³¹P NMR Shift Predictor

Draw a molecule or paste a SMILES string. Both inputs stay synchronized.

1) Molecule input

When you edit the SMILES manually, the molecule is redrawn automatically after a short delay.
Logging and transparency
We log the date, time, and prediction count for statistics. The submitted SMILES and predicted value can also be logged for learning purposes to improve the model.
Transparency: View the public logging JSON
References and License

License: Academic, research, and non-commercial evaluation use only. Commercial use, including internal industrial evaluation, requires a separate written license. Contact: Dr. André K. Eckhardt

Please cite this paper when using this tool.

  1. A light-weight Graph Neural Network for the prediction of 31P Nuclear Magnetic Resonance signals. D. Domnjuk, J. de Wiljes, R. Geitner, J. Cheminform. 2026, advance online publication, doi:10.1186/s13321-026-01178-6.
Further references
  1. Ilm-NMR-P31: an open-access 31P nuclear magnetic resonance database and data-driven prediction of 31P NMR shifts. J. Hack, M. Jordan, A. Schmitt, M. Raru, H. S. Zorn, A. Seyfarth, I. Eulenberger, R. Geitner, J. Cheminform. 2023, 15, 122, doi:10.1186/s13321-023-00792-y.
  2. Predicting 31P NMR Shifts in Large-Scale, Heterogeneous Databases by Gas Phase DFT: Impact of Conformer and Solvent Effects. R. Geitner, C. Dreßler, ACS Omega 2026, 11, 6773–6782, doi:10.1021/acsomega.5c13249.