2024-11-17-treyde24a.md

abstract	title	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Predicting a ligand’s bound pose to a target protein is a key component of early-stage computational drug discovery. Recent developments in machine learning methods have focused on improving pose quality at the cost of model runtime. For high-throughput virtual screening applications, this exposes a capability gap that can be filled by moderately accurate but fast pose prediction. To this end, we developed QUICKBIND, a light-weight pose prediction algorithm. We assess QUICKBIND on widely used benchmarks and find that it provides an attractive trade-off between model accuracy and runtime. To facilitate virtual screening applications, we augment QUICKBIND with a binding affinity module and demonstrate its capabilities for multiple clinically-relevant drug targets. Finally, we investigate the mechanistic basis by which QUICKBIND makes predictions and find that it has learned key physicochemical properties of molecular docking, providing new insights into how machine learning models generate protein-ligand poses. By virtue of its simplicity, QUICKBIND can serve as both an effective virtual screening tool and a minimal test bed for exploring new model architectures and innovations. Model code and weights are available at this GitHub repository.	QuickBind: A Light-Weight And Interpretable Molecular Docking Model	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	treyde24a	0	QuickBind: A Light-Weight And Interpretable Molecular Docking Model	129	152	129-152	129	false	Treyde, Wojtek and Kim, Seohyun Chris and Bouatta, Nazim and AlQuraishi, Mohammed	given family Wojtek Treyde given family Seohyun Chris Kim given family Nazim Bouatta given family Mohammed AlQuraishi	2024-11-17		Proceedings of the 19th Machine Learning in Computational Biology meeting	261	inproceedings	date-parts 2024 11 17	https://raw.githubusercontent.com/mlresearch/v261/main/assets/treyde24a/treyde24a.pdf