Context-Aware Automated NMR Structure Elucidation

Frank Hu; Jonathan M. Tubb; Grant M. Rotskoff; Matthew W. Kanan; Thomas E. Markland

physics.chem-phNov 4, 2026

Context-Aware Automated NMR Structure Elucidation

Authors: Frank Hu, Jonathan M. Tubb, Grant M. Rotskoff, Matthew W. Kanan, Thomas E. Markland

Organizations: Department of Chemistry, Stanford University, Stanford, California, 94305, USA

Abstract

Machine learning approaches are rapidly revolutionizing the ability to analyze and extract structural insights from chemical data, enabling high-throughput chemical discovery. While existing data-driven approaches have shown remarkable promise for predicting chemical structures in the de novo setting, incorporating additional chemically informed context offers the opportunity to further improve these models' performance and extend their real-world utility. Here we provide a straightforward protocol to combine artificial-intelligence-based spectroscopic elucidation pipelines with contextual chemical data, e.g., known reactants or a desired product, by using automated retrosynthetic analysis to generate large training sets of molecules and contextual data in the form of synthetic precursors. We demonstrate our approach by showing that our recently introduced NMR structure elucidation framework can be trained to effectively leverage molecular precursor context. We show that when the chemical context provides useful information on the target molecule we obtain dramatically improved accuracy over using NMR spectra alone, obtaining Top-15 accuracies of up to 95.4% for molecules up to 40 heavy atoms spanning the full elemental range of organic chemistry. Furthermore, we demonstrate that our approach is highly robust, such that even when the context provided is uncorrelated with the target, one still obtains accuracies commensurate with those of the original NMR structure elucidation framework. This approach provides an efficient route to improve a wide range of spectroscopic structure elucidation platforms using contextual data.

Figures & tables

Figure 1: An overview of our context-aware training approach for structure elucidation models using a retrosynthetic tree approach. A) A single retrosynthetic tree for a target molecule. Retrosynthetic trees were generated for molecules to varying retrosynthetic depths, $d$ , with the precursors at each level generated via retrosynthetic disconnections of parent molecules at earlier depths. B) Random sampling of the retrosynthetic tree selects out a pair of precursors (green box) to serve as a prompt for the structure elucidation model during training, where it is used alongside the 1 H NMR and 13 C NMR inputs to elucidate the structure of the corresponding small molecule. A subset of the predicted candidate molecules is shown along with their probabilities $p$ based on a sampling budget of 15 predictions.

Figure 2: Top- $N$ accuracy ( $N=1,5,15$ , left to right) as a function of the retrosynthetic depth, $d$ , of the precursors provided in the prompt, for the NMR+Precursor (blue), Precursor-only (orange), and NMR-only (green) models. A retrosynthetic depth of $d$ corresponds to precursors obtained after $d$ successive retrosynthetic disconnections of the target. The Top- $N$ accuracy is the percentage of targets for which the correct structure appears among the first $N$ independent predictions. The green horizontal line shows the accuracy of the NMR-only model from our previous work, which does not use a prompt (38.9%, 53.1%, and 60.4% for $N=1,5,15$ , respectively). Accuracies are computed on the full test set of our previous work (201,953 molecules) using, when possible, one randomly selected prompt per molecule at each retrosynthetic depth, excluding prompts in which the target itself appears as a precursor (SI Table S2).

Figure 3: Top-15 accuracy of the NMR+Precursor (blue), Precursor-only (orange), and NMR-only (green) models as a function of the maximum Tanimoto similarity between the precursors in the prompt and the target, pooled over all retrosynthetic depths. Accuracies are computed on the full test set using, when possible, one randomly selected prompt per molecule at each retrosynthetic depth. Prompts in which the target itself appears as a precursor are excluded, as in Figure 2 , and so are the 132 remaining prompts with a maximum Tanimoto similarity of exactly 1. Shaded bands show the standard error of each accuracy; they are almost indistinguishable from the line width. The green horizontal line shows the Top-15 accuracy of the NMR-only model (60.4%). The Top-1 and Top-5 accuracies are shown in SI Figure S5.

Figure 4: Top-15 accuracy as a function of retrosynthetic depth for target molecules containing the uncommon elements Si (top), B (middle), and P (bottom), for the NMR+Precursor (blue), Precursor-only (orange), and NMR-only (green) models separated into the cases where the prompt does (solid) or does not (dashed) contain the element. Error bars show the standard error of each accuracy, which depends on the number of prompts at that depth and prompt type. The green horizontal lines show the Top-15 accuracy of the NMR-only model on the same molecules (44.1%, 38.7%, and 25.0% for Si, B, and P, respectively). The Top-1 and Top-5 accuracies, and the numbers of molecules used, are given in SI Figure S7.

