Machine learning for the structure-energy-property landscapes of molecular crystals

被引:159
作者
Musil, Felix [1 ]
De, Sandip [1 ]
Yang, Jack [2 ]
Campbell, Joshua E. [2 ]
Day, Graeme M. [2 ]
Ceriotti, Michele [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Inst Mat, Lab Computat Sci & Modelling, Natl Ctr Computat Design & Discovery Novel Mat MA, Lausanne, Switzerland
[2] Univ Southampton, Sch Chem, Southampton, Hants, England
基金
欧洲研究理事会; 瑞士国家科学基金会;
关键词
STRUCTURE PREDICTION; PACKING MOTIFS; PARAMETERS; DISCOVERY; SOLIDS; FIELD; PATH; ATOM;
D O I
10.1039/c7sc04665k
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Molecular crystals play an important role in several fields of science and technology. They frequently crystallize in different polymorphs with substantially different physical properties. To help guide the synthesis of candidate materials, atomic-scale modelling can be used to enumerate the stable polymorphs and to predict their properties, as well as to propose heuristic rules to rationalize the correlations between crystal structure and materials properties. Here we show how a recently-developed machine-learning (ML) framework can be used to achieve inexpensive and accurate predictions of the stability and properties of polymorphs, and a data-driven classification that is less biased and more flexible than typical heuristic rules. We discuss, as examples, the lattice energy and property landscapes of pentacene and two azapentacene isomers that are of interest as organic semiconductor materials. We show that we can estimate force field or DFT lattice energies with sub-kJ mol(-1) accuracy, using only a few hundred reference configurations, and reduce by a factor of ten the computational effort needed to predict charge mobility in the crystal structures. The automatic structural classification of the polymorphs reveals a more detailed picture of molecular packing than that provided by conventional heuristics, and helps disentangle the role of hydrogen bonded and p-stacking interactions in determining molecular self-assembly. This observation demonstrates that ML is not just a black-box scheme to interpolate between reference calculations, but can also be used as a tool to gain intuitive insights into structure-property relations in molecular crystal engineering.
引用
收藏
页码:1289 / 1300
页数:12
相关论文
共 77 条
[1]   High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide [J].
Artrith, Nongnuch ;
Morawietz, Tobias ;
Behler, Joerg .
PHYSICAL REVIEW B, 2011, 83 (15)
[2]   Machine learning unifies the modeling of materials and molecules [J].
Bartok, Albert P. ;
De, Sandip ;
Poelking, Carl ;
Bernstein, Noam ;
Kermode, James R. ;
Csanyi, Gabor ;
Ceriotti, Michele .
SCIENCE ADVANCES, 2017, 3 (12)
[3]   On representing chemical environments [J].
Bartok, Albert P. ;
Kondor, Risi ;
Csanyi, Gabor .
PHYSICAL REVIEW B, 2013, 87 (18)
[4]   Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons [J].
Bartok, Albert P. ;
Payne, Mike C. ;
Kondor, Risi ;
Csanyi, Gabor .
PHYSICAL REVIEW LETTERS, 2010, 104 (13)
[5]   Ritonavir: An extraordinary example of conformational polymorphism [J].
Bauer, J ;
Spanton, S ;
Henry, R ;
Quick, J ;
Dziki, W ;
Porter, W ;
Morris, J .
PHARMACEUTICAL RESEARCH, 2001, 18 (06) :859-866
[6]   Generalized neural-network representation of high-dimensional potential-energy surfaces [J].
Behler, Joerg ;
Parrinello, Michele .
PHYSICAL REVIEW LETTERS, 2007, 98 (14)
[7]  
Berg C., 1984, HARMONIC ANAL SEMIGR, P86
[8]   Molecular crystals - Pinching polymorphs [J].
Bernstein, J .
NATURE MATERIALS, 2005, 4 (06) :427-428
[9]   Predicted energy-structure-function maps for the evaluation of small molecule organic semiconductors [J].
Campbell, Josh E. ;
Yang, Jack ;
Day, Graeme M. .
JOURNAL OF MATERIALS CHEMISTRY C, 2017, 5 (30) :7574-7584
[10]   Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection [J].
Campello, Ricardo J. G. B. ;
Moulavi, Davoud ;
Zimek, Arthur ;
Sander, Joerg .
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2015, 10 (01)