DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks

Abstract Drug-target interactions (DTIs) are pivotal in drug discovery and development, and their accurate identification can significantly expedite the process. Numerous DTI prediction methods have emerged, yet many fail to fully harness the feature information of drugs and targets or address the i...

Full description

Saved in:
Bibliographic Details
Main Authors: Guang Yang, Yinbo Liu, Sijian Wen, Wenxi Chen, Xiaolei Zhu, Yongmei Wang
Format: Article
Language:English
Published: BMC 2025-01-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-024-06021-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832594445969653760
author Guang Yang
Yinbo Liu
Sijian Wen
Wenxi Chen
Xiaolei Zhu
Yongmei Wang
author_facet Guang Yang
Yinbo Liu
Sijian Wen
Wenxi Chen
Xiaolei Zhu
Yongmei Wang
author_sort Guang Yang
collection DOAJ
description Abstract Drug-target interactions (DTIs) are pivotal in drug discovery and development, and their accurate identification can significantly expedite the process. Numerous DTI prediction methods have emerged, yet many fail to fully harness the feature information of drugs and targets or address the issue of feature redundancy. We aim to refine DTI prediction accuracy by eliminating redundant features and capitalizing on the node topological structure to enhance feature extraction. To achieve this, we introduce a PCA-augmented multi-layer heterogeneous graph-based network that concentrates on key features throughout the encoding-decoding phase. Our approach initiates with the construction of a heterogeneous graph from various similarity metrics, which is then encoded via a graph neural network. We concatenate and integrate the resultant representation vectors to merge multi-level information. Subsequently, principal component analysis is applied to distill the most informative features, with the random forest algorithm employed for the final decoding of the integrated data. Our method outperforms six baseline models in terms of accuracy, as demonstrated by extensive experimentation. Comprehensive ablation studies, visualization of results, and in-depth case analyses further validate our framework’s efficacy and interpretability, providing a novel tool for drug discovery that integrates multimodal features.
format Article
id doaj-art-e21a7592be114661a9a0d4f454ad8287
institution Kabale University
issn 1471-2105
language English
publishDate 2025-01-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-e21a7592be114661a9a0d4f454ad82872025-01-19T12:40:54ZengBMCBMC Bioinformatics1471-21052025-01-0126112410.1186/s12859-024-06021-zDTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networksGuang Yang0Yinbo Liu1Sijian Wen2Wenxi Chen3Xiaolei Zhu4Yongmei Wang5School of Information and Artificial Intelligence, Anhui Agricultural UniversitySchool of Information and Artificial Intelligence, Anhui Agricultural UniversitySchool of Information and Artificial Intelligence, Anhui Agricultural UniversitySchool of Information and Artificial Intelligence, Anhui Agricultural UniversitySchool of Information and Artificial Intelligence, Anhui Agricultural UniversitySchool of Information and Artificial Intelligence, Anhui Agricultural UniversityAbstract Drug-target interactions (DTIs) are pivotal in drug discovery and development, and their accurate identification can significantly expedite the process. Numerous DTI prediction methods have emerged, yet many fail to fully harness the feature information of drugs and targets or address the issue of feature redundancy. We aim to refine DTI prediction accuracy by eliminating redundant features and capitalizing on the node topological structure to enhance feature extraction. To achieve this, we introduce a PCA-augmented multi-layer heterogeneous graph-based network that concentrates on key features throughout the encoding-decoding phase. Our approach initiates with the construction of a heterogeneous graph from various similarity metrics, which is then encoded via a graph neural network. We concatenate and integrate the resultant representation vectors to merge multi-level information. Subsequently, principal component analysis is applied to distill the most informative features, with the random forest algorithm employed for the final decoding of the integrated data. Our method outperforms six baseline models in terms of accuracy, as demonstrated by extensive experimentation. Comprehensive ablation studies, visualization of results, and in-depth case analyses further validate our framework’s efficacy and interpretability, providing a novel tool for drug discovery that integrates multimodal features.https://doi.org/10.1186/s12859-024-06021-zDTIs predictionHeterogeneous graph attention networksFeature concatenationPCARandom forest
spellingShingle Guang Yang
Yinbo Liu
Sijian Wen
Wenxi Chen
Xiaolei Zhu
Yongmei Wang
DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks
BMC Bioinformatics
DTIs prediction
Heterogeneous graph attention networks
Feature concatenation
PCA
Random forest
title DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks
title_full DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks
title_fullStr DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks
title_full_unstemmed DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks
title_short DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks
title_sort dti mhapr optimized drug target interaction prediction via pca enhanced features and heterogeneous graph attention networks
topic DTIs prediction
Heterogeneous graph attention networks
Feature concatenation
PCA
Random forest
url https://doi.org/10.1186/s12859-024-06021-z
work_keys_str_mv AT guangyang dtimhaproptimizeddrugtargetinteractionpredictionviapcaenhancedfeaturesandheterogeneousgraphattentionnetworks
AT yinboliu dtimhaproptimizeddrugtargetinteractionpredictionviapcaenhancedfeaturesandheterogeneousgraphattentionnetworks
AT sijianwen dtimhaproptimizeddrugtargetinteractionpredictionviapcaenhancedfeaturesandheterogeneousgraphattentionnetworks
AT wenxichen dtimhaproptimizeddrugtargetinteractionpredictionviapcaenhancedfeaturesandheterogeneousgraphattentionnetworks
AT xiaoleizhu dtimhaproptimizeddrugtargetinteractionpredictionviapcaenhancedfeaturesandheterogeneousgraphattentionnetworks
AT yongmeiwang dtimhaproptimizeddrugtargetinteractionpredictionviapcaenhancedfeaturesandheterogeneousgraphattentionnetworks