UV–Visible Absorption Spectra of Solvated Molecules by Quantum Chemical Machine Learning

Chen, Zekun; Bononi, Fernanda; Sievers, C.; Kong, Wang-Yeuk; Donadio, Davide

doi:10.1021/acs.jctc.1c01181

Cited by 10 publications

(11 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed in Multifidelity Machine Learning, this is mathematically realized by first constructing a single-fidelity Since all calculations were performed along both MD and DFTB trajectories, the main article in most cases shows only the results arising from the MD trajectories of the molecules. For each trajectory, the training is performed with the data set structured as follows: on the target fidelity, that is TZVP, 1.5 • 2 9 = 768 excitation energies are determined. The factor of 1.5 ensures that the training data are sufficiently different for each random shuffling needed in the Model Evaluation.…”

Section: Resultsmentioning

confidence: 99%

Multifidelity Machine Learning for Molecular Excitation Energies

Vinod,

Maity,

Zaspel

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

The accurate but fast calculation of molecular excited states is still a very challenging topic. For many applications, detailed knowledge of the energy funnel in larger molecular aggregates is of key importance, requiring highly accurate excitation energies. To this end, machine learning techniques can be a very useful tool, though the cost of generating highly accurate training data sets still remains a severe challenge. To overcome this hurdle, this work proposes the use of multifidelity machine learning where very little training data from high accuracies is combined with cheaper and less accurate data to achieve the accuracy of the costlier level. In the present study, the approach is employed to predict vertical excitation energies to the first excited state for three molecules of increasing size, namely, benzene, naphthalene, and anthracene. The energies are trained and tested for conformations stemming from classical molecular dynamics and density functional based tight-binding simulations. It can be shown that the multifidelity machine learning model can achieve the same accuracy as a machine learning model built only on high-cost training data while expending a much lower computational effort to generate the data. The numerical gain observed in these benchmark test calculations was over a factor of 30 but certainly can be much higher for high-accuracy data.

show abstract

Section: Resultsmentioning

confidence: 99%

Multifidelity Machine Learning for Molecular Excitation Energies

Vinod,

Maity,

Zaspel

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

“…However, the model extension may not be straightforward, especially for larger molecules, owing to the inherent DNN complexity . Chen et al devised a framework that overcomes these limitations and enables theoretical spectral lines comparable to experimentally measured ones to be computed by coupling high-level QC calculations with an ML model that can be applied to several different molecules . McNaughton et al designed four different ML architectures based on SchNetPack, a deep tensor neural network, an MPNN, and transformer and tested the models’ prediction accuracy .…”

Section: Brief Overview Of Modern Ai Methods Used For Interpreting Sp...mentioning

confidence: 99%

Advances in the Application of Artificial Intelligence-Based Spectral Data Interpretation: A Perspective

Xue,

Sun,

Yang

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

The interpretation of spectral data, including mass, nuclear magnetic resonance, infrared, and ultraviolet–visible spectra, is critical for obtaining molecular structural information. The development of advanced sensing technology has multiplied the amount of available spectral data. Chemical experts must use basic principles corresponding to the spectral information generated by molecular fragments and functional groups. This is a time-consuming process that requires a solid professional knowledge base. In recent years, the rapid development of computer science and its applications in cheminformatics and the emergence of computer-aided expert systems have greatly reduced the difficulty in analyzing large quantities of data. For expert systems, however, the problem-solving strategy must be known in advance or extracted by human experts and translated into algorithms. Gratifyingly, the development of artificial intelligence (AI) methods has shown great promise for solving such problems. Traditional algorithms, including the latest neural network algorithms, have shown great potential for both extracting useful information and processing massive quantities of data. This Perspective highlights recent innovations covering all of the emerging AI-based spectral interpretation techniques. In addition, the main limitations and current obstacles are presented, and the corresponding directions for further research are proposed. Moreover, this Perspective gives the authors’ personal outlook on the development and future applications of spectral interpretation.

show abstract

“…In recent years, several authors have tried to bypass the computational cost of expensive QM calculations by exploiting machine learning (ML) techniques. Some works focused on obtaining estimates of excitation energies and couplings in vacuum. − Inclusion of the environment effects poses further challenges, and several works have tried to include these effects, either in excited-state properties , or by developing ground-state QM/MM potentials. − …”

Section: Introductionmentioning

confidence: 99%

“…Some works focused on obtaining estimates of excitation energies and couplings in vacuum. 17 − 20 Inclusion of the environment effects poses further challenges, and several works have tried to include these effects, either in excited-state properties 21 , 22 or by developing ground-state QM/MM potentials. 23 − 29 …”

Section: Introductionmentioning

confidence: 99%

Machine Learning Exciton Hamiltonians in Light-Harvesting Complexes

Cignoni

Cupellini

Mennucci

2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

We propose a machine learning (ML)-based strategy for an inexpensive calculation of excitonic properties of lightharvesting complexes (LHCs). The strategy uses classical molecular dynamics simulations of LHCs in their natural environment in combination with ML prediction of the excitonic Hamiltonian of the embedded aggregate of pigments. The proposed ML model can reproduce the effects of geometrical fluctuations together with those due to electrostatic and polarization interactions between the pigments and the protein. The training is performed on the chlorophylls of the major LHC of plants, but we demonstrate that the model is able to extrapolate well beyond the initial training set. Moreover, the accuracy in predicting the effects of the environment is tested on the simulation of the small changes observed in the absorption spectra of the wild-type and a mutant of a minor LHC.

show abstract

UV–Visible Absorption Spectra of Solvated Molecules by Quantum Chemical Machine Learning

Cited by 10 publications

References 95 publications

Multifidelity Machine Learning for Molecular Excitation Energies

Multifidelity Machine Learning for Molecular Excitation Energies

Advances in the Application of Artificial Intelligence-Based Spectral Data Interpretation: A Perspective

Machine Learning Exciton Hamiltonians in Light-Harvesting Complexes

Contact Info

Product

Resources

About