Macs in Chemistry

Insanely Great Science

NMR shift prediction using machine learning competition results


A while back a Kaggle competition called Champs for developing ML models that predict NMR coupling constants with DFT accuracy was initiated

"Champs received 47,800 ML model predictions from 2,700 teams in 84 countries. Within 3 weeks, the Kaggle community produced models with comparable accuracy to our best previously published ‘in-house’ efforts. A meta-ensemble model constructed as a linear combination of the top predictions has a prediction accuracy which exceeds that of any individual model, 7-19x better than our previous state-of-the-art."

More details on Computational Chemistry Highlights.

blog comments powered by Disqus