Figure 5: Examples of target molecules containing Si (top), B (middle), and P (bottom) for which only the NMR+Precursor model recovers the correct structure within its Top-15 predictions. Each row, labeled with the target’s uncommon element and the retrosynthetic depth $d$ of the prompt, shows, from left to right: the target, the precursors provided in the prompt, and the predictions of the NMR+Precursor, Precursor-only, and NMR-only models. For the NMR+Precursor model, we show the correct structure, which appears among its 15 predictions. The Precursor-only and NMR-only models do not produce the target in any of their 15 predictions, so the prediction with the highest Tanimoto similarity to the target is shown instead. Examples were drawn from the full test set, among single-component targets with at least 30 heavy atoms whose prompt does not contain the target itself and for which the closest prediction of both the Precursor-only and NMR-only models has a Tanimoto similarity to the target below 0.5.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Setting	Value
Software	AiZynthFinder 4.4.1 ( AiZynthExpander )
Expansion policy	USPTO template-based neural network ( uspto_model.onnx , uspto_templates.csv.gz )
Template cutoffs	cumulative probability 0.995, at most 50 templates ( cutoff_cumulative , cutoff_number )
Reactant sets returned per expansion ( return_n )	50
Feasibility (filter) model	USPTO ( uspto_filter_model.onnx ); scores recorded only, no reactions removed
Selection at each node	uniformly at random among the returned reactant sets

Appendix

Table S1: Settings used to generate the retrosynthetic trees with AiZynthExpander. Settings not listed are AiZynthFinder defaults.

Figure S1: An example retrosynthetic tree generated by AiZynthExpander for a test-set molecule (top), one of the five trees generated for this molecule, expanded to the maximum retrosynthetic depth of $d=5$ . Each row shows the precursors at retrosynthetic depth $d$ , and the lines connect each molecule to the precursors obtained from its disconnection; the children of a molecule together form one possible prompt.

$d$	Molecules with a prompt	Target among precursors	Prompts used	% of test set
1	201,376	55 (0.03%)	201,321	99.69
2	201,302	8,057 (4.00%)	193,245	95.69
3	201,280	708 (0.35%)	200,572	99.32
4	201,271	976 (0.48%)	200,295	99.18
5	201,266	183 (0.09%)	201,083	99.57
Total	1,006,495	9,979 (0.99%)	996,516

Appendix

Table S2: Number of test-set prompts at each retrosynthetic depth

d

before and after excluding prompts in which the target molecule itself appears among the precursors. Each of the 201,953 test molecules contributes at most one randomly selected prompt per depth; a molecule has no prompt at a depth if none of its retrosynthetic trees reaches that depth (577 molecules have no usable tree at all). The NMR+Precursor and Precursor-only models are evaluated on identical prompts.

Figure S2: Cross-attention between the NMR spectra and the precursor prompt, as performed in each of the eight decoder layers of the NMR+Precursor structure model. Keys (

K

) and values (

V

) are linear projections of the output of the spectrum encoder, whose input sequence consists of the 1 H NMR spectrum tokens produced by the convolutional embedding followed by one token per 13 C NMR chemical shift. Queries (

Q

) are linear projections of the decoder states of the precursor prompt and target SMILES tokens after masked self-attention. Attention is computed in

h=8

heads, whose outputs are concatenated, linearly projected, and added to the decoder states (Add & Norm) before the decoder’s feed-forward block. The cross-attention layers are the only place in the model where the precursor prompt and the NMR spectra interact.

Figure S3: Top- $N$ accuracy ( $N=1,5,15$ , left to right) as a function of the retrosynthetic depth $d$ of the precursors in the prompt for the Precursor-only baselines: the encoder-decoder model used for all comparisons in the main text (orange), and the decoder-only model trained with a probability $p_{0}=0.25$ (purple) or $p_{0}=0$ (magenta) of replacing the training prompt by a blank prompt. The green horizontal lines show the accuracy of the NMR-only model (38.9%, 53.1%, and 60.4% for $N=1,5,15$ , respectively). Accuracies are computed on the full test set, using one randomly selected prompt per molecule at each retrosynthetic depth when possible and excluding prompts in which the target itself appears as a precursor.

