期刊
FRONTIERS IN MOLECULAR BIOSCIENCES
卷 9, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fmolb.2022.867241
关键词
virtual docking; small molecule screening; drug screening; machine learning; binding affinity
资金
- National Institutes for Health [R35 GM134864, RF1 AG071675]
- National Science Foundation [2040667]
- Passan Foundation
- Dir for Tech, Innovation, & Partnerships
- Innovation and Technology Ecosystems [2040667] Funding Source: National Science Foundation
Virtual screening is a cost- and time-effective alternative to traditional high-throughput screening in the drug discovery process. NeuralDock, a neural network framework, accelerates computational docking and accurately predicts binding energy and affinity of protein-small molecule pairs without prior knowledge of a ligand. It has the potential to be useful in brute-force virtual screening and drug model training.
Virtual screening is a cost- and time-effective alternative to traditional high-throughput screening in the drug discovery process. Both virtual screening approaches, structure-based molecular docking and ligand-based cheminformatics, suffer from computational cost, low accuracy, and/or reliance on prior knowledge of a ligand that binds to a given target. Here, we propose a neural network framework, NeuralDock, which accelerates the process of high-quality computational docking by a factor of 10(6), and does not require prior knowledge of a ligand that binds to a given target. By approximating both protein-small molecule conformational sampling and energy-based scoring, NeuralDock accurately predicts the binding energy, and affinity of a protein-small molecule pair, based on protein pocket 3D structure and small molecule topology. We use NeuralDock and 25 GPUs to dock 937 million molecules from the ZINC database against superoxide dismutase-1 in 21 h, which we validate with physical docking using MedusaDock. Due to its speed and accuracy, NeuralDock may be useful in brute-force virtual screening of massive chemical libraries and training of generative drug models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据