# Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential

arXiv: https://arxiv.org/abs/2108.04879 · HTML: https://mlsanity.com/paper/2108.04879/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 174 references that are in the map.
- First posted on arXiv 10 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Directional Message Passing for Molecular Graphs](https://mlsanity.com/paper/2003.03123/) (2020)
- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects](https://mlsanity.com/paper/2105.00304/) (2021)
- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features](https://mlsanity.com/paper/2007.08026/) (2020)
- [Machine learning for electronically excited states of molecules](https://mlsanity.com/paper/2007.05320/) (2020)
- [Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks](https://mlsanity.com/paper/2101.11588/) (2021)
- [Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics](https://mlsanity.com/paper/2002.07264/) (2020)
- [Machine learning enables long time scale molecular photodynamics simulations](https://mlsanity.com/paper/1811.09112/) (2018)
- [Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces](https://mlsanity.com/paper/2011.02680/) (2020)
- [Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space](https://mlsanity.com/paper/2007.07684/) (2020)

## Built on by (most cited first, 7 of 7)

- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [NAPA: Intermediate-level Variational Native-pulse Ansatz for Variational Quantum Algorithms](https://mlsanity.com/paper/2208.01215/) (2022)
- [Thermal half-lives of azobenzene derivatives: virtual screening based on intersystem crossing using a machine learning potential](https://mlsanity.com/paper/2207.11592/) (2022)
- [Machine Learning Nonadiabatic Dynamics: Eliminating Phase Freedom of Nonadiabatic Couplings with the State-Intraction State-Averaged Spin-Restricted Ensemble-Referenced Kohn-Sham Approach](https://mlsanity.com/paper/2410.22801/) (2024)
- [OpenQDC: Open Quantum Data Commons](https://mlsanity.com/paper/2411.19629/) (2024)
- [A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors](https://mlsanity.com/paper/2505.23344/) (2025)
- [Computational Design and Experimental Validation of Photoactive PARP1 Inhibitors](https://mlsanity.com/paper/2604.24634/) (2026)

## Abstract (arXiv)

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.