Inverse-IMPRESSION: A Graph-Based Platform for Molecular Structure Elucidation from Experimental NMR Spectroscopic Properties

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 reads in NMR parameters and uses these to predict bond connectivity between atoms; a structure correction stage that corrects the predicted structures by removing uncertain bonds and iteratively reassigning them; and noise-augmented multishot prediction, generating an ensemble of candidate structures, which are ranked to identify the best-fit structure. By integrating a range of 1H and 13C 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 11 of 19 (58%) molecules using experimental NMR data. The experimental structures solved are representative of the complex structures in synthetic and natural products that routinely challenge chemists, assessed by high nSPS scores (greater than 40) for successfully elucidated structures and molecular weights of up to 480 Da. The inverse-IMPRESSION framework thus provides a highly effective approach for automated molecular structure elucidation by using graph-based machine learning on experimental data.