Binding affinity prediction by pairwise function based on neural network
… larger training sets, it should not be interpreted as a negative … more of a traditional
distance-based scoring function such as … Our method treats the protein–ligand interactions in a …
distance-based scoring function such as … Our method treats the protein–ligand interactions in a …
DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening
H Zhang, T Zhang, KM Saravanan, L Liao, H Wu… - Methods, 2022 - Elsevier
… Some ML scoring functions have been designed for a specific type of protein–ligand interaction,
such as G-protein … To generate a negative dataset, we need to create decoys that do not …
such as G-protein … To generate a negative dataset, we need to create decoys that do not …
[HTML][HTML] OnionNet-2: a convolutional neural network model for predicting protein-ligand binding affinity based on residue-atom contacting shells
… In this study, we proposed a simple scoring function (called … model, we characterized the
protein-ligand interactions by the … affinity is represented by the negative logarithms (pK d ) of the …
protein-ligand interactions by the … affinity is represented by the negative logarithms (pK d ) of the …
Graph convolutional neural networks for predicting drug-target interactions
… -E: Pairwise interaction data set, we further added negative … to 3DCNN protein-ligand scoring,
Vina, RF-Score, and … for the task of predicting protein-ligand interactions, the Graph-CNN …
Vina, RF-Score, and … for the task of predicting protein-ligand interactions, the Graph-CNN …
Docking and scoring for nucleic acid–ligand interactions: Principles and current status
… and scoring functions for protein–ligand interactions might … with a set of sphere points that
represent the negative image of … , which was originally trained for protein–ligand interactions. …
represent the negative image of … , which was originally trained for protein–ligand interactions. …
Interpretable prediction of protein-ligand interaction by convolutional neural network
… Their model outperformed any other classical scoring functions … The ratio of negatives to
positives was set to 1.5:1 to avoid … achieves the lowest RMSE on training set which is used to …
positives was set to 1.5:1 to avoid … achieves the lowest RMSE on training set which is used to …
Dowker complex based machine learning (DCML) models for protein-ligand binding affinity prediction
… For topology-based protein-ligand interaction models, we … entries with negative binding
energies from the training sets for … specific scoring models and train them separatively for scoring, …
energies from the training sets for … specific scoring models and train them separatively for scoring, …
Predicting Protein-Ligand Binding Structure Using E (n) Equivariant Graph Neural Networks
… binding pose of protein-ligand interactions using an EGNN [… team led by Jose for estimating
pose scores. In this approach, … and proteins along the positive and negative axes of the three-…
pose scores. In this approach, … and proteins along the positive and negative axes of the three-…
Learning characteristics of graph neural networks predicting protein–ligand affinities
… not learn protein–ligand interactions but memorize ligand and protein training data instead.
… -prone affinity annotations including very low (negative logarithmic) potency values of less …
… -prone affinity annotations including very low (negative logarithmic) potency values of less …
[HTML][HTML] TopoFormer: Multiscale Topology-enabled Structure-to-Sequence Transformer for Protein-Ligand Interaction Predictions
… To assess the scoring capability of our models, we have … after fine-tuning, we explored which
filtration parameter, ie, the spatial scale… The dataset utilized for pre-training in this study is a …
filtration parameter, ie, the spatial scale… The dataset utilized for pre-training in this study is a …