Related Experiment Video
Updated: Oct 25, 2026

Atomic Scale Structural Studies of Macromolecular Assemblies by Solid-state Nuclear Magnetic Resonance Spectroscopy
Published on: September 17, 2017
Public Database Leakage Distorts Model Rankings in Real-Spectra NMR Structure Elucidation
Zihan Zhang1,2, Mengxi Chen1,2, Xuezhou Zhao1,2
1International College of Pharmaceutical Innovation, Soochow University, Suzhou215123, China.
Abstract:
Sequence models that translate NMR spectra into molecular structures report up to 96% top-1 accuracy, but they are pretrained on simulated spectra and tested on public databases that can overlap those corpora. We build a leakage-controlled benchmark on nmrshiftdb2 and find that 26.9% of public molecules are exact training-corpus matches under a stated identity rule, with substantial training-set proximity remaining after exact-match removal. On the wider exact-match-removed real-spectrum cohort, released-model top-1 accuracy is 24.4% (95% CI 23.3-25.6%). A training-free rerank using molecular formula and 13C-peak count consistency raises it to 31.1% (29.9-32.4%), supporting leakage-controlled evaluation and decode-time consistency checks before claims of experimental generalization for simulation-pretrained inverse models.
Related Concept Videos
¹H NMR: Interpreting Distorted and Overlapping Signals
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are slanted or...
¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)
NMR Spectrometers: Resolution and Error Correction
¹³C NMR: ¹H–¹³C Decoupling
A broadband decoupling technique is used to simplify these complex, sometimes overlapping, signals. Broadband decoupling relies on a...
NMR Spectroscopy: Chemical Shift Overview
For instance, the proton...
¹H NMR Signal Integration: Overview

