The paradigm of data science has increasingly been applied to chemistry and biology thanks to wide-spread availability of empirical data and high-performance computing resources. Within domains like computational chemistry, the vital role of experimental data is manifest: experimental data are readily issued to parametrize molecular dynamics (MD) force fields, predict secondary structural features of proteins and relate the evolutionary histories of organisms. Commonly, the use of data scientific methods moves unilaterally toward aiding <i>in silico</i> research, although many opportunities exist for the contrary. Here, we present our efforts to bridge the gap between theory and experiment. Semi-empirical chemical shift prediction, oft used by nuclear magnetic resonance (NMR) spectroscopists to aid peak assignment, is used directly as a correction to the MD force field, refining atomic coordinates along the prediction model’s first derivative gradient to gain insight into the dynamic and structural implications of experimental results. Further, we show a GPU-enabled, convolutional neural network (CNN) capable of predicting chemical shifts and torsion angles with high accuracy, providing means of assignment validation to NMR spectroscopists and structural validation to computational chemists. Lastly, a deep-learning solution to classifying electron micrographs of human immunodeficiency type 1 (HIV-1) is presented, which can identify and categorize viral particles based on their respective maturities above 90% accuracy.<br/>

Data-driven solutions to problems in chemistry: Aiding experiments with deep learning and guiding protein simulations with empirical data

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.