Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information

Abstract Background Prediction of protein–protein interactions (PPIs) is fundamental for identifying drug targets and understanding cellular processes. The rapid growth of PPI studies necessitates the development of efficient and accurate tools for automated prediction of PPIs. In recent years, seve...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Tang, Taiguang Shen, Jing Jiang, Weizhuo Li, Peng Wang, Sisi Yuan, Xiaofeng Cao, Yuansheng Liu
Format: Article
Language:English
Published: BMC 2025-08-01
Series:BMC Biology
Subjects:
Online Access:https://doi.org/10.1186/s12915-025-02359-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234497119191040
author Tao Tang
Taiguang Shen
Jing Jiang
Weizhuo Li
Peng Wang
Sisi Yuan
Xiaofeng Cao
Yuansheng Liu
author_facet Tao Tang
Taiguang Shen
Jing Jiang
Weizhuo Li
Peng Wang
Sisi Yuan
Xiaofeng Cao
Yuansheng Liu
author_sort Tao Tang
collection DOAJ
description Abstract Background Prediction of protein–protein interactions (PPIs) is fundamental for identifying drug targets and understanding cellular processes. The rapid growth of PPI studies necessitates the development of efficient and accurate tools for automated prediction of PPIs. In recent years, several robust deep learning models have been developed for PPI prediction and have found widespread application in proteomics research. Despite these advancements, current computational tools still face limitations in modeling both the pairwise interactions and the hierarchical relationships between proteins. Results We present HI-PPI, a novel deep learning method that integrates hierarchical representation of PPI network and interaction-specific learning for protein–protein interaction prediction. HI-PPI extracts the hierarchical information by embedding structural and relational information into hyperbolic space. A gated interaction network is then employed to extract pairwise features for interaction prediction. Experiments on multiple benchmark datasets demonstrate that HI-PPI outperforms the state-of-the-art methods; HI-PPI improves Micro-F1 scores by 2.62%–7.09% over the second-best method. Moreover, HI-PPI offers explicit interpretability of the hierarchical organization within the PPI network. The distance between the origin and the hyperbolic embedding computed by HI-PPI naturally reflects the hierarchical level of proteins. Conclusions Overall, the proposed HI-PPI effectively addresses the limitations of existing PPI prediction methods. By leveraging the hierarchical structure of PPI network, HI-PPI significantly enhances the accuracy and robustness of PPI predictions.
format Article
id doaj-art-df10a02ea4214cbf8e22c4a6b456fe04
institution Kabale University
issn 1741-7007
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series BMC Biology
spelling doaj-art-df10a02ea4214cbf8e22c4a6b456fe042025-08-20T04:03:07ZengBMCBMC Biology1741-70072025-08-0123111410.1186/s12915-025-02359-9Prediction of protein–protein interaction based on interaction-specific learning and hierarchical informationTao Tang0Taiguang Shen1Jing Jiang2Weizhuo Li3Peng Wang4Sisi Yuan5Xiaofeng Cao6Yuansheng Liu7School of Modern Posts, Nanjing University of Posts and TelecommunicationsSchool of Modern Posts, Nanjing University of Posts and TelecommunicationsCollege of Computer Science and Electronic Engineering, Hunan UniversitySchool of Modern Posts, Nanjing University of Posts and TelecommunicationsSchool of Electronic Information, Hunan First Normal UniversityDepartment of Bioinformatics and Genomics, University of North Carolina at CharlotteSchool of Computer Science and Technology, Tongji UniversityCollege of Computer Science and Electronic Engineering, Hunan UniversityAbstract Background Prediction of protein–protein interactions (PPIs) is fundamental for identifying drug targets and understanding cellular processes. The rapid growth of PPI studies necessitates the development of efficient and accurate tools for automated prediction of PPIs. In recent years, several robust deep learning models have been developed for PPI prediction and have found widespread application in proteomics research. Despite these advancements, current computational tools still face limitations in modeling both the pairwise interactions and the hierarchical relationships between proteins. Results We present HI-PPI, a novel deep learning method that integrates hierarchical representation of PPI network and interaction-specific learning for protein–protein interaction prediction. HI-PPI extracts the hierarchical information by embedding structural and relational information into hyperbolic space. A gated interaction network is then employed to extract pairwise features for interaction prediction. Experiments on multiple benchmark datasets demonstrate that HI-PPI outperforms the state-of-the-art methods; HI-PPI improves Micro-F1 scores by 2.62%–7.09% over the second-best method. Moreover, HI-PPI offers explicit interpretability of the hierarchical organization within the PPI network. The distance between the origin and the hyperbolic embedding computed by HI-PPI naturally reflects the hierarchical level of proteins. Conclusions Overall, the proposed HI-PPI effectively addresses the limitations of existing PPI prediction methods. By leveraging the hierarchical structure of PPI network, HI-PPI significantly enhances the accuracy and robustness of PPI predictions.https://doi.org/10.1186/s12915-025-02359-9Protein–protein interactionsDeep learningInteraction-specific learningHyperbolic space
spellingShingle Tao Tang
Taiguang Shen
Jing Jiang
Weizhuo Li
Peng Wang
Sisi Yuan
Xiaofeng Cao
Yuansheng Liu
Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information
BMC Biology
Protein–protein interactions
Deep learning
Interaction-specific learning
Hyperbolic space
title Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information
title_full Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information
title_fullStr Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information
title_full_unstemmed Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information
title_short Prediction of protein–protein interaction based on interaction-specific learning and hierarchical information
title_sort prediction of protein protein interaction based on interaction specific learning and hierarchical information
topic Protein–protein interactions
Deep learning
Interaction-specific learning
Hyperbolic space
url https://doi.org/10.1186/s12915-025-02359-9
work_keys_str_mv AT taotang predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT taiguangshen predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT jingjiang predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT weizhuoli predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT pengwang predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT sisiyuan predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT xiaofengcao predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation
AT yuanshengliu predictionofproteinproteininteractionbasedoninteractionspecificlearningandhierarchicalinformation