuous Constraint Satisfaction Problem (CSP) solvers to identify all valid trajectories, but faced difficulties in extracting solutions, especially when the number of genes exceeded 3 genes. Rather than characterising all solutions, we will present in this presentation how we adapt metaheuristics to sample the search space with as much diversity as possible. First, artificial evolution is adapted by transforming the constrained satisfaction problem into an unconstrained optimisation problem combined with a penalty fitness function. Several metaheuristics are then compared. Second, we treat the problem as a sequential decision problem using reinforcement learning with Monte Carlo tree search algorithms (MCTS).


Dernière modification le 06/12/2024