… 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 …

… is the false-negative rate, TN is the true-negative rate, and FP … initially trained 12 sets of 1000
neural networks, again using … for characterizing protein–ligand interactions and developing …

… 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 …

… trained on different ligand/protein data sets. Moreover, the … not be construed as reflecting
negatively on the originals. … Hence, the alternative kind of protein/ligand interaction …

… protein−ligand interactions in the complex to the experimental binding affinity of the ligand.
In principle, the highest scoring … to position R 5 without forming bad contacts with Lys89. …

… 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’ […

… 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 …

… than polar contacts in a typical protein-ligand interaction. … parameters estimated to best fit the
observed quantitative binding … data, but there is also an opportunity to make use of negative …

… 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 …

… using a training set of protein-ligand complexes with a set of … geometric and energetic
parameters of optimal interaction for OC-… reversed as negative scores for the sake of convenience. …