Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1021/acs.jcim.2c00127 | JOURNAL OF CHEMICAL INFORMATION AND MODELING |
DocType | Volume | Issue |
Journal | 62 | 12 |
ISSN | Citations | PageRank |
1549-9596 | 0 | 0.34 |
References | Authors | |
30 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huaipan Jiang | 1 | 0 | 0.34 |
Jin Wang | 2 | 2 | 3.74 |
Weilin Cong | 3 | 0 | 0.34 |
Yihe Huang | 4 | 0 | 0.34 |
Morteza Ramezani | 5 | 0 | 0.34 |
Anup Sarma | 6 | 8 | 2.56 |
Nikolay V Dokholyan | 7 | 141 | 18.45 |
Mehrdad Mahdavi | 8 | 1213 | 65.15 |
Mahmut T. Kandemir | 9 | 7371 | 568.54 |