Abstract
Carbohydrate complexes are crucial in many various biological and medicinal processes. The impacts of N-acetyl on the glycosidic linkage flexibility of methyl β-D-glucopyranose, and of the glycoamino acid β-D-glucopyranose-asparagine are poorly understood at the electronic level. Furthermore, the effect of D- and L-isomers of asparagine in the complexes of N-acetyl-β-D-glucopyranose-(L)-asparagine and N-acetyl-β-D-glucopyranose-(D)-asparagine is unknown. In this study, we performed density functional theory calculations of methyl β-D-glucopyranose, methyl N-acetyl-β-D-glucopyranose, and of glycoamino acids β-D-glucopyranose-asparagine, N-acetyl-β-D-glucopyranose-(L)-asparagine and N-acetyl-β-D-glucopyranose-(D)-asparagine for studying their linkage flexibilities, total solvated energies, thermochemical properties and intra-molecular hydrogen bond formations in an aqueous solution environment using the COnductor-like Screening MOdel (COSMO) for water. We linked these density functional theory calculations to deep learning via estimating the total solvated energy of each linkage torsional angle value. Our results show that deep learning methods accurately estimate the total solvated energies of complex carbohydrate and glycopeptide species and provide linkage flexibility trends for methyl β-D-glucopyranose, methyl N-acetyl-β-D-glucopyranose, and of glycoamino acids β-D-glucopyranose-asparagine, N-acetyl-β-D-glucopyranose-(L)-asparagine and N-acetyl-β-D-glucopyranose-(D)-asparagine in agreement with density functional theory results. To the best of our knowledge, this study represents the first application of density functional theory along with deep learning for complex carbohydrate and glycopeptide species in an aqueous solution medium. In addition, this study shows that a few thousands of optimization frames from DFT calculations are enough for accurate estimations by deep learning tools.
Deep learning and density-functional theory
