MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation

2026-10-08

AI Summary

This work proposes the MAST framework to address conditional ambiguity arising from global representations and the prohibitive computational overhead of full-sampling inference in spectral graph parsing. Specifically, the method introduces explicit motif priors as intermediate denoising evidence to mitigate conditional ambiguity, while reformulating diffusion sampling as reward-guided tree search to prioritize high-reward trajectories, thereby enabling efficient joint generation of 2D and 3D molecular structures. Evaluated on the QM9S benchmark, MAST achieves an exact recovery rate of 94.89%, substantially reducing the computational budget while simultaneously improving candidate set quality, 3D fidelity, and chemical validity.

Abstract

Elucidating molecular structures from spectra is a foundational problem in chemical and materials characterization, yet remains challenging due to spectral ambiguity and the vast molecular space. Although recent diffusion-based generators show strong promise for spectra-conditioned elucidation, existing methods struggle to learn robust spectra-structure relationships from limited paired data when relying solely on global spectral representation. Moreover, the repeated full sampling inference strategy incurs substantial computation overhead. To address these limitations, we propose \textbf{MAST}, a \textbf{M}otif-\textbf{A}ugmented diffusion framework with \textbf{S}earch \textbf{T}ree, for joint 2D-3D spectroscopic molecular structure elucidation. MAST introduces explicit, interpretable \emph{motif priors} as intermediate evidences throughout denoising, reducing conditional ambiguity and facilitating spectra-conditioned optimization. We further cast diffusion sampling as \emph{reward-guided tree search} to prioritize high-reward denoising trajectories, yielding a compact set of spectra-consistent candidates under limited budgets. On the QM9S multi-spectra benchmark, MAST achieves \textbf{94.89\%} exact recovery and improves 3D fidelity, while preserving high chemical validity and stability. Code is available at https://github.com/Jia040223/MAST.

Problem

• molecular structure elucidation
• spectral ambiguity
• diffusion models
• computational overhead
• spectroscopy

Innovation

• Motif-Augmented Diffusion
• Search Tree
• Spectroscopic Molecular Structure Elucidation
• Reward-Guided Sampling
• Motif Priors