Vib2Conf: AI-driven discrimination of molecular conformations from vibrational spectra

TL;DR

Vib2Conf is a deep learning model that accurately discriminates 3D molecular conformations from vibrational spectra, overcoming spectral ambiguities caused by conformational heterogeneity.

Contribution

It introduces an attentional resampler and Mixture-of-Experts modules to improve 3D conformation discrimination from vibrational spectra, achieving state-of-the-art accuracy.

Findings

Top-1 recall exceeds 95% on benchmark datasets.

Discriminates near-isomeric conformers with 82.06% recall.

Effective in resolving conformational heterogeneity.

Abstract

Retrieving or generating two-dimensional molecular structures on the basis of vibrational spectra has been well demonstrated via deep learning models. However, deciphering three-dimensional molecular conformations is still challenging, primarily due to spectral ambiguities caused by conformational heterogeneity, which are difficult to resolve. To address this limitation, we propose Vib2Conf, a deep learning model directly discriminating 3D molecular conformations from vibrational spectra. We implement an attentional resampler to distill conformation-sensitive features from sparse spectral signals, and integrate Mixture-of-Experts (MoE) to partition the conformational space for precise geometric mapping. These modules enable Vib2Conf to achieve state-of-the-art top-1 recall exceeding 95% on traditional spectrum-structure benchmarks, including QM9S, VB-Mols, and QMe14S. More importantly, Vib2Conf can discriminate near-isomeric conformers with a top-1 recall of 82.06% on VB-Confs test set, where conformational isomers differ by a root-mean-square deviation (RMSD) of only ~1 {\AA}. In general, Vib2Conf is a promising method for fine-grained spectrum-to-conformation analysis.