Comparing molecules and solids across structural and alchemical space.

By Sandip De, A. P. Bart'ok, Gábor Csányi, Michele Ceriotti. 2015

593 citations recorded by the source corpus.

Evaluating the (dis)similarity of crystalline, disordered and molecular compounds is a critical step in the development of algorithms to navigate automatically the configuration space of complex materials. For instance, a structural similarity metric is crucial for classifying structures, searching chemical space for better compounds and materials, and driving the next generation of machine-learning techniques for predicting the stability and properties of molecules and materials. In the last few years several strategies have been designed to compare atomic coordination environments. In particular, the smooth overlap of atomic positions (SOAPs) has emerged as an elegant framework to obtain translation, rotation and permutation-invariant descriptors of groups of atoms, underlying the development of various classes of machine-learned inter-atomic potentials. Here we discuss how one can combine such local descriptors using a regularized entropy match (REMatch) approach to describe the similarity of both whole molecular and bulk periodic structures, introducing powerful metrics that enable the navigation of alchemical and structural complexities within a unified framework. Furthermore, using this kernel and a ridge regression method we can predict atomization energies for a database of small organic molecules with a mean absolute error below 1 kcal mol(-1), reaching an important milestone in the application of machine-learning techniques for the evaluation of molecular properties.

Subfields: Computational Theory and Mathematics, 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 Computational Theory and Mathematics

In Materials Chemistry

In Physical and Theoretical Chemistry

In Computational Chemistry & Drug Discovery

Citations in the corpus

Wavelet Scattering Regression of Quantum Chemical Energies (2016, methodology): “More recently machine learning algorithms have been developed to interpolate molecular energies across “chemical compound space,” fitting the potential energy surface across a range of molecules with different compositions [41, 46, 16].”
Machine Learning a General-Purpose Interatomic Potential for Silicon (2018, background): “One approach to this optimization is to maximize the dissimilarity between the elements of the representative set [153] such that the small number of environments best represents the variety of the entire set.”
Machine-learned potentials for next-generation matter simulations (2021, methodology): “The SOAP-GAP model and similar methods 76 can furthermore be used to compare environment-embedded atoms in molecules and solids 76,77 as well as to predict molecular properties 78 .”
Convolutional neural networks for atomistic systems (2017, methodology): “This approach was then successfully applied to fit the potential energy surfaces of different silicon structures, and was also successfully applied in another report [31] to traverse through chemical space and make energy predictions for small molecules within chemical accuracy.”