Cargando…

Electronic Descriptors for Supervised Spectroscopic Predictions

[Image: see text] Spectroscopic properties of molecules hold great importance for the description of the molecular response under the effect of UV/vis electromagnetic radiation. Computationally expensive ab initio (e.g., MultiConfigurational SCF, Coupled Cluster) or TDDFT methods are commonly used b...

Descripción completa

Detalles Bibliográficos
Autores principales: de Armas-Morejón, Carlos Manuel, Montero-Cabrera, Luis A., Rubio, Angel, Jornet-Somoza, Joaquim
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10061681/
https://www.ncbi.nlm.nih.gov/pubmed/36877528
http://dx.doi.org/10.1021/acs.jctc.2c01039
_version_ 1785017342372085760
author de Armas-Morejón, Carlos Manuel
Montero-Cabrera, Luis A.
Rubio, Angel
Jornet-Somoza, Joaquim
author_facet de Armas-Morejón, Carlos Manuel
Montero-Cabrera, Luis A.
Rubio, Angel
Jornet-Somoza, Joaquim
author_sort de Armas-Morejón, Carlos Manuel
collection PubMed
description [Image: see text] Spectroscopic properties of molecules hold great importance for the description of the molecular response under the effect of UV/vis electromagnetic radiation. Computationally expensive ab initio (e.g., MultiConfigurational SCF, Coupled Cluster) or TDDFT methods are commonly used by the quantum chemistry community to compute these properties. In this work, we propose a (supervised) Machine Learning approach to model the absorption spectra of organic molecules. Several supervised ML methods have been tested such as Kernel Ridge Regression (KRR), Multiperceptron Neural Networs (MLP), and Convolutional Neural Networks. [Ramakrishnan et al. J. Chem. Phys.2015, 143, 084111.26328822Ghosh et al. Adv. Sci.2019, 6, 1801367.] The use of only geometrical-atomic number descriptors (e.g., Coulomb Matrix) proved to be insufficient for an accurate training. [Ramakrishnan et al. J. Chem. Phys.2015, 143, 084111.26328822] Inspired by the TDDFT theory, we propose to use a set of electronic descriptors obtained from low-cost DFT methods: orbital energy differences (Δϵ(ia) = ϵ(a) – ϵ(i)), transition dipole moment between occupied and unoccupied Kohn–Sham orbitals (⟨ϕ(i)|r|ϕ(a)⟩), and when relevant, charge-transfer character of monoexcitations (R(ia)). We demonstrate that with these electronic descriptors and the use of Neural Networks we can predict not only a density of excited states but also get a very good estimation of the absorption spectrum and charge-transfer character of the electronic excited states, reaching results close to chemical accuracy (∼2 kcal/mol or ∼0.1 eV).
format Online
Article
Text
id pubmed-10061681
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-100616812023-03-31 Electronic Descriptors for Supervised Spectroscopic Predictions de Armas-Morejón, Carlos Manuel Montero-Cabrera, Luis A. Rubio, Angel Jornet-Somoza, Joaquim J Chem Theory Comput [Image: see text] Spectroscopic properties of molecules hold great importance for the description of the molecular response under the effect of UV/vis electromagnetic radiation. Computationally expensive ab initio (e.g., MultiConfigurational SCF, Coupled Cluster) or TDDFT methods are commonly used by the quantum chemistry community to compute these properties. In this work, we propose a (supervised) Machine Learning approach to model the absorption spectra of organic molecules. Several supervised ML methods have been tested such as Kernel Ridge Regression (KRR), Multiperceptron Neural Networs (MLP), and Convolutional Neural Networks. [Ramakrishnan et al. J. Chem. Phys.2015, 143, 084111.26328822Ghosh et al. Adv. Sci.2019, 6, 1801367.] The use of only geometrical-atomic number descriptors (e.g., Coulomb Matrix) proved to be insufficient for an accurate training. [Ramakrishnan et al. J. Chem. Phys.2015, 143, 084111.26328822] Inspired by the TDDFT theory, we propose to use a set of electronic descriptors obtained from low-cost DFT methods: orbital energy differences (Δϵ(ia) = ϵ(a) – ϵ(i)), transition dipole moment between occupied and unoccupied Kohn–Sham orbitals (⟨ϕ(i)|r|ϕ(a)⟩), and when relevant, charge-transfer character of monoexcitations (R(ia)). We demonstrate that with these electronic descriptors and the use of Neural Networks we can predict not only a density of excited states but also get a very good estimation of the absorption spectrum and charge-transfer character of the electronic excited states, reaching results close to chemical accuracy (∼2 kcal/mol or ∼0.1 eV). American Chemical Society 2023-03-06 /pmc/articles/PMC10061681/ /pubmed/36877528 http://dx.doi.org/10.1021/acs.jctc.2c01039 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle de Armas-Morejón, Carlos Manuel
Montero-Cabrera, Luis A.
Rubio, Angel
Jornet-Somoza, Joaquim
Electronic Descriptors for Supervised Spectroscopic Predictions
title Electronic Descriptors for Supervised Spectroscopic Predictions
title_full Electronic Descriptors for Supervised Spectroscopic Predictions
title_fullStr Electronic Descriptors for Supervised Spectroscopic Predictions
title_full_unstemmed Electronic Descriptors for Supervised Spectroscopic Predictions
title_short Electronic Descriptors for Supervised Spectroscopic Predictions
title_sort electronic descriptors for supervised spectroscopic predictions
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10061681/
https://www.ncbi.nlm.nih.gov/pubmed/36877528
http://dx.doi.org/10.1021/acs.jctc.2c01039
work_keys_str_mv AT dearmasmorejoncarlosmanuel electronicdescriptorsforsupervisedspectroscopicpredictions
AT monterocabreraluisa electronicdescriptorsforsupervisedspectroscopicpredictions
AT rubioangel electronicdescriptorsforsupervisedspectroscopicpredictions
AT jornetsomozajoaquim electronicdescriptorsforsupervisedspectroscopicpredictions