Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra

2026-02-01

AI Summary

This work addresses the bidirectional mapping between ¹³C nuclear magnetic resonance (NMR) spectra and molecular structures, with a particular focus on the one-to-many ambiguity inherent in spectrum-to-structure inference. The authors propose the first unified framework based on invertible neural networks, leveraging an i-RevNet architecture that integrates graph neural networks to encode molecular structures, a 128-dimensional binned spectral code representation, and bijective modules to enable end-to-end spectral prediction and structure generation. The model is numerically invertible on training data, significantly outperforms random baselines in spectral prediction, and successfully inverts validation spectra to generate structurally plausible candidate molecules at a coarse-grained chemical level, thereby explicitly modeling the multiplicity of the spectrum–structure mapping.

Technology Category

• Machine Learning: Structured Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

We introduce a reversible deep learning model for 13C NMR that uses a single conditional invertible neural network for both directions between molecular structures and spectra. The network is built from i-RevNet style bijective blocks, so the forward map and its inverse are available by construction. We train the model to predict a 128-bit binned spectrum code from a graph-based structure encoding, while the remaining latent dimensions capture residual variability. At inference time, we invert the same trained network to generate structure candidates from a spectrum code, which explicitly represents the one-to-many nature of spectrum-to-structure inference. On a filtered subset, the model is numerically invertible on trained examples, achieves spectrum-code prediction above chance, and produces coarse but meaningful structural signals when inverted on validation spectra. These results demonstrate that invertible architectures can unify spectrum prediction and uncertainty-aware candidate generation within one end-to-end model.

Problem

• 13C NMR
• molecular structure
• spectrum-structure mapping
• one-to-many inference
• chemoinformatics

Innovation

• reversible deep learning
• invertible neural network
• 13C NMR
• structure-spectrum mapping
• chemoinformatics