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

CPP: Fachverband Chemische Physik und Polymerphysik

CPP 21: Modeling and Simulation of Soft Matter II

CPP 21.2: Vortrag

Dienstag, 18. März 2025, 14:15–14:30, H34

Navigating Chemical Space: An Active Learning Strategy Using Multi-Level Coarse-Graining — •Luis Walter and Tristan Bereau — ITP, Heidelberg University

Exploring the vast chemical compound space remains a significant challenge due to the immense number of possible molecules and limited scalability of conventional screening methods. To approach chemical space exploration more effectively, we have developed an active learning-based method that uses transferable coarse-grained models to compress chemical space into varying levels of resolution. By using multiple representations of chemical space with different coarse-graining resolutions, we balance combinatorial complexity and chemical detail. To identify target compounds, we first use an autoencoder to transform the discrete molecular spaces into continuous latent spaces. We then perform Bayesian optimization within these latent spaces, using molecular dynamics simulations to calculate target free energies of the coarse-grained compounds. This multi-level approach allows for an effective balance between exploration at lower and exploitation at higher resolutions. We demonstrate the effectiveness of our method by optimizing molecules to enhance phase separation in phospholipid bilayers. Our funnel-like strategy not only suggests optimal compounds, but also provides insight into relevant neighborhoods in chemical space. We show how this neighborhood information from lower resolutions can be used to guide the optimization at higher resolutions, thereby providing an efficient way to navigate large chemical spaces for free energy-based molecular optimization.

Keywords: chemical space; coarse-graining; bayesian optimization; molecular dynamics simulations; machine learning