Alberto Fabrizio¹, Andrea Grisafi², Benjamin Meyer¹, Michele Ceriotti², Clemence Corminboeuf^1*

1 Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering, École Polytechnique Fédérale de Lausanne, CH-1015 Lausanne, Switzerland

2 Laboratory of Computational Science and Modeling, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland

* Corresponding authors emails: clemence.corminboeuf@epfl.ch

DOI10.24435/materialscloud:2019.0071/v1 [version v1]

Publication date: Oct 28, 2019

How to cite this record

Alberto Fabrizio, Andrea Grisafi, Benjamin Meyer, Michele Ceriotti, Clemence Corminboeuf, Electron density learning of non-covalent systems, Materials Cloud Archive 2019.0071/v1 (2019), doi: 10.24435/materialscloud:2019.0071/v1.

Description

Chemists continuously harvest the power of non-covalent interactions to control phenomena in both the micro- and macroscopic worlds. From the quantum chemical perspective, the strategies essentially rely upon an in-depth understanding of the physical origin of these interactions, the quantification of their magnitude and their visualization in real-space. The total electron density ρ(r) represents the simplest yet most comprehensive piece of information available for fully characterizing bonding patterns and non-covalent interactions. The charge density of a molecule can be computed by solving the Schrödinger equation, but this approach becomes rapidly demanding if the electron density has to be evaluated for thousands of different molecules or very large chemical systems, such as peptides and proteins. Here we present a transferable and scalable machine-learning model capable of predicting the total electron density directly from the atomic coordinates. The regression model is used to access qualitative and quantitative insights beyond the underlying ρ(r) in a diverse ensemble of sidechain–sidechain dimers extracted from the BioFragment database (BFDb). The transferability of the model to more complex chemical systems is demonstrated by predicting and analyzing the electron density of a collection of 8 polypeptides.

Materials Cloud sections using this data

Files

File name	Size	Description
coordinates_training_test.tar.gz MD5md5:d96cfc997cebe1ca4c7b92be416b1359	552.6 KiB	All the structures (xyz format) of the molecules included in the training and the test set.
coefficients_training_test.tar.gz MD5md5:b5792d607bd75f307232fdcbfcc40eee	15.6 MiB	All the reference density coefficients of the molecules included in the training and the test set.
predicted_coefficients.zip MD5md5:253e172af6723799da7c10ca934e927d	102.7 MiB	All the predicted density coefficients of the molecules included in the test set.
biomolecules.tar.gz MD5md5:6a4ff66087fe9f99af8b647c470b40a7	504.4 KiB	Data (structure and coefficients) to reconstruct the density of the extrapolated biomolecules.
README.txt MD5md5:3008ce8f7bfb052867ab791a26fe060c	880 Bytes	More detailed description of the files content

License

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

Keywords

MARVEL/DD1 Machine Learning Electron density Non-Covalent Systems