Physics-Informed Neural Networks for Parameter Recovery in the Repressilator Oscillatory Model
Bernat Casajuana, Roger Casals-Franch, Adrián López García de Lomana, Pere Martí-Puig, Jordi Villà-Freixa
This study evaluates the reliability of physics-informed neural networks (PINNs) for parameter recovery in the repressilator model, showing accurate trajectory reconstruction but challenges in parameter estimation due to noise and model assumptions.
bioRxiv · May 15, 2026 · PreprintBioinformatics