The prediction by the machine learning using molecular orbital energies as an explanatory variable is attempted to predict the strength of anxiolytics, anti-anxiety, and muscle relaxant of benzodiazepine anxiolytics. We also attempt to predict half-life of concentration in the body T1/2, and time to reach maximum body concentration Tmax of benzodiazepine anxiolytics with the same procedure. The molecular orbital calculations are performed at 6-31G(d, p) level and random forest is used as regression method. The number of molecular orbitals is varied from 2 to 20 and it is found that 4 or 6 is almost sufficient for the prediction of these 5 objective variables. Finally, the predictions of five properties in the present study are fairly well agreed with the experiments by machine learning employing the molecular orbital energies as the only explanatory variables.
Prediction of molecular properties with machine learning and molecular orbital energies
Hiroyuki Teramae, Meiyan Xuan, Jun Takayama, Mari Okazaki, Takeshi Sakamoto; Prediction of molecular properties with machine learning and molecular orbital energies. AIP Conf. Proc. 23 November 2022; 2611 (1): 020007. https://doi.org/10.1063/5.0119589
Download citation file: