We will discuss two novel deep neural network-based approaches for molecular simulation. The first is to obtain a reactive forcefield of neural network potentials based on explicit semi-classical electrons, motivated by our desire to model explicit oxidation states in electron transfer reactions, but also to have more transferable networks in general. The second application is to find descriptive collective variables from simulation trajectories of molecular transitions. Rather than targeting committor probabilities or a maximum transition flux, we target a prediction of the molecular structure.

Deep neural networks for molecular modeling and analysis of reactive trajectories

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.