Predict the Polarizability and Order of Magnitude of Second Hyperpolarizability of Molecules by Machine Learning.

In order to determine the polarizability and hyperpolarizability of a molecule, several key parameters need to be known, including the excitation energy of the ground and excited states, the transition dipole moment, and the difference of dipole moment between the ground and excited states. In this study, a machine-learning model was developed and trained to predict the molecular polarizability and second-order hyperpolarizability on a subset of QM9 data set. The density of states was employed as input to the model. The results demonstrated that the machine-learning model effectively estimated both polarizability and the order of magnitude of second-order hyperpolarizability. However, the model was unable to predict the dipole moment and first-order hyperpolarizability, suggesting limitations in its ability to predict the difference of dipole moment between the ground and excited states. The computational efficiency of machine-learning models compared to traditional quantum mechanical calculations enables the possibility of large-scale screening of molecules that satisfy specific requirements using existing databases. This work presents a potential solution for the efficient exploration and analysis of molecules on a larger scale.

[1]  Yahya Nural,et al.  Recent advances in the nonlinear optical (NLO) properties of phthalocyanines: A review , 2021, Dyes and Pigments.

[2]  Muhammad Imran,et al.  Theoretical investigation of nonlinear optical behavior for rod and T-Shaped phenothiazine based D-π-A organic compounds and their derivatives , 2021, Journal of Saudi Chemical Society.

[3]  Wei Yan,et al.  Tin Metal Cluster Compounds as New Third-Order Nonlinear Optical Materials by Computational Study. , 2021, The journal of physical chemistry letters.

[4]  S. Anandan,et al.  Nonlinear Optical Studies of Conjugated Organic Dyes for Optical Limiting Applications , 2021 .

[5]  Yi Ding,et al.  Molecular fingerprint-based machine learning assisted QSAR model development for prediction of ionic liquid properties , 2021 .

[6]  X. Bu,et al.  Aggregation‐induced emission materials for nonlinear optics , 2021, Aggregate.

[7]  Victor Fung,et al.  Machine learned features from density of states for accurate adsorption energy prediction , 2021, Nature Communications.

[8]  Shan Chang,et al.  Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning , 2020, Frontiers in Pharmacology.

[9]  Rongjian Sa,et al.  Accelerated design of photovoltaic Ruddlesden–Popper perovskite Ca6Sn4S14−xOx using machine learning , 2020 .

[10]  Jihan Kim,et al.  Inverse design of porous materials using artificial neural networks , 2020, Science Advances.

[11]  Stefano E. Rensi,et al.  Machine learning in chemoinformatics and drug discovery. , 2018, Drug discovery today.

[12]  I. Yahia,et al.  A first principles study of key electronic, optical, second and third order nonlinear optical properties of 3-(4-chlorophenyl)-1-(pyridin-3-yl) prop-2-en-1-one: a novel D-$$\pi $$π-A type chalcone derivative , 2018 .

[13]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[14]  Pavlo O. Dral,et al.  Quantum chemistry structures and properties of 134 kilo molecules , 2014, Scientific Data.

[15]  Jean-Louis Reymond,et al.  Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17 , 2012, J. Chem. Inf. Model..

[16]  Nicola Zamboni,et al.  Metabolite identification and molecular fingerprint prediction through machine learning , 2012, Bioinform..

[17]  J. Brédas,et al.  Tuning of large second hyperpolarizabilities in organic conjugated compounds , 1994 .

[18]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[19]  Clifford E. Dykstra,et al.  Derivative Hartree—Fock theory to all orders , 1984 .

[20]  P. Lazzeretti,et al.  On the theoretical determination of molecular first hyperpolarizability , 1981 .

[21]  N. Hush,et al.  Finite-field method calculations of molecular polarisabilities. I. Theoretical basis and limitations of SCF and Galerkin treatments , 1977 .

[22]  N. S. Ostlund,et al.  Self‐Consistent Perturbation Theory. I. Finite Perturbation Methods , 1968 .

[23]  C. Roothaan,et al.  Electric Dipole Polarizability of Atoms by the Hartree—Fock Method. I. Theory for Closed‐Shell Systems , 1965 .

[24]  Masayoshi Nakano,et al.  Open-Shell-Character-Based Molecular Design Principles: Applications to Nonlinear Optics and Singlet Fission. , 2017, Chemical record.

[25]  E. Nadaraya.  On Estimating Regression , 1964 .