Gaussian process regression performs better than DFT and Karplus calculations for 1JCαH Spin-spin Scalar Coupling Constants

ARROYUELO, AGUSTINA.; MARTÍN, OSVALDO ANTONIO; SCHERAGA, HAROLD A.; VILA, JORGE A.

San Luis

Congreso; XLVIII Reunión Anual de la Sociedad Argentina de Biofísica; 2019

We show that Gaussian Processes regression (GPs) can predict the observed 1JCαH SSCC values for six proteins, as a function of ψ, φ and χ1, with RMSD values ranging from 1.47Hz to 10.51Hz (see Table 1). Analysis of GPs results, in terms of RMSD, shows that the torsional-angle dependence of the 1JCαH SSCC in proteins is captured mainly by the ψ torsional-angle with a lesser contribution by φ. Moreover, in the presence of ψ and φ, the addition of χ1 does not substantially help to get better predictions.