دورية أكاديمية
Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states.
| العنوان: | Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states. |
|---|---|
| المؤلفون: | Husch T; Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, USA., Sun J; Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, USA., Cheng L; Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, USA., Lee SJR; Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, USA., Miller TF 3rd; Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, USA. |
| المصدر: | The Journal of chemical physics [J Chem Phys] 2021 Feb 14; Vol. 154 (6), pp. 064108. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: American Institute of Physics Country of Publication: United States NLM ID: 0375360 Publication Model: Print Cited Medium: Internet ISSN: 1089-7690 (Electronic) Linking ISSN: 00219606 NLM ISO Abbreviation: J Chem Phys Subsets: PubMed not MEDLINE; MEDLINE |
| أسماء مطبوعة: | Publication: New York, NY : American Institute of Physics Original Publication: Lancaster, Pa., American Institute of Physics. |
| مستخلص: | Molecular-orbital-based machine learning (MOB-ML) provides a general framework for the prediction of accurate correlation energies at the cost of obtaining molecular orbitals. The application of Nesbet's theorem makes it possible to recast a typical extrapolation task, training on correlation energies for small molecules and predicting correlation energies for large molecules, into an interpolation task based on the properties of orbital pairs. We demonstrate the importance of preserving physical constraints, including invariance conditions and size consistency, when generating the input for the machine learning model. Numerical improvements are demonstrated for different datasets covering total and relative energies for thermally accessible organic and transition-metal containing molecules, non-covalent interactions, and transition-state energies. MOB-ML requires training data from only 1% of the QM7b-T dataset (i.e., only 70 organic molecules with seven and fewer heavy atoms) to predict the total energy of the remaining 99% of this dataset with sub-kcal/mol accuracy. This MOB-ML model is significantly more accurate than other methods when transferred to a dataset comprising of 13 heavy atom molecules, exhibiting no loss of accuracy on a size intensive (i.e., per-electron) basis. It is shown that MOB-ML also works well for extrapolating to transition-state structures, predicting the barrier region for malonaldehyde intramolecular proton-transfer to within 0.35 kcal/mol when only trained on reactant/product-like structures. Finally, the use of the Gaussian process variance enables an active learning strategy for extending the MOB-ML model to new regions of chemical space with minimal effort. We demonstrate this active learning strategy by extending a QM7b-T model to describe non-covalent interactions in the protein backbone-backbone interaction dataset to an accuracy of 0.28 kcal/mol. |
| تواريخ الأحداث: | Date Created: 20210216 Date Completed: 20210217 Latest Revision: 20210217 |
| رمز التحديث: | 20231215 |
| DOI: | 10.1063/5.0032362 |
| PMID: | 33588560 |
| قاعدة البيانات: | MEDLINE |
Find this article in full text from Scitation. | تدمد: | 1089-7690 |
|---|---|
| DOI: | 10.1063/5.0032362 |