2DNMRGym: An Annotated Experimental Dataset for Atom-Level Molecular Representation Learning in 2D NMR via Surrogate Supervision

TL;DR

This paper introduces 2DNMRGym, a large annotated dataset for machine learning-based molecular interpretation of 2D NMR spectra, utilizing surrogate supervision to enable model training and evaluation.

Contribution

It provides the first large-scale annotated 2D NMR dataset with surrogate supervision, facilitating development of ML models for molecular representation learning in NMR analysis.

Findings

Benchmark results for GNN and transformer models on 2DNMRGym.

Demonstrates surrogate supervision effectiveness in NMR data interpretation.

Establishes a foundation for future ML research in NMR-based molecular analysis.

Abstract

Two-dimensional (2D) Nuclear Magnetic Resonance (NMR) spectroscopy, particularly Heteronuclear Single Quantum Coherence (HSQC) spectroscopy, plays a critical role in elucidating molecular structures, interactions, and electronic properties. However, accurately interpreting 2D NMR data remains labor-intensive and error-prone, requiring highly trained domain experts, especially for complex molecules. Machine Learning (ML) holds significant potential in 2D NMR analysis by learning molecular representations and recognizing complex patterns from data. However, progress has been limited by the lack of large-scale and high-quality annotated datasets. In this work, we introduce 2DNMRGym, the first annotated experimental dataset designed for ML-based molecular representation learning in 2D NMR. It includes over 22,000 HSQC spectra, along with the corresponding molecular graphs and SMILES strings. Uniquely, 2DNMRGym adopts a surrogate supervision setup: models are trained using algorithm-generated annotations derived from a previously validated method and evaluated on a held-out set of human-annotated gold-standard labels. This enables rigorous assessment of a model's ability to generalize from imperfect supervision to expert-level interpretation. We provide benchmark results using a series of 2D and 3D GNN and GNN transformer models, establishing a strong foundation for future work. 2DNMRGym supports scalable model training and introduces a chemically meaningful benchmark for evaluating atom-level molecular representations in NMR-guided structural tasks. Our data and code is open-source and available on Huggingface and Github.