Cargando…

MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction

The accurate prediction of drug–target binding affinity (DTA) is an essential step in drug discovery and drug repositioning. Although deep learning methods have been widely adopted for DTA prediction, the complexity of extracting drug and target protein features hampers the accuracy of these predict...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Shudong, Song, Xuanmo, Zhang, Yuanyuan, Zhang, Kuijie, Liu, Yingye, Ren, Chuanru, Pang, Shanchen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10179712/
https://www.ncbi.nlm.nih.gov/pubmed/37176031
http://dx.doi.org/10.3390/ijms24098326
_version_ 1785041162799677440
author Wang, Shudong
Song, Xuanmo
Zhang, Yuanyuan
Zhang, Kuijie
Liu, Yingye
Ren, Chuanru
Pang, Shanchen
author_facet Wang, Shudong
Song, Xuanmo
Zhang, Yuanyuan
Zhang, Kuijie
Liu, Yingye
Ren, Chuanru
Pang, Shanchen
author_sort Wang, Shudong
collection PubMed
description The accurate prediction of drug–target binding affinity (DTA) is an essential step in drug discovery and drug repositioning. Although deep learning methods have been widely adopted for DTA prediction, the complexity of extracting drug and target protein features hampers the accuracy of these predictions. In this study, we propose a novel model for DTA prediction named MSGNN-DTA, which leverages a fused multi-scale topological feature approach based on graph neural networks (GNNs). To address the challenge of accurately extracting drug and target protein features, we introduce a gated skip-connection mechanism during the feature learning process to fuse multi-scale topological features, resulting in information-rich representations of drugs and proteins. Our approach constructs drug atom graphs, motif graphs, and weighted protein graphs to fully extract topological information and provide a comprehensive understanding of underlying molecular interactions from multiple perspectives. Experimental results on two benchmark datasets demonstrate that MSGNN-DTA outperforms the state-of-the-art models in all evaluation metrics, showcasing the effectiveness of the proposed approach. Moreover, the study conducts a case study based on already FDA-approved drugs in the DrugBank dataset to highlight the potential of the MSGNN-DTA framework in identifying drug candidates for specific targets, which could accelerate the process of virtual screening and drug repositioning.
format Online
Article
Text
id pubmed-10179712
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101797122023-05-13 MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction Wang, Shudong Song, Xuanmo Zhang, Yuanyuan Zhang, Kuijie Liu, Yingye Ren, Chuanru Pang, Shanchen Int J Mol Sci Article The accurate prediction of drug–target binding affinity (DTA) is an essential step in drug discovery and drug repositioning. Although deep learning methods have been widely adopted for DTA prediction, the complexity of extracting drug and target protein features hampers the accuracy of these predictions. In this study, we propose a novel model for DTA prediction named MSGNN-DTA, which leverages a fused multi-scale topological feature approach based on graph neural networks (GNNs). To address the challenge of accurately extracting drug and target protein features, we introduce a gated skip-connection mechanism during the feature learning process to fuse multi-scale topological features, resulting in information-rich representations of drugs and proteins. Our approach constructs drug atom graphs, motif graphs, and weighted protein graphs to fully extract topological information and provide a comprehensive understanding of underlying molecular interactions from multiple perspectives. Experimental results on two benchmark datasets demonstrate that MSGNN-DTA outperforms the state-of-the-art models in all evaluation metrics, showcasing the effectiveness of the proposed approach. Moreover, the study conducts a case study based on already FDA-approved drugs in the DrugBank dataset to highlight the potential of the MSGNN-DTA framework in identifying drug candidates for specific targets, which could accelerate the process of virtual screening and drug repositioning. MDPI 2023-05-05 /pmc/articles/PMC10179712/ /pubmed/37176031 http://dx.doi.org/10.3390/ijms24098326 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Shudong
Song, Xuanmo
Zhang, Yuanyuan
Zhang, Kuijie
Liu, Yingye
Ren, Chuanru
Pang, Shanchen
MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction
title MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction
title_full MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction
title_fullStr MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction
title_full_unstemmed MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction
title_short MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug–Target Binding Affinity Prediction
title_sort msgnn-dta: multi-scale topological feature fusion based on graph neural networks for drug–target binding affinity prediction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10179712/
https://www.ncbi.nlm.nih.gov/pubmed/37176031
http://dx.doi.org/10.3390/ijms24098326
work_keys_str_mv AT wangshudong msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction
AT songxuanmo msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction
AT zhangyuanyuan msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction
AT zhangkuijie msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction
AT liuyingye msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction
AT renchuanru msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction
AT pangshanchen msgnndtamultiscaletopologicalfeaturefusionbasedongraphneuralnetworksfordrugtargetbindingaffinityprediction