… since it was used as the “scoring power” benchmark in the … For training and performance
evaluation, the negative base-… The quality of docked poses was estimated by calculating the …

… for fast evaluation of protein–ligand interactions, and it is of … quality training data, we have
developed a linear empirical scoring … of decoy set 1 (see Table S1), which serves as a negative …

… of coefficients and parameters that are estimated from … splitting node, is the only parameter
used to fine tune our model. … to develop ET-Score by training it on docking data to evaluate its …

… on the Glide scoring function value, if “bad” contacts were not … -Score-based descriptors for
each protein–ligand complex in … By integrating intermediate-state protein–ligand interaction …

… Our model was trained using the 3772 protein-ligand … They approximate protein-ligand
interactions using equations … When the number of parameters is large, the final parameter set …

… in the initial version of RF-Score), bias towards the training dataset and the description of …
the ligand and force field parameters are assigned to the protein and ligand using ‘ff99SB’ […

… while randomly selecting a decoy pose from the same protein–ligand pair as the negative. …
of protein–ligand interactions and ensuring the effectiveness of deep learning scoring …

… the most common data sets encountered in the training and … In this way, protein-ligand
interactions are encoded implicitly … ) from bad (high RMSD) docking poses using CNNs based on …

… Our IGN model was trained using the 8298 complexes from PDBBind … bad RMSE values do
not always mean relatively bad … sensitive to the scoring of the same protein–ligand pair with …

… We distill every protein-ligand pose in our training set into a … loss to balance the influence
of the negative examples with the … code for calculating SASA protein-ligand interaction terms. …