Machine learning of molecular electronic properties in chemical compound space

By Grgoire Montavon, Matthias Rupp , Vivekanand V Gobre, Á. Vázquez-Mayagoitia, Katja Hansen, Alexandre Tkatchenko, Klaus‐Robert Müller , O. V. Lilienfeld. 2013

659 citations recorded by the source corpus.

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.

Subfields: Atomic and Molecular Physics, and Optics, Materials Chemistry, Physical and Theoretical Chemistry, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Materials Chemistry

In Physical and Theoretical Chemistry

In Computational Chemistry & Drug Discovery

Citations in the corpus

Fast Graph Representation Learning with PyTorch Geometric (2019, background): “In detail, we provide over 60 graph kernel benchmark datasets 3 (Kersting et al., 2016), e.g. , PROTEINS or IMDB-BINARY, the citation graphs Cora, CiteSeer, PubMed and Cora-Full (Sen et al., 2008; Bojchevski & Günnemann, 2018), the Coauthor CS/Physics and Amazon Computers/Photo datasets from Shchur ”
Methods for interpreting and understanding deep neural networks (2017, methodology): “In the domain of atomistic simulations, powerful machine learning models have been produced to link molecular structure to electronic properties [36, 21, 43, 16].”
Explaining nonlinear classification decisions with deep Taylor decomposition (2015, background): “research fields such as natural language processing [13, 14], human action recognition [15, 16, 17], or physics [18, 19].”
Cormorant: Covariant Molecular Neural Networks (2019, methodology): “…in using ML methods not just for learning force ﬁelds, but also for predicting many other physical/chemical properties of atomic systems across different branches of materials science, chemistry and pharmacology [Montavon et al., 2013, Gilmer et al., 2017, Smith et al., 2017, Yao et al., 2018].”
Evaluating the Visualization of What a Deep Neural Network Has Learned (2015, background): “2599820 mated image classification [1]–[4], natural language processing [5], [6], human action recognition [7], [8], or physics [9]”
Prediction of Compressive Strength of Geopolymer Concrete Using Entirely Steel Slag Aggregates: Novel Hybrid Artificial Intelligence Approaches (2019, methodology): “In prediction problems, MAE, RMSE, and R are popular statistical validation methods for machine learning models [50].”