Model	Optimizer	Precision	Gradient clipping	$p_{0}$	Epochs trained	Best epoch
NMR+Precursor	AdamW	FP32	norm 1.0	0.25	84	50
Precursor-only, encoder-decoder	Adam	bf16 mixed	none	0	112	112
Precursor-only, decoder-only	Adam	bf16 mixed	none	0.25	180	147
Precursor-only, decoder-only	Adam	bf16 mixed	none	0	180	171

Appendix

Table S3: Optimization settings for each model. All models use a batch size of 128, a constant learning rate of

10^{-5}

, and a single NVIDIA H100 GPU.

p_{0}

is the probability that a training prompt is replaced by a blank prompt. The best epoch is the epoch with the lowest validation loss, whose checkpoint is used for evaluation.

Figure S4: Distributions of the maximum Tanimoto similarity to the target (left) and of the size of the largest precursor in heavy atoms (right), taken over the precursors in each prompt and separated by retrosynthetic depth. Tanimoto similarities are computed from Morgan fingerprints (radius 2, 2048 bits). The distributions are computed over all prompts in the retrosynthetic trees of the full dataset of $\sim$ 2 million molecules; prompts in which the target itself appears as a precursor are excluded from the Tanimoto similarity distributions.

Figure S5: Top- $N$ accuracy ( $N=1,5,15$ , left to right) of the NMR+Precursor (blue), Precursor-only (orange), and NMR-only (green) models as a function of the maximum Tanimoto similarity between the precursors in the prompt and the target, pooled over all retrosynthetic depths. Accuracies are computed on the full test set using, when possible, one randomly selected prompt per molecule at each retrosynthetic depth. Prompts in which the target itself appears as a precursor are excluded, and so are the 132 remaining prompts with a maximum Tanimoto similarity of exactly 1. Shaded bands show the standard error of each accuracy. The green horizontal lines show the accuracy of the NMR-only model (38.9%, 53.1%, and 60.4% for $N=1,5,15$ , respectively). The Top-15 panel is shown in the main text (Figure 3).

Figure S6: Five randomly selected prompts with a maximum precursor Tanimoto similarity between 0.90 and 1.0, drawn from the full test set with prompts in which the target itself appears as a precursor excluded, and excluding prompts whose most similar precursor differs from the target only in its salt form or counterions. Each row shows, from left to right, the target (labeled with the maximum Tanimoto similarity and the retrosynthetic depth $d$ of the prompt), the precursor in the prompt most similar to the target, and the first (Top-1) prediction of the NMR+Precursor and Precursor-only models. Atoms highlighted in red lie outside the maximum common substructure with the target (for the target, with the most similar precursor). Prediction boxes are outlined in green if the prediction is the target and in red otherwise.

Figure S7: Top- $N$ accuracy ( $N=1,5,15$ , left to right) as a function of retrosynthetic depth for target molecules containing Si (top row), B (middle row), and P (bottom row), for the NMR+Precursor (blue), Precursor-only (orange), and NMR-only (green) models. Results are separated by whether at least one precursor in the prompt contains that element (solid lines, circles) or not (dashed lines, squares). Error bars show the standard error of each accuracy, which depends on the number of prompts at that depth and prompt type. The green horizontal lines show the accuracy of the NMR-only model on the same molecules (Top-1, Top-5, and Top-15 accuracies of 23.2%, 35.8%, and 44.1% for Si; 21.2%, 31.8%, and 38.7% for B; and 10.5%, 19.2%, and 25.0% for P). All results are for the 2,650 Si-, 1,048 B-, and 2,715 P-containing molecules of the full test set, with one randomly selected prompt per molecule at each retrosynthetic depth when possible, excluding prompts in which the target itself appears as a precursor. The Top-15 panels are shown in the main text (Figure 4).

Magnetic Resonance Spectroscopy

See all 15 papers

Jun 29, 2026

Towards Generalizable and Evidential Nuclear Magnetic Resonance-Based Molecular Structure Elucidation via Large Language Model Agent

Nuclear Magnetic Resonance (NMR) spectroscopy is the gold standard for molecular structure elucidation, yet interpreting complex spectra for unknown molecules remains a bottleneck reliant on human expertise. While artificial intelligence has advanced this field, current methods face a critical trade-off: database retrieval cannot identify novel scaffolds, while de novo molecular structure elucidation models operate as black boxes, lacking the atom-level interpretability required for rigorous scientific validation. Here, we present NMRAgent, an evidential reasoning agent powered by large language models (LLMs) that bridges this gap by integrating specialized spectral analysis tools with chemical knowledge graphs. Unlike previous approaches, NMRAgent mimics the deductive reasoning of human experts: it takes experimental NMR spectra and molecular formula as input, plans the elucidation process, proposes candidate structures, verifies peak-atom consistency, and refines misaligned substructure through formula-aware fragment optimization. Enabled by its evidential reasoning, NMRAgent outperforms state-of-the-art methods, improving top-1 accuracy by 46.5% and Tanimoto similarity by 0.502 on a scaffold-split benchmark with novel scaffolds in the test set. Besides, we demonstrate the agent's practical utility by elucidating the structures of two previously unknown natural products isolated from Hydrangea davidii and Vitex trifolia, and by correcting structural misassignments in established literature. By combining high-accuracy prediction with transparent and evidence-based reasoning, NMRAgent establishes a new paradigm for interpretable AI in analytical chemistry.

