Protonation Pattern and pKa The present computation is based on the electrostatic continuum model created by solving the linear Poisson-Boltzmann equation with the MEAD program (21). To facilitate a direct comparison with previous computational results (e.g. see Refs. 22 and 23), identical computat...
Sparse categorical cross-entropy only uses a portion of all classes, thereby significantly decreasing the computational time. Training was performed by minimizing the sparse categorical cross-entropy, using adaptive learning rate optimization (ADAM [30]). XGBoost is a fast implementation of the gradient...