DTI-MHAPR: Optimized Drug-target Interaction Prediction Via PCA-enhanced Features and Heterogeneous Graph Attention Networks

Overview

Journal BMC Bioinformatics

Publisher Biomed Central

Date 2025 Jan 12

PMID 39800678

Authors

Guang Yang

Yinbo Liu

Sijian Wen

Wenxi Chen

Xiaolei Zhu

Yongmei Wang

Affiliations

Soon will be listed here.

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.

References

Hu L, Wang X, Huang Y, Hu P, You Z . A survey on computational models for predicting protein-protein interactions. Brief Bioinform. 2021; 22(5). DOI: 10.1093/bib/bbab036. View

Tangmanussukum P, Kawichai T, Suratanee A, Plaimas K . Heterogeneous network propagation with forward similarity integration to enhance drug-target association prediction. PeerJ Comput Sci. 2022; 8:e1124. PMC: 9575853. DOI: 10.7717/peerj-cs.1124. View

Qin J, Hu Y, Yao J, Leung R, Zhou Y, Qin Y . Cell fate conversion prediction by group sparse optimization method utilizing single-cell and bulk OMICs data. Brief Bioinform. 2021; 22(6). DOI: 10.1093/bib/bbab311. View

Zhang W, Chen Y, Liu F, Luo F, Tian G, Li X . Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data. BMC Bioinformatics. 2017; 18(1):18. PMC: 5217341. DOI: 10.1186/s12859-016-1415-9. View

Keshava Prasad T, Goel R, Kandasamy K, Keerthikumar S, Kumar S, Mathivanan S . Human Protein Reference Database--2009 update. Nucleic Acids Res. 2008; 37(Database issue):D767-72. PMC: 2686490. DOI: 10.1093/nar/gkn892. View

Zeng X, Zhu S, Lu W, Liu Z, Huang J, Zhou Y . Target identification among known drugs by deep learning from heterogeneous networks. Chem Sci. 2021; 11(7):1775-1797. PMC: 8150105. DOI: 10.1039/c9sc04336e. View

Laarhoven T, Marchiori E . Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile. PLoS One. 2013; 8(6):e66952. PMC: 3694117. DOI: 10.1371/journal.pone.0066952. View

Wang W, Zhang L, Sun J, Zhao Q, Shuai J . Predicting the potential human lncRNA-miRNA interactions based on graph convolution network with conditional random field. Brief Bioinform. 2022; 23(6). DOI: 10.1093/bib/bbac463. View

Chen X, Liu M, Yan G . Drug-target interaction prediction by random walk on the heterogeneous network. Mol Biosyst. 2012; 8(7):1970-8. DOI: 10.1039/c2mb00002d. View

Zeng X, Liu L, Lu L, Zou Q . Prediction of potential disease-associated microRNAs using structural perturbation method. Bioinformatics. 2018; 34(14):2425-2432. DOI: 10.1093/bioinformatics/bty112. View

Deng L, Liu Z, Qian Y, Zhang J . Predicting circRNA-drug sensitivity associations via graph attention auto-encoder. BMC Bioinformatics. 2022; 23(1):160. PMC: 9066932. DOI: 10.1186/s12859-022-04694-y. View

10.

Wan F, Hong L, Xiao A, Jiang T, Zeng J . NeoDTI: neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions. Bioinformatics. 2018; 35(1):104-111. DOI: 10.1093/bioinformatics/bty543. View

11.

Zhao T, Hu Y, Valsdottir L, Zang T, Peng J . Identifying drug-target interactions based on graph convolutional network and deep neural network. Brief Bioinform. 2020; 22(2):2141-2150. DOI: 10.1093/bib/bbaa044. View

12.

Sheng N, Cui H, Zhang T, Xuan P . Attentional multi-level representation encoding based on convolutional and variance autoencoders for lncRNA-disease association prediction. Brief Bioinform. 2020; 22(3). DOI: 10.1093/bib/bbaa067. View

13.

Zhang R, Wang Z, Wang X, Meng Z, Cui W . MHTAN-DTI: Metapath-based hierarchical transformer and attention network for drug-target interaction prediction. Brief Bioinform. 2023; 24(2). DOI: 10.1093/bib/bbad079. View

14.

Gonen M . Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization. Bioinformatics. 2012; 28(18):2304-10. DOI: 10.1093/bioinformatics/bts360. View

15.

Rigatti S . Random Forest. J Insur Med. 2017; 47(1):31-39. DOI: 10.17849/insm-47-01-31-39.1. View

16.

Gharizadeh A, Abbasi K, Ghareyazi A, Mofrad M, Rabiee H . HGTDR: Advancing drug repurposing with heterogeneous graph transformers. Bioinformatics. 2024; 40(7). PMC: 11223801. DOI: 10.1093/bioinformatics/btae349. View

17.

Liang X, Guo M, Jiang L, Fu Y, Zhang P, Chen Y . Predicting miRNA-Disease Associations by Combining Graph and Hypergraph Convolutional Network. Interdiscip Sci. 2024; 16(2):289-303. DOI: 10.1007/s12539-023-00599-3. View

18.

Zhang Y, Liu Y, Xu J, Wang X, Peng X, Song J . Leveraging the attention mechanism to improve the identification of DNA N6-methyladenine sites. Brief Bioinform. 2021; 22(6). PMC: 8575024. DOI: 10.1093/bib/bbab351. View