Inverse-IMPRESSION: A Graph-based Platform for Molecular Structure Elucidation from Experimental NMR Spectroscopic Properties
2026-07-10 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a new tool called IMPRESSION-G2 that can figure out how atoms are connected in a molecule using data from NMR spectroscopy, a method to study molecules. Their approach uses three steps: first, it guesses the bonds between atoms, then it fixes any uncertain parts, and finally, it creates and ranks several possible structures to find the best match. They tested their system on simulated and real NMR data, successfully identifying many molecules with up to 30 heavier atoms. This work offers a new way to automatically determine molecular structures using machine learning and experimental data.
Nuclear Magnetic Resonance (NMR)Molecular structure elucidationGraph Transformer NetworkBond connectivity2D NMR experimentsCOSYHSQCHMBCMachine learningSynthetic and natural products
Authors
Zheqi Jin, Grace Armitage, Richard Cox, Ben Honoré, Mohammad Golbabaee, Craig Butts
Abstract
Here, we present a platform built on our inverted Graph Transformer Network, IMPRESSION-G2, which can accurately and rapidly reconstruct molecular bonding directly from experimental nuclear magnetic resonance (NMR) spectroscopic information. It comprises three interconnected stages: a one-shot model that predicts bond connectivity between atoms; a structure-correction stage that corrects the predicted structures by removing uncertain bonds and iteratively reassigning them; noise-augmented multi-shot prediction, generating an ensemble of candidate structures, which are ranked to identify the best-fit structure. By integrating a range of $^{1}$H and $^{13}$C NMR data, including two-dimensional (2D) experiments such as COSY, HSQC, and HMBC, the inverse-IMPRESSION platform correctly identifies the structures of 77.8% of molecules with up to 30 heavy atoms (H, C, N, O and F) using simulated NMR data, and 10 of 19 (53%) molecules using experimental NMR data. The experimental structures solved have molecular weights of up to 480 Da and are representative of the complex structures in synthetic and natural products that routinely challenge chemists. The inverse-IMPRESSION framework thus provides the first effective approach for automated molecular structure elucidation using graph-based machine learning on experimental data.