Cargando…
SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction
Deep learning methods, which can predict the binding affinity of a drug–target protein interaction, reduce the time and cost of drug discovery. In this study, we propose a novel deep convolutional neural network called SE-OnionNet, with two squeeze-and-excitation (SE) modules, to computationally pre...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7962986/ https://www.ncbi.nlm.nih.gov/pubmed/33737946 http://dx.doi.org/10.3389/fgene.2020.607824 |
_version_ | 1783665555695206400 |
---|---|
author | Wang, Shudong Liu, Dayan Ding, Mao Du, Zhenzhen Zhong, Yue Song, Tao Zhu, Jinfu Zhao, Renteng |
author_facet | Wang, Shudong Liu, Dayan Ding, Mao Du, Zhenzhen Zhong, Yue Song, Tao Zhu, Jinfu Zhao, Renteng |
author_sort | Wang, Shudong |
collection | PubMed |
description | Deep learning methods, which can predict the binding affinity of a drug–target protein interaction, reduce the time and cost of drug discovery. In this study, we propose a novel deep convolutional neural network called SE-OnionNet, with two squeeze-and-excitation (SE) modules, to computationally predict the binding affinity of a protein–ligand complex. The OnionNet is used to extract a feature map from the three-dimensional structure of a protein–drug molecular complex. The SE module is added to the second and third convolutional layers to improve the non-linear expression of the network to improve model performance. Three different optimizers, stochastic gradient descent (SGD), Adam, and Adagrad, were also used to improve the performance of the model. A majority of protein–molecule complexes were used for training, and the comparative assessment of scoring functions (CASF-2016) was used as the benchmark. Experimental results show that our model performs better than OnionNet, Pafnucy, and AutoDock Vina. Finally, we chose the macrophage migration inhibitor factor (PDB ID: 6cbg) to test the stability and robustness of the model. We found that the prediction results were not affected by the docking position, and thus, our model is of acceptable robustness. |
format | Online Article Text |
id | pubmed-7962986 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-79629862021-03-17 SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction Wang, Shudong Liu, Dayan Ding, Mao Du, Zhenzhen Zhong, Yue Song, Tao Zhu, Jinfu Zhao, Renteng Front Genet Genetics Deep learning methods, which can predict the binding affinity of a drug–target protein interaction, reduce the time and cost of drug discovery. In this study, we propose a novel deep convolutional neural network called SE-OnionNet, with two squeeze-and-excitation (SE) modules, to computationally predict the binding affinity of a protein–ligand complex. The OnionNet is used to extract a feature map from the three-dimensional structure of a protein–drug molecular complex. The SE module is added to the second and third convolutional layers to improve the non-linear expression of the network to improve model performance. Three different optimizers, stochastic gradient descent (SGD), Adam, and Adagrad, were also used to improve the performance of the model. A majority of protein–molecule complexes were used for training, and the comparative assessment of scoring functions (CASF-2016) was used as the benchmark. Experimental results show that our model performs better than OnionNet, Pafnucy, and AutoDock Vina. Finally, we chose the macrophage migration inhibitor factor (PDB ID: 6cbg) to test the stability and robustness of the model. We found that the prediction results were not affected by the docking position, and thus, our model is of acceptable robustness. Frontiers Media S.A. 2021-02-19 /pmc/articles/PMC7962986/ /pubmed/33737946 http://dx.doi.org/10.3389/fgene.2020.607824 Text en Copyright © 2021 Wang, Liu, Ding, Du, Zhong, Song, Zhu and Zhao. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Genetics Wang, Shudong Liu, Dayan Ding, Mao Du, Zhenzhen Zhong, Yue Song, Tao Zhu, Jinfu Zhao, Renteng SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction |
title | SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction |
title_full | SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction |
title_fullStr | SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction |
title_full_unstemmed | SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction |
title_short | SE-OnionNet: A Convolution Neural Network for Protein–Ligand Binding Affinity Prediction |
title_sort | se-onionnet: a convolution neural network for protein–ligand binding affinity prediction |
topic | Genetics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7962986/ https://www.ncbi.nlm.nih.gov/pubmed/33737946 http://dx.doi.org/10.3389/fgene.2020.607824 |
work_keys_str_mv | AT wangshudong seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT liudayan seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT dingmao seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT duzhenzhen seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT zhongyue seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT songtao seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT zhujinfu seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction AT zhaorenteng seonionnetaconvolutionneuralnetworkforproteinligandbindingaffinityprediction |