IMPRESSION -- Prediction of NMR Parameters for 3-dimensional chemical structures using Machine Learning with near quantum chemical accuracy

TL;DR

IMPRESSION uses machine learning trained on quantum chemical data to rapidly and accurately predict NMR parameters from 3D structures, enabling efficient analysis of molecular conformations and isomerism.

Contribution

The paper introduces IMPRESSION, a machine learning system that predicts NMR parameters with near quantum chemical accuracy at a fraction of the computational cost.

Findings

Machine learning predictions match quantum chemical accuracy

Prediction time per molecule is tens of milliseconds

Applicable to complex 3D molecular problems

Abstract

The IMPRESSION (Intelligent Machine PREdiction of Shift and Scalar Information Of Nuclei) machine learning system provides an efficient and accurate route to the prediction of NMR parameters from 3-dimensional chemical structures. Here we demonstrate that machine learning predictions, trained on quantum chemical computed values for NMR parameters, are essentially as accurate but computationally much more efficient (tens of milliseconds per molecule) than quantum chemical calculations (hours/days per molecule). Training the machine learning systems on quantum chemical, rather than experimental, data circumvents the need for existence of large, structurally diverse, error-free experimental databases and makes IMPRESSION applicable to solving 3-dimensional problems such as molecular conformation and isomerism