Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
This work addresses the problem of slow and expensive simulations for photoswitchable compounds like azobenzene derivatives, enabling faster virtual screening for drug discovery and materials science, though it is incremental as it builds on existing machine learning potentials for a specific domain.
The researchers tackled the challenge of simulating light-induced chemical processes for photoswitchable molecules by developing a diabatic artificial neural network (DANN) that is six orders of magnitude faster than quantum chemistry methods, enabling virtual screening of 3,100 hypothetical molecules and identifying novel species with high predicted quantum yields.
Light-induced chemical processes are ubiquitous in nature and have widespread technological applications. For example, photoisomerization can allow a drug with a photo-switchable scaffold such as azobenzene to be activated with light. In principle, photoswitches with desired photophysical properties like high isomerization quantum yields can be identified through virtual screening with reactive simulations. In practice, these simulations are rarely used for screening, since they require hundreds of trajectories and expensive quantum chemical methods to account for non-adiabatic excited state effects. Here we introduce a diabatic artificial neural network (DANN) based on diabatic states to accelerate such simulations for azobenzene derivatives. The network is six orders of magnitude faster than the quantum chemistry method used for training. DANN is transferable to azobenzene molecules outside the training set, predicting quantum yields for unseen species that are correlated with experiment. We use the model to virtually screen 3,100 hypothetical molecules, and identify novel species with extremely high predicted quantum yields. The model predictions are confirmed using high accuracy non-adiabatic dynamics. Our results pave the way for fast and accurate virtual screening of photoactive compounds.