Zheng Fang, Chen Yang, Yusen Tan +9

Information Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · The University of Hong Kong, Hong Kong, China · 3StateUniversity,Key Xiamen,LaboratoryChinaof Physical Chemistry of Solid Surface, College of Chemistry and Chemical Engineering, Xiamen +6

Agentic Reasoning Large Language Model-Guided Scientific Discovery

Ask PDF

Aug 12, 2026

Multi-Agent Closed-Loop Reasoning for Organic Structure Elucidation from Multimodal Spectra

Following the molecular discovery and synthesis revolutions, scalable automated structure elucidation from routine spectroscopic data remains an outstanding challenge. Despite decades of computational efforts, no existing system achieved reliable reasoning over unseen spectra. Here, we propose MACROS, a multi-agent system automating structure elucidation by emulating expert iterative hypothesis-testing. Trained on 100M simulated and 1.6M experimental spectra-molecule pairs, it natively supports arbitrary combinations of routine spectroscopic techniques. It achieves unprecedented zero-shot generalization to diverse real-world samples, correctly identifying synthetic compounds, natural products and metabolites above 500 Da with 1D NMR. Remarkably, MACROS spontaneously recovers textbook spectroscopic correlations from unassigned data and exhibits emergent chemical intuition such as a ring-first parsing preference, learning fundamental chemical principles rather than memorizing database patterns. MACROS augments chemists via collaboration to deliver sixfold faster, 40% more accurate elucidation. MACROS establishes a scalable foundation for fully automated structure elucidation, and catalyzes accelerated molecular discovery toward autonomous laboratories.

Bingsen Xue, Zhuojun Jiang, Jianhao Zhang +10

Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China · CAS Key Laboratory of Green Process and Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China · Department of Neurology, National Centre for Neurological Disorders, National Clinical Research Centre for Aging and Medicine, Huashan Hospital, Fudan University, Shanghai 200240, China +6

Magnetic Resonance Spectroscopy

Ask PDF

Jul 22, 2026

Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data

Determining molecular structures from spectroscopic data remains fundamentally challenging because the inverse problem is intrinsically underdetermined: individual spectra are sparse, low-dimensional, and encode only partial structural evidence relative to the vast space of possible molecules. We address this challenge by formulating automated structure elucidation as a scalable hypothesis-refinement paradigm that tightly integrates spectral evidence with large-scale molecular priors. To supply structure-resolving NMR signals for multimodal learning, we construct QM9SPIN, a DFT-derived dataset comprising diverse 1D and 2D spectra, including J-coupling, DEPT experiments, and explicit spin--spin interactions. On this foundation, we introduce SpectroMol, a spectrum-to-structure model that proposes chemically valid molecular hypotheses conditioned on multimodal spectral inputs. Complementarily, we develop MS-Mol2Mol, a high-resolution mass-constrained molecular generator that integrates molecular formula, exact mass, and degree of unsaturation within a conditional generative prior trained on 400 million molecules, ensuring global compositional consistency and chemically realistic refinement. The integrated system achieves 93.8% top-1 accuracy on the simulated benchmark, adapts effectively from simulated to experimental spectra with limited experimental fine-tuning, and further improves experimental predictions through mass-guided refinement, establishing a scalable route toward automated, data-driven organic structure elucidation.

Chengchun Liu, Zhiyuan Yan, Li Yuan +5

School of AI for Science, Peking University Shenzhen Graduate School, Shenzhen 518055, China · State Key Laboratory of Advanced Waterproof Materials, School of Materials Science and Engineering, Peking University, Beijing 100871, China · School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen 518055, China +6

Molecular Generation Magnetic Resonance Spectroscopy

Ask PDF

Abstract

Magnetic Resonance Spectroscopy

Explore similar work

Towards Generalizable and Evidential Nuclear Magnetic Resonance-Based Molecular Structure Elucidation via Large Language Model Agent

Multi-Agent Closed-Loop Reasoning for Organic Structure Elucidation from Multimodal Spectra

Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data