Latent Diffusion-Based 3D Molecular Recovery from Vibrational Spectra

2026-03-06

AI Summary

This work proposes IR-GeoDiff, the first latent diffusion-based framework for recovering three-dimensional molecular geometries directly from infrared (IR) spectra. Existing approaches typically rely on one-dimensional SMILES strings or two-dimensional molecular graphs, which struggle to capture the intricate relationship between spectral features and 3D molecular conformations. IR-GeoDiff addresses this limitation by integrating IR spectral information into node and edge representations via graph neural networks, thereby modeling the distributional mapping from spectra to 3D structures. The method uniquely enables the reconstruction of the full 3D geometric distribution corresponding to a single IR spectrum and incorporates an attention mechanism that highlights the model’s focus on key functional group regions, enhancing chemical interpretability. Experimental results demonstrate its superior performance under dual evaluation criteria—spectral fidelity and structural plausibility.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Graph-based Machine Learning
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Infrared (IR) spectroscopy, a type of vibrational spectroscopy, is widely used for molecular structure determination and provides critical structural information for chemists. However, existing approaches for recovering molecular structures from IR spectra typically rely on one-dimensional SMILES strings or two-dimensional molecular graphs, which fail to capture the intricate relationship between spectral features and three-dimensional molecular geometry. Recent advances in diffusion models have greatly enhanced the ability to generate molecular structures in 3D space. Yet, no existing model has explored the distribution of 3D molecular geometries corresponding to a single IR spectrum. In this work, we introduce IR-GeoDiff, a latent diffusion model that recovers 3D molecular geometries from IR spectra by integrating spectral information into both node and edge representations of molecular structures. We evaluate IR-GeoDiff from both spectral and structural perspectives, demonstrating its ability to recover the molecular distribution corresponding to a given IR spectrum. Furthermore, an attention-based analysis reveals that the model is able to focus on characteristic functional group regions in IR spectra, qualitatively consistent with common chemical interpretation practices.

Problem

• 3D molecular geometry
• infrared spectroscopy
• molecular structure recovery
• vibrational spectra
• spectral-structure relationship

Innovation

• latent diffusion model
• 3D molecular geometry
• infrared spectroscopy
• molecular structure recovery
• spectral-structure integration