Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation
… SE(3) denoising score matching (DSM) and interpret its log-… matching (DSM) [33, 15] as
maximum likelihood estimation is … K perturbed protein-ligand complexes X1, ··· , XK as negative …
maximum likelihood estimation is … K perturbed protein-ligand complexes X1, ··· , XK as negative …
InteractionNet: Modeling and explaining of noncovalent protein-ligand interactions with noncovalent graph neural network and layer-wise relevance propagation
H Cho, EK Lee, IS Choi - arXiv preprint arXiv:2005.13438, 2020 - arxiv.org
… scoring function on the structure-based drug design with data… any physical parameters,
wherein the NC interactions are … downsizing the protein-ligand structure and efficient training. …
wherein the NC interactions are … downsizing the protein-ligand structure and efficient training. …
PocketAnchor: Learning structure-based pocket representations for protein-ligand interaction prediction
… scores used in our analysis is also described in STAR Methods. To maintain an adequate
amount of training data … the probability scores of all the potential positive and negative samples…
amount of training data … the probability scores of all the potential positive and negative samples…
PharmRF: A machine‐learning scoring function to identify the best protein‐ligand complexes for structure‐based pharmacophore screening with high enrichments
… These include analyzing protein-ligand interaction … (PharmRF score bears positive sign and
Vina score carries negative … training on pharmacophoric feature counts in a large dataset as …
Vina score carries negative … training on pharmacophoric feature counts in a large dataset as …
Multitask deep networks with grid featurization achieve improved scoring performance for protein–ligand binding
… terms without considering specific protein–ligand interaction. The … Note that the scoring
function of Vina was trained on a set of … larger than 2 Å as negative pose. Kumar and coworkers …
function of Vina was trained on a set of … larger than 2 Å as negative pose. Kumar and coworkers …
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 …
Predicting drug–target interaction using a novel graph neural network with 3D structure-embedded graph representation
… model learn how protein–ligand interactions affect the node … positive, and PDBbind negative
samples with the fixed ratio … In terms of the RE score, our method shows 9–10 times better …
samples with the fixed ratio … In terms of the RE score, our method shows 9–10 times better …
Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design
PG Francoeur, T Masuda, J Sunseri, A Jia… - Journal of chemical …, 2020 - ACS Publications
… of this data set for benchmarking protein–ligand binding … parameters estimated from
experimental and simulated data … its own representation of the protein–ligand interaction in order …
experimental and simulated data … its own representation of the protein–ligand interaction in order …
[HTML][HTML] RASPD+: fast protein-ligand binding free energy prediction using simplified physicochemical features
S Holderbach, L Adam, B Jayaram… - Frontiers in molecular …, 2020 - frontiersin.org
… RASPD method and traditional scoring functions on a range … of non-covalent protein-ligand
interactions with a resolution … energy has the strongest negative correlation with the ligand …
interactions with a resolution … energy has the strongest negative correlation with the ligand …
Ranking docking poses by graph matching of protein–ligand interactions: lessons learned from the D3R Grand Challenge 2
P da Silva Figueiredo Celestino Gomes… - Journal of Computer …, 2018 - Springer
… and scoring/ranking a set of ligands for well-defined targets [5, 8,9,10,11,12,13,14]. … parameters
to the IShape similarity score [15] parametrized on a training set of 1800 protein–ligand X-…
to the IShape similarity score [15] parametrized on a training set of 1800 protein–ligand X-…