This article is cited in 2 papers

Communications

Towards machine learning prediction of the fluorescent protein absorption spectra

R. A. Stepanyuk^ab, I. V. Polyakov^ac, A. M. Kulakova^a, E. I. Marchenko^d, M. G. Khrenova<sup>ab

a</sup> Department of Chemistry, M.V. Lomonosov Moscow State University, Moscow, Russian Federation
^b Federal Research Centre 'Fundamentals of Biotechnology' of the Russian Academy of Sciences, Moscow, Russian Federation
^c N.M. Emanuel Institute of Biochemical Physics, Russian Academy of Sciences, Moscow, Russian Federation
^d Department of Materials Science, M.V. Lomonosov Moscow State University, Moscow, Russian Federation

Abstract: We demonstrate that machine learning models trained on a set of features obtained from QM/MM molecular dynamic trajectories of fluorescent proteins can be used to predict the chromophore dipole moment variation upon excitation, the quantity related to the electronic excitation energy. Linear regression, gradient boosting, and artificial neural network- based models were considered using cross-validation on the training dataset. Gradient boosting approach proved to be the most accurate for both internal (R² = 0.77) and external (R² = 0.7) test sets.

Keywords: machine learning, fluorescent proteins, QM/MM molecular dynamics, dipole moment variation upon excitation.

Language: English

DOI: 10.1016/j.mencom.2024.10.007

Bibliographic databases:

•