| Reference : Many-Body Descriptors for Predicting Molecular Properties with Machine Learning: Anal... |
| Scientific journals : Article | |||
| Physical, chemical, mathematical & earth Sciences : Physics | |||
| Physics and Materials Science | |||
| http://hdl.handle.net/10993/37899 | |||
| Many-Body Descriptors for Predicting Molecular Properties with Machine Learning: Analysis of Pairwise and Three-Body Interactions in Molecules | |
| English | |
| Pronobis, Wiktor* [Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany] | |
Tkatchenko, Alexandre*  [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Physics and Materials Science Research Unit >] | |
| Müller, Klaus-Robert [] | |
| * These authors have contributed equally to this work. | |
| 11-May-2018 | |
| Journal of Chemical Theory and Computation | |
| American Chemical Society | |
| 14 | |
| 13 | |
| Yes | |
| International | |
| 1549-9618 | |
| 1549-9626 | |
| DC | |
| [en] Machine learning (ML) based prediction of molecular properties
across chemical compound space is an important and alternative approach to efficiently estimate the solutions of highly complex many-electron problems in chemistry and physics. Statistical methods represent molecules as descriptors that should encode molecular symmetries and interactions between atoms. Many such descriptors have been proposed; all of them have advantages and limitations. Here, we propose a set of general two-body and three-body interaction descriptors which are invariant to translation, rotation, and atomic indexing. By adapting the successfully used kernel ridge regression methods of machine learning, we evaluate our descriptors on predicting several properties of small organic molecules calculated using density-functional theory. We use two data sets. The GDB-7 set contains 6868 molecules with up to 7 heavy atoms of type CNO. The GDB-9 set is composed of 131722 molecules with up to 9 heavy atoms containing CNO. When trained on 5000 random molecules, our best model achieves an accuracy of 0.8 kcal/mol (on the remaining 1868 molecules of GDB-7) and 1.5 kcal/mol (on the remaining 126722 molecules of GDB-9) respectively. Applying a linear regression model on our novel many-body descriptors performs almost equal to a nonlinear kernelized model. Linear models are readily interpretable: a feature importance ranking measure helps to obtain qualitative and quantitative insights on the importance of two- and three-body molecular interactions for predicting molecular properties computed with quantum-mechanical methods. | |
| Researchers ; Professionals ; Students ; General public ; Others | |
| http://hdl.handle.net/10993/37899 | |
| 10.1021/acs.jctc.8b00110 | |
| H2020 ; 725291 - BeStMo - Beyond Static Molecules: Modeling Quantum Fluctuations in Complex Molecular Environments |
| File(s) associated to this reference | ||||||||||||||
|
Fulltext file(s):
| ||||||||||||||
All documents in ORBilu are protected by a user license.
