Regensburg 2025 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

BP: Fachverband Biologische Physik

BP 14: Poster Session I

BP 14.7: Poster

Dienstag, 18. März 2025, 10:00–12:30, P3

Exploring coarse graining RNA force fields via Machine Learning — •Anton Dorn¹ and Alexander Schug^{1, 2} — ¹Forschungszentrum Jülich, Jülich, Germany — ²KIT Scientific Computing Center, Karlsruhe, Germany

In Protein structure prediction there have been massive improvements recently with the help of machine learning. In RNA structure prediction however the situation is less ideal due too much sparser experimental data. Here we attempt to solve a modified version of the problem by determining a coarse-grained RNA force field for Molecular Dynamics simulations. The data sparsity can here be alleviated by atomistic RNA simulations using proven and established force fields. In a first step we show the viability of this approach with a limited scenario of only small RNA molecules. For this we adapt the invariant Graph Neural Network architecture, cgSchnett.

Keywords: RNA; Machine Learning; Coarse graining; Graph neural network