NMIRacle: Multi-modal Generative Molecular Elucidation from IR and NMR Spectra

• URL: http://arxiv.org/abs/2512.19733v1
• Date: Wed, 17 Dec 2025 10:29:39 GMT
• Title: NMIRacle: Multi-modal Generative Molecular Elucidation from IR and NMR Spectra
• Authors: Federico Ottomano, Yingzhen Li, Alex M. Ganose,
• Abstract summary: We introduce NMIRacle, a two-stage generative framework that builds upon recent paradigms in AI-driven spectroscopy with minimal assumptions.<n>In the first stage, NMIRacle learns to reconstruct molecular structures from count-aware fragment encodings.<n>In the second stage, a spectral encoder maps input spectroscopic measurements into a latent embedding.<n>This formulation bridges fragment-level chemical modeling with spectral evidence, yielding accurate molecular predictions.
• Score: 13.594833907772783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Molecular structure elucidation from spectroscopic data is a long-standing challenge in Chemistry, traditionally requiring expert interpretation. We introduce NMIRacle, a two-stage generative framework that builds upon recent paradigms in AI-driven spectroscopy with minimal assumptions. In the first stage, NMIRacle learns to reconstruct molecular structures from count-aware fragment encodings, which capture both fragment identities and their occurrences. In the second stage, a spectral encoder maps input spectroscopic measurements (IR, 1H-NMR, 13C-NMR) into a latent embedding that conditions the pre-trained generator. This formulation bridges fragment-level chemical modeling with spectral evidence, yielding accurate molecular predictions. Empirical results show that NMIRacle outperforms existing baselines on molecular elucidation, while maintaining robust performance across increasing levels of molecular complexity.

Related papers

• How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning? [51.286853421822705]
  Large language models (LLMs) have shown promise for reasoning-intensive scientific tasks, but their capability for chemical interpretation is still unclear.<n>We introduce a Chain-of-Thought (CoT) prompting framework and benchmark that evaluate how LLMs reason about mass spectral data to predict molecular structures.<n>Our evaluation across metrics of SMILES validity, formula consistency, and structural similarity reveals that while LLMs can produce syntactically valid and partially plausible structures, they fail to achieve chemical accuracy or link reasoning to correct molecular predictions.
  arXiv  Detail & Related papers  (2026-01-09T20:08:42Z)
• Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR Spectra [5.818797900550866]
  ChefNMR (CHemical Elucidation From NMR) is an end-to-end framework that directly predicts an unknown molecule's structure.<n>To model the complex chemical groups found in natural products, we generated a dataset of simulated 1D NMR spectra for over 111,000 natural products.<n>ChefNMR predicts the structures of challenging natural product compounds with an unsurpassed accuracy of over 65%.
  arXiv  Detail & Related papers  (2025-12-02T18:59:13Z)
• Mamba-driven multi-perspective structural understanding for molecular ground-state conformation prediction [69.32436472760712]
  We propose an approach of Mamba-driven multi-perspective structural understanding (MPSU-Mamba) to localize molecular ground-state conformation.<n>For complex and diverse molecules, three different kinds of dedicated scanning strategies are explored to construct a comprehensive perception of corresponding molecular structures.<n> Experimental results on QM9 and Molecule3D datasets indicate that MPSU-Mamba significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-10T11:18:32Z)
• Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra [60.08608779794957]
  We propose GLMR, a Generative Language Model-based Retrieval framework.<n>In the pre-retrieval stage, a contrastive learning-based model identifies top candidate molecules as contextual priors for the input mass spectrum.<n>In the generative retrieval stage, these candidate molecules are integrated with the input mass spectrum to guide a generative model in producing refined molecular structures.
  arXiv  Detail & Related papers  (2025-11-09T07:25:53Z)
• NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization [24.714189961887215]
  Nuclear Magnetic Resonance (NMR) spectroscopy is one of the most powerful and widely used tools for molecular structure elucidation in organic chemistry.<n>Here, we present NMR-r, a practical and interpretable framework for the automated determination of small organic molecule structures from $1$H and $13$C NMR spectra.
  arXiv  Detail & Related papers  (2025-08-30T23:59:12Z)
• $\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models [59.125833618091846]
  We propose a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view.<n>Experiments demonstrate that $textM2$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-12T05:46:47Z)
• DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models [68.19129717255053]
  We present DiffSpectra, a generative framework that formulates molecular structure elucidation as a conditional generation process.<n>Our experiments demonstrate that DiffSpectra accurately elucidates molecular structures, achieving 40.76% top-1 and 99.49% top-10 accuracy.
  arXiv  Detail & Related papers  (2025-07-09T13:57:20Z)
• DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation [9.321270922757442]
  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.
  arXiv  Detail & Related papers  (2025-07-09T06:21:36Z)
• 2DNMRGym: An Annotated Experimental Dataset for Atom-Level Molecular Representation Learning in 2D NMR via Surrogate Supervision [7.470166291890153]
  We introduce 2DNMRGym, the first annotated experimental dataset designed for Machine Learning-based representation learning in 2D NMR.<n>2DNMRGym adopts a surrogate supervision setup: models are trained using algorithm-generated annotations from a previously validated method.<n>We provide benchmark results using a series of 2D and 3D GNN and GNN transformer models, establishing a strong foundation for future work.
  arXiv  Detail & Related papers  (2025-05-16T18:02:05Z)
• 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)
• 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)

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.