Search

Structure-based drug discovery is a process for both hit finding and optimization that relies on a validated three-dimensional model of a target biomolecule, used to rationalize the structure-function relationship for this particular target. An ultralarge virtual screening approach has emerged recently for rapid discovery of high-affinity hit compounds, but it requires substantial computational resources. This study shows that active learning with simple linear regression models can accelerate virtual screening, retrieving up to 90% of the top-1% of the docking hit list after docking just 10% of the ligands. The results demonstrate that it is unnecessary to use complex models, such as deep learning approaches, to predict the imprecise results of ligand docking with a low sampling depth. Furthermore, we explore active learning meta-parameters and find that constant batch size models with a simple ensembling method provide the best ligand retrieval rate. Finally, our approach is validated on the ultralarge size virtual screening data set, retrieving 70% of the top-0.05% of ligands after screening only 2% of the library. Altogether, this work provides a computationally accessible approach for accelerated virtual screening that can serve as a blueprint for the future design of low-compute agents for exploration of the chemical space via large-scale accelerated docking. With recent breakthroughs in protein structure prediction, this method can significantly increase accessibility for the academic community and aid in the rapid discovery of high-affinity hit compounds for various targets.

Membrane proteins are indispensable for every living organism, yet their structural organization remains underexplored. Despite the recent advancements in single-particle cryogenic electron microscopy and cryogenic electron tomography, which have significantly increased the structural coverage of membrane proteins across various kingdoms, certain scientific methods, such as time-resolved crystallography, still mostly rely on crystallization techniques, such as lipidic cubic phase (LCP) or in meso crystallization. In this study, we present an open-access blueprint for a humidity control chamber designed for LCP/ in meso crystallization experiments using a Gryphon crystallization robot. Using this chamber, we have obtained crystals of a transmembrane aspartate transporter Glt Tk from Thermococcus kodakarensis in a lipidic environment using in meso crystallization. The data collected from these crystals allowed us to perform an analysis of lipids bound to the transporter. With this publication of our open-access design of a humidity chamber, we aim to improve the accessibility of in meso protein crystallization for the scientific community., Competing Interests: The authors declare no competing financial interest., (© 2023 The Authors. Published by American Chemical Society.)