Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information

IntroductionProtein–protein interactions (PPIs) are critical for understanding the molecular mechanisms underlying various biological processes, particularly in microbes associated with cardiovascular disease. Traditional experimental methods for detecting PPIs are often time-consuming and costly, l...

Full description

Saved in:
Bibliographic Details
Main Authors: Senyu Zhou, Jian Luo, Mei Tang, Chaojun Li, Yang Li, Wenhua He
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Pharmacology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphar.2025.1565860/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850250832779411456
author Senyu Zhou
Jian Luo
Mei Tang
Chaojun Li
Yang Li
Wenhua He
author_facet Senyu Zhou
Jian Luo
Mei Tang
Chaojun Li
Yang Li
Wenhua He
author_sort Senyu Zhou
collection DOAJ
description IntroductionProtein–protein interactions (PPIs) are critical for understanding the molecular mechanisms underlying various biological processes, particularly in microbes associated with cardiovascular disease. Traditional experimental methods for detecting PPIs are often time-consuming and costly, leading to an urgent need for reliable computational approaches.MethodsIn this study, we present a novel model, the deep denoising autoencoder for protein–protein interaction (DAEPPI), which leverages the denoising autoencoder and the CatBoost algorithm to predict PPIs from the evolutionary information of protein sequences.ResultsOur extensive experiments demonstrate the effectiveness of the DAEPPI model, achieving average prediction accuracies of 97.85% and 98.49% on yeast and human datasets, respectively. Comparative analyses with existing effective methods further validate the robustness and reliability of our model in predicting PPIs.DiscussionAdditionally, we explore the application of DAEPPI in the context of cardiovascular disease, showcasing its potential to uncover significant interactions that could contribute to the understanding of disease mechanisms. Our findings indicate that DAEPPI is a powerful tool for advancing research in proteomics and could play a pivotal role in the identification of novel therapeutic targets in cardiovascular disease.
format Article
id doaj-art-dfbaf48dbdb74080bd34cd4b29f4c845
institution OA Journals
issn 1663-9812
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Pharmacology
spelling doaj-art-dfbaf48dbdb74080bd34cd4b29f4c8452025-08-20T01:58:04ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122025-03-011610.3389/fphar.2025.15658601565860Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary informationSenyu Zhou0Jian Luo1Mei Tang2Chaojun Li3Yang Li4Wenhua He5Cardiovascular Department, The Fourth Hospital of Changsha (Integrated Traditional Chinese and Western Medicine Hospital of Changsha, Changsha Hospital of Hunan Normal University), Changsha, ChinaCardiovascular Department, The Fourth Hospital of Changsha (Integrated Traditional Chinese and Western Medicine Hospital of Changsha, Changsha Hospital of Hunan Normal University), Changsha, ChinaCardiovascular Department, The Fourth Hospital of Changsha (Integrated Traditional Chinese and Western Medicine Hospital of Changsha, