edoc

Machine learning of molecular electronic properties in chemical compound space

Montavon, Gregoire and Rupp, Matthias and Gobre, Vivekanand and Vazquez-Mayagoitia, Alvaro and Hansen, Katja and Tkatchenko, Alexandre and Mueller, Klaus-Robert and von Lilienfeld, O. Anatole. (2013) Machine learning of molecular electronic properties in chemical compound space. New Journal of Physics, 15. 095003.

[img]
Preview
PDF - Published Version
Available under License CC BY (Attribution).

6Mb

Official URL: http://edoc.unibas.ch/53261/

Downloads: Statistics Overview

Abstract

The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning model, trained on a database of ab initio calculation results for thousands of organic molecules, that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity and excitation energies. The machine learning model is based on a deep multi-task artificial neural network, exploiting the underlying correlations between various molecular properties. The input is identical to ab initio methods, i.e. nuclear charges and Cartesian coordinates of all atoms. For small organic molecules, the accuracy of such a 'quantum machine' is similar, and sometimes superior, to modern quantum-chemical methods-at negligible computational cost.
Faculties and Departments:05 Faculty of Science > Departement Chemie > Former Organization Units Chemistry > Physikalische Chemie (Lilienfeld)
UniBasel Contributors:von Lilienfeld, Anatole
Item Type:Article, refereed
Article Subtype:Research Article
Publisher:IOP Publishing
ISSN:1367-2630
Note:Publication type according to Uni Basel Research Database: Journal article
Language:English
Identification Number:
edoc DOI:
Last Modified:25 Jan 2017 14:03
Deposited On:25 Jan 2017 14:00

Repository Staff Only: item control page