Varnavas D. Mouchlis

TL;DR: Deep reinforcement learning is a subdivision of machine learning that combines artificial neural networks with reinforcement-learning architectures as mentioned in this paper, which has successfully been employed to develop novel de novo drug design approaches using a variety of artificial networks including recurrent neural networks, convolutional neural network, generative adversarial networks, and autoencoders.

TL;DR: This review will introduce and summarize the regulation of catalytic activity and cellular localization, structural characteristics, interfacial activation and kinetics, substrate specificity, inhibitor binding and interactions, and the downstream implications for eicosanoid biosynthesis of these three important PLA2 enzymes.

TL;DR: The hypothesis that the membrane acts as anAllosteric ligand that binds at the allosteric site of the enzyme’s interfacial surface, shifting its conformation from a closed state in water to an open state at the membrane interface is supported.

TL;DR: In this article, a database of relative binding affinity of a large number of estrogen receptor (ER) and/or ERβ ligands was assembled (546 for ERα and 137 for ERβ) and both single-task learning (STL) and multitask learning (MTL) continuous quantitative structure-activity relationship (QSAR) models were developed for predicting ligand binding affinity to ERα or ERβ.

TL;DR: Multidisciplinary approaches including hydrogen/deuterium exchange mass spectrometry, molecular dynamics simulations, and other computer-aided drug design techniques have been successfully employed by the laboratory to study interactions of phospholipases with membranes, phospholIPid substrates and inhibitors.