Featurization strategies for proteinligand interactions and their applications in scoring function development

G Xiong, C Shen, Z Yang, D Jiang, S Liu… - Wiley …, 2022 - Wiley Online Library
Differential geometry takes the discrete and continuousinteractions and the other for both
covalent and noncovalent … between the feature matrix and modified adjacency matrix, thereby …

graphDelta: MPNN scoring function for the affinity prediction of proteinligand complexes

DS Karlov, S Sosnin, MV Fedorov, P Popov - ACS omega, 2020 - ACS Publications
… for both covalent and non-covalent interactions; in other … a novel tool for scoring of
proteinligand interactions based on … The loss function is the modified MSE loss (eq 9), where N …

Multiscale topology-enabled structure-to-sequence transformer for proteinligand interaction predictions

D Chen, J Liu, GW Wei - Nature Machine Intelligence, 2024 - nature.com
… models from algebraic topology, differential geometry and combinatorial graph theory… tuning,
we analysed the impact of spatial scale on proteinligand interactions using attention scores

Developing novel scoring functions for protein-ligand docking using machine learning

F Boyles - 2020 - ora.ox.ac.uk
… wide range of noncovalent interactions between molecules, … physical principle underlying
protein-ligand interactions. The … lead molecule is studied and modified to increase its affinity for …

A consistent scheme for gradient-based optimization of proteinligand poses

F Flachsenberg, A Meyder, K Sommer… - Journal of Chemical …, 2020 - ACS Publications
… In summary, a function to score proteinligand docking … All scoring contributions (except for
the continuous torsion score, … In salmon, the modified structure is shown that clashes with the …

Toward generalizable structure‐based deep learning models for proteinligand interaction prediction: Challenges and strategies

S Moon, W Zhung, WY Kim - Wiley Interdisciplinary Reviews …, 2024 - Wiley Online Library
… or even newly faced situations without further tuning a model. Since practical … scoring
involves predicting binding affinity values for proteinligand complexes and ranking derivative

A new paradigm for applying deep learning to proteinligand interaction prediction

Z Wang, S Wang, Y Li, J Guo, Y Wei, Y Mu… - Briefings in …, 2024 - academic.oup.com
… by our group, adopts modified formats of van der Waals and … the pocket is governed by
non-covalent interactions, and the … scoring framework for predicting proteinligand interactions, …

Non-covalent interactions from a Quantum Chemical Topology perspective

PLA Popelier - Journal of molecular modeling, 2022 - Springer
… per mole matters in the calculation of proteinligand interaction. On the other hand, a … ’s
architecture does not differentiate between intra- and intermolecular interactions: an atom …

Can machine learning consistently improve the scoring power of classical scoring functions? Insights into the role of machine learning in scoring functions

C Shen, Y Hu, Z Wang, X Zhang, H Zhong… - Briefings in …, 2021 - academic.oup.com
functional forms as force-field methods but introduce addition empirical terms to represent the
proteinligand interactions… each model were automatically tuned with BOA implemented in …

Planet: a multi-objective graph neural network model for proteinligand binding affinity prediction

X Zhang, H Gao, H Wang, Z Chen… - Journal of Chemical …, 2023 - ACS Publications
… matrix indicating the non-covalent interactions between each … The ligand feature extraction
module is modified from the … quality of a proteinligand interaction scoring function. However, …