Large Scale Docking in the Cloud

Irwin, John J.; Tingle, Benjamin I

doi:10.26434/chemrxiv-2023-f182x

Cited by 1 publication

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, ultralarge library docking has been shown to provide high-affinity hit compounds for various targets − after experimental testing of only few hundreds of compounds. However, such an approach requires substantial computational resources: namely, docking of a single compound requires a few CPU-seconds, resulting in tens of CPU-years for the whole library, which in turn equals to tens of thousands of dollars of computational costs at cloud services such as Google Cloud or Amazon Web Services. − …”

Section: Introductionmentioning

confidence: 99%

“…However, such an approach requires substantial computational resources: namely, docking of a single compound requires a few CPU-seconds, resulting in tens of CPU-years for the whole library, which in turn equals to tens of thousands of dollars of computational costs at cloud services such as Google Cloud or Amazon Web Services. 16 − 18 …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Regression-Based Active Learning for Accessible Acceleration of Ultra-Large Library Docking

Marin,

Kovaleva,

Kadukova

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Structure-based drug discovery is a process for both hit finding and optimization that relies on a validated threedimensional 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 lowcompute 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.

show abstract