期刊
JOURNAL OF CHEMICAL INFORMATION AND MODELING
卷 56, 期 12, 页码 2495-2506出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jcim.6b00355
关键词
-
类别
资金
- Oswaldo Cruz Foundation
- Faperj [E-26/111.401/2013]
- CNPq.Papes [VI./407741/2012-7]
In this work, we propose a deep learning approach to improve docking-based virtual screening. The deep neural network that is introduced, DeepVS, uses the output of a docking program and learns how to extract relevant features from basic data such as atom and residues types obtained from protein ligand complexes. Our approach introduces the use of atom and amino acid embeddings and implements an effective way of creating distributed vector representations of protein ligand complexes by modeling the compound as a set of atom contexts that is further processed by a convolutional layer. One of the main advantages of the proposed method is that it does not require feature engineering. We evaluate DeepVS on the Directory of Useful Decoys (DUD), using the output of two docking programs: Autodock Vina1.1.2 and Dock 6.6. Using a strict evaluation with leave-one-out cross-validation, DeepVS outperforms the docking programs, with regard to both AUC ROC and enrichment factor. Moreover, using the output of Autodock DeepVS achieves, an AUC ROC of 0.81, which, to the best of our knowledge, is the best AUC reported so far for virtual screening using the 40 receptors from the DUD.
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