期刊
JOURNAL OF CHEMICAL INFORMATION AND MODELING
卷 62, 期 12, 页码 2923-2932出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jcim.2c00127
关键词
-
类别
资金
- National Science Foundation
- National Institutes for Health
- NSF [1955815, 1629129, 1629915, 1931531, 2008398, 2028929]
- National Institutes of Health (NIH) [1R01AG065294, 1R35GM134864, 1RF1AG071675]
- Passan Foundation
- National Center for Advancing Translational Sciences, NIH [UL1 TR002014]
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [2008398] Funding Source: National Science Foundation
Modern drug discovery is costly and time-consuming. Computational approaches help reduce costs, but traditional software has low accuracy and high latency. MedusaGraph is a novel framework based on graph neural networks that generates docking poses directly and achieves 10 to 100 times speedup compared to current methods with slightly better accuracy.
Modern day drug discovery is extremely expensive and time consuming. Although computational approaches help accelerate and decrease the cost of drug discovery, existing computational software packages for docking-based drug discovery suffer from both low accuracy and high latency. A few recent machine learning-based approaches have been proposed for virtual screening by improving the ability to evaluate protein-ligand binding affinity, but such methods rely heavily on conventional docking software to sample docking poses, which results in excessive execution latencies. Here, we propose and evaluate a novel graph neural network (GNN)-based framework, MedusaGraph, which includes both pose-prediction (sampling) and pose-selection (scoring) models. Unlike the previous machine learning-centric studies, MedusaGraph generates the docking poses directly and achieves from 10 to 100 times speedup compared to state-of-the-art approaches, while having a slightly better docking accuracy.
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