DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation

• URL: http://arxiv.org/abs/2507.08854v1
• Date: Wed, 09 Jul 2025 06:21:36 GMT
• Title: DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation
• Authors: Qingsong Yang, Binglan Wu, Xuwei Liu, Bo Chen, Wei Li, Gen Long, Xin Chen, Mingjun Xiao,
• Abstract summary: Nuclear Magnetic Resonance (NMR) spectroscopy is a central characterization method for molecular structure elucidation.<n>We introduce DiffNMR, a novel end-to-end framework that leverages a conditional discrete diffusion model for de novo molecular structure elucidation from NMR spectra.
• Score: 9.321270922757442
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nuclear Magnetic Resonance (NMR) spectroscopy is a central characterization method for molecular structure elucidation, yet interpreting NMR spectra to deduce molecular structures remains challenging due to the complexity of spectral data and the vastness of the chemical space. In this work, we introduce DiffNMR, a novel end-to-end framework that leverages a conditional discrete diffusion model for de novo molecular structure elucidation from NMR spectra. DiffNMR refines molecular graphs iteratively through a diffusion-based generative process, ensuring global consistency and mitigating error accumulation inherent in autoregressive methods. The framework integrates a two-stage pretraining strategy that aligns spectral and molecular representations via diffusion autoencoder (Diff-AE) and contrastive learning, the incorporation of retrieval initialization and similarity filtering during inference, and a specialized NMR encoder with radial basis function (RBF) encoding for chemical shifts, preserving continuity and chemical correlation. Experimental results demonstrate that DiffNMR achieves competitive performance for NMR-based structure elucidation, offering an efficient and robust solution for automated molecular analysis.

Related papers

• DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models [66.41802970528133]
  Molecular structure elucidation from spectra is a foundational problem in chemistry.<n>Traditional methods rely heavily on expert interpretation and lack scalability.<n>We present DiffSpectra, a generative framework that directly infers both 2D and 3D molecular structures from multi-modal spectral data.
  arXiv  Detail & Related papers  (2025-07-09T13:57:20Z)
• DiffNMR: Advancing Inpainting of Randomly Sampled Nuclear Magnetic Resonance Signals [1.2582887633807602]
  Nuclear Magnetic Resonance spectroscopy is used to probe molecules' chemical environment, structure, and dynamics.<n>Non-Uniform sampling (NUS) is widely employed as a sub-sampling method to address these challenges.<n>We propose the use of deep learning techniques to enhance the reconstruction quality of NUS spectra.
  arXiv  Detail & Related papers  (2025-05-26T11:06:11Z)
• DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra [60.39311767532607]
  We present DiffMS, a formula-restricted encoder-decoder generative network that achieves state-of-the-art performance on this task.<n>To develop a robust decoder that bridges latent embeddings and molecular structures, we pretrain the diffusion decoder with fingerprint-structure pairs.<n>Experiments on established benchmarks show that DiffMS outperforms existing models on de novo molecule generation.
  arXiv  Detail & Related papers  (2025-02-13T18:29:48Z)
• DiffNMR3: Advancing NMR Resolution Beyond Instrumental Limits [1.1844780810044506]
  High-field NMR instruments provide high-resolution spectra but are prohibitively expensive, whereas lower-field instruments offer more accessible, but lower-resolution, results.<n>This paper introduces an AI-driven approach that enhances the frequency resolution of NMR spectra through super-resolution techniques.
  arXiv  Detail & Related papers  (2025-02-06T21:00:35Z)
• DiffNMR2: NMR Guided Sampling Acquisition Through Diffusion Model Uncertainty [2.4634393035848494]
  We propose a novel sub-sampling strategy based on a diffusion model trained on protein NMR data.<n>Our method iteratively reconstructs under-sampled spectra while using model uncertainty to guide subsequent sampling, significantly reducing acquisition time.<n>This advancement holds promise for many applications, from drug discovery to materials science, where rapid and high-resolution spectral analysis is critical.
  arXiv  Detail & Related papers  (2025-02-06T20:10:28Z)
• Graph-neural-network predictions of solid-state NMR parameters from spherical tensor decomposition [0.0]
  Nuclear magnetic resonance (NMR) is a powerful spectroscopic technique that is sensitive to the local atomic structure of matter.<n>Machine learning (ML) has emerged as an efficient route to making such predictions.
  arXiv  Detail & Related papers  (2024-12-19T17:11:07Z)
• Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry [0.1747623282473278]
  This dataset comprises simulated $1$H-NMR, $13$C-NMR, HSQC-NMR, Infrared, and Mass spectra for 790k molecules extracted from chemical reactions in patent data. We provide benchmarks for evaluating single-modality tasks such as structure elucidation, predicting the spectra for a target molecule, and functional group predictions.
  arXiv  Detail & Related papers  (2024-07-04T12:52:48Z)
• TransPeakNet: Solvent-Aware 2D NMR Prediction via Multi-Task Pre-Training and Unsupervised Learning [5.7279868722119325]
  We introduce an unsupervised training framework for predicting cross-peaks in 2D NMR.<n>Our approach pretrains an ML model on an annotated 1D dataset of 1H and 13C shifts, then finetunes it in an unsupervised manner.<n> Evaluation on 479 expert-annotated HSQC spectra demonstrates our model's superiority over traditional methods.
  arXiv  Detail & Related papers  (2024-03-17T21:52:51Z)
• Towards Predicting Equilibrium Distributions for Molecular Systems with Deep Learning [60.02391969049972]
  We introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system.
  arXiv  Detail & Related papers  (2023-06-08T17:12:08Z)
• Calculating non-linear response functions for multi-dimensional electronic spectroscopy using dyadic non-Markovian quantum state diffusion [68.8204255655161]
  We present a methodology for simulating multi-dimensional electronic spectra of molecular aggregates with coupling electronic excitation to a structured environment. A crucial aspect of our approach is that we propagate the NMQSD equation in a doubled system Hilbert space but with the same noise.
  arXiv  Detail & Related papers  (2022-07-06T15:30:38Z)
• Unsupervised Spectral Unmixing For Telluric Correction Using A Neural Network Autoencoder [58.720142291102135]
  We present a neural network autoencoder approach for extracting a telluric transmission spectrum from a large set of high-precision observed solar spectra from the HARPS-N radial velocity spectrograph.
  arXiv  Detail & Related papers  (2021-11-17T12:54:48Z)
• Two-Dimensional Single- and Multiple-Quantum Correlation Spectroscopy in Zero-Field Nuclear Magnetic Resonance [55.41644538483948]
  We present single- and multiple-quantum correlation $J$-spectroscopy detected in zero magnetic field using a Rb vapor-cell magnetometer. At zero field the spectrum of ethanol appears as a mixture of carbon isotopomers, and correlation spectroscopy is useful in separating the two composite spectra.
  arXiv  Detail & Related papers  (2020-04-09T10:02:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.