A new paradigm for applying deep learning to protein–ligand interaction prediction
… native protein–ligand complex is expressed as the negative … protein–ligand pairs in training,
validation and test sets. The … scoring framework for predicting protein–ligand interactions, …
validation and test sets. The … scoring framework for predicting protein–ligand interactions, …
Generic protein–ligand interaction scoring by integrating physical prior knowledge and data augmentation modelling
D Cao, G Chen, J Jiang, J Yu, R Zhang… - Nature Machine …, 2024 - nature.com
… training data rather than learning protein–ligand interactions. … Third, for negative sample
construction, we first constructed negative … function form and has fewer parameters, had the best …
construction, we first constructed negative … function form and has fewer parameters, had the best …
Artificial intelligence in the prediction of protein–ligand interactions: recent advances and future directions
… for new data, a sufficient amount of training data is required. The … model with existing scoring
functions on the same test set. All … sets, whereas the remainder were labeled as negative …
functions on the same test set. All … sets, whereas the remainder were labeled as negative …
Baseline model for predicting protein–ligand unbinding kinetics through machine learning
N Amangeldiuly, D Karlov… - Journal of Chemical …, 2020 - ACS Publications
… 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 …
each protein–ligand complex in … By integrating intermediate-state protein–ligand interaction …
DEELIG: A deep learning approach to predict protein-ligand binding affinity
… the degree of protein-ligand interactions and is a useful … -based approach is the negative
natural logarithmic value of Kd … Training of atomic model for 35 epochs achieved MAE score of …
natural logarithmic value of Kd … Training of atomic model for 35 epochs achieved MAE score of …
Protein-ligand interaction graphs: Learning from ligand-shaped 3d interaction graphs to improve binding affinity prediction
… 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 …
evaluation, the negative base-… The quality of docked poses was estimated by calculating the …
On the frustration to predict binding affinities from protein–ligand structures with deep neural networks
… that a model trained on protein–ligand interactions (I model) … the PDBbind training set
on the scoring power of MPNN … parameter, notably for models trained only on protein–ligand …
on the scoring power of MPNN … parameter, notably for models trained only on protein–ligand …
ET‐score: Improving Protein‐ligand Binding Affinity Prediction Based on Distance‐weighted Interatomic Contact Features Using Extremely Randomized Trees …
… 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 …
used to fine tune our model. … to develop ET-Score by training it on docking data to evaluate its …
Modern machine‐learning for binding affinity estimation of protein–ligand complexes: Progress, opportunities, and challenges
T Harren, T Gutermuth, C Grebner… - Wiley …, 2024 - Wiley Online Library
… using them as training data for machine-learning scoring … task, a cutoff is set, which separates
good from bad poses, and the … size, which use a protein–ligand interaction as the center. …
good from bad poses, and the … size, which use a protein–ligand interaction as the center. …
EquiScore: A generic protein-ligand interaction scoring method integrating physical prior knowledge with data augmentation modeling
D Cao, G Chen, J Jiang, J Yu, R Zhang, M Chen… - bioRxiv, 2023 - biorxiv.org
… This way, the model cannot distinguish positive and negative … and can be modulated by
a parameter α to adjust the weight … the PDBscreen dataset, we trained a model using an …
a parameter α to adjust the weight … the PDBscreen dataset, we trained a model using an …