Recommended by

Indexed by

Bayesian probabilistic assignment of chemical shifts in organic solids

Manuel Cordova1*, Martins Balodis1, Bruno Simões de Almeida1, Michele Ceriotti2, Lyndon Emsley1*

1 Institut des Sciences et Ingénierie Chimiques, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland

2 Institut des matériaux, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland

* Corresponding authors emails: manuel.cordova@epfl.ch, lyndon.emsley@epfl.ch
DOI10.24435/materialscloud:vp-ft [version v1]

Publication date: Oct 06, 2021

How to cite this record

Manuel Cordova, Martins Balodis, Bruno Simões de Almeida, Michele Ceriotti, Lyndon Emsley, Bayesian probabilistic assignment of chemical shifts in organic solids, Materials Cloud Archive 2021.158 (2021), doi: 10.24435/materialscloud:vp-ft.


A pre-requisite for NMR studies of organic materials is assigning each experimental chemical shift to a set of geometrically equivalent nuclei. Obtaining the assignment experimentally can be challenging and typically requires time-consuming multi-dimensional correlation experiments. An alternative solution for determining the assignment involves statistical analysis of experimental chemical shift databases, but no such database exists for molecular solids. Here, by combining the Cambridge structural database with a machine learning model of chemical shifts, we construct a statistical basis for probabilistic chemical shift assignment of organic crystals by calculating shifts for over 200,000 compounds, enabling the probabilistic assignment of organic crystals directly from their two-dimensional chemical structure. The approach is demonstrated with the 13C and 1H assignment of eleven molecular solids with experimental shifts, and benchmarked on 100 crystals using predicted shifts. The correct assignment was found among the two most probable assignments in over 80% of cases.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
1.5 GiB Database of chemical shieldings associated to graph descriptors (should be downloaded and placed in the "db" directory of the Github repository in order to run the software)
1.4 MiB Code of the probabilistic assignment software (archive of the code available at https://github.com/manucordova/ProbAsn)
811.9 MiB Experimental solid-state NMR spectra of strychnine and ritonavir
985.7 MiB List of structures and ShiftML computed shieldings extracted from the CSD database (in extended XYZ format)


Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference (Paper in which the method is described)
Software (Github repository containing the code of the method described)


MARVEL/DD1 SNSF machine learning Experimental NMR

Version history:

2021.158 (version v1) [This version] Oct 06, 2021 DOI10.24435/materialscloud:vp-ft