Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915951379742720 |
|---|---|
| author | Kuhn, Stefan Dwarka, Vandana Grenda, Przemyslaw Karol Vainikko, Eero |
| author_facet | Kuhn, Stefan Dwarka, Vandana Grenda, Przemyslaw Karol Vainikko, Eero |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03875 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra Kuhn, Stefan Dwarka, Vandana Grenda, Przemyslaw Karol Vainikko, Eero Machine Learning Artificial Intelligence Quantitative Methods I.2.6; J.3 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. |
| title | Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra |
| topic | Machine Learning Artificial Intelligence Quantitative Methods I.2.6; J.3 |
| url | https://arxiv.org/abs/2602.03875 |