Deffini: A family-specific deep neural network model for structure-based virtual screening
文献类型：期刊论文
| 作者 | Zhou, Dixin1,2; Liu, Fei1; Zheng, Yiwen4; Hu, Liangjian4; Huang, Tao2; Huang, Yu S.1,3,5 |
| 刊名 | COMPUTERS IN BIOLOGY AND MEDICINE
 |
| 出版日期 | 2022-12-01 |
| 卷号 | 151页码:8 |
| 关键词 | Virtual screening Protein family -specific model Structure -based Convolutional neural network Drug discovery |
| ISSN号 | 0010-4825 |
| DOI | 10.1016/j.compbiomed.2022.106323 |
| 通讯作者 | Huang, Tao(thuang@deepdrug.com) ; Huang, Yu S.(thuang@deepdrug.com) |
| 英文摘要 | Deep learning-based virtual screening methods have been shown to significantly improve the accuracy of traditional docking-based virtual screening methods. In this paper, we developed Deffini, a structure-based virtual screening neural network model. During training, Deffini learns protein-ligand docking poses to distin-guish actives and decoys and then to predict whether a new ligand will bind to the protein target. Deffini out-performed Smina with an average AUC ROC of 0.92 and AUC PRC of 0.44 in 3-fold cross-validation on the benchmark dataset DUD-E. However, when tested on the maximum unbiased validation (MUV) dataset, Deffini achieved poor results with an average AUC ROC of 0.517. We used the family-specific training approach to train the model to improve the model performance and concluded that family-specific models performed better than the pan-family models. To explore the limits of the predictive power of the family-specific models, we con-structed Kernie, a new protein kinase dataset consisting of 358 kinases. Deffini trained with the Kernie dataset outperformed all recent benchmarks on the MUV kinases, with an average AUC ROC of 0.745, which highlights the importance of quality datasets in improving the performance of deep neural network models and the importance of using family-specific models. |
| WOS关键词 | DOCKING ; PREDICTION ; SETS |
| 资助项目 | Strategic Priority Research Program of the Chi-nese Academy of Sciences ; [XDA12050202] |
| WOS研究方向 | Life Sciences & Biomedicine - Other Topics ; Computer Science ; Engineering ; Mathematical & Computational Biology |
| 语种 | 英语 |
| WOS记录号 | WOS:000900262900001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://119.78.100.183/handle/2S10ELR8/304040]  |
| 专题 | 新药研究国家重点实验室 |
| 通讯作者 | Huang, Tao; Huang, Yu S. |
| 作者单位 | 1.Chinese Acad Sci, Shanghai Inst Materia Med, State Key Lab Drug Res, Drug Discovery & Design Ctr, Shanghai 201203, Peoples R China 2.Shenzhen Zhiyao Informat Technol Co Ltd, Shenzhen, Guangdong, Peoples R China 3.Genecast Biotechnol Co Ltd, Wuxi, Peoples R China 4.Donghua Univ, Dept Stat, 2999 North Renmin Rd, Shanghai 201620, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhou, Dixin,Liu, Fei,Zheng, Yiwen,et al. Deffini: A family-specific deep neural network model for structure-based virtual screening[J]. COMPUTERS IN BIOLOGY AND MEDICINE,2022,151:8. |
| APA | Zhou, Dixin,Liu, Fei,Zheng, Yiwen,Hu, Liangjian,Huang, Tao,&Huang, Yu S..(2022).Deffini: A family-specific deep neural network model for structure-based virtual screening.COMPUTERS IN BIOLOGY AND MEDICINE,151,8. |
| MLA | Zhou, Dixin,et al."Deffini: A family-specific deep neural network model for structure-based virtual screening".COMPUTERS IN BIOLOGY AND MEDICINE 151(2022):8. |
入库方式： OAI收割
来源：上海药物研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。