A Pilot Study For Fragment Identification Using 2D NMR and Deep Learning

TL;DR

This study introduces a deep learning approach using CNNs to identify substructures in 2D NMR spectra, effectively analyzing pure compounds and mixtures with improved accuracy when combining HMBC and HSQC data.

Contribution

It demonstrates a novel image-based CNN method for substructure identification in 2D NMR spectra, including mixtures, with enhanced performance using combined spectra.

Findings

Reliable detection of substructures in pure compounds.

Effective identification of mixtures trained solely on pure data.

Better results achieved with combined HMBC and HSQC spectra.

Abstract

This paper presents a method to identify substructures in NMR spectra of mixtures, specifically 2D spectra, using a bespoke image-based Convolutional Neural Network application. This is done using HSQC and HMBC spectra separately and in combination. The application can reliably detect substructures in pure compounds, using a simple network. It can work for mixtures when trained on pure compounds only. HMBC data and the combination of HMBC and HSQC show better results than HSQC alone.