Papers for

chemical analysis laboratories

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Motif augmented diffusion improves molecular structure identification from spectra

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

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.

Thu 8 OctArtificial Intelligence
The gist
Figuring out the exact shape of molecules from their spectra is hard because many different molecules can produce similar signals. The authors introduce MAST, a method that uses known small molecule parts called motifs to guide the process, helping reduce confusion. They also use a smart search strategy to focus on the best guesses without wasting time. Their method greatly improves the accuracy and 3D detail of the predicted molecules compared to previous approaches.
Open → 2610.12067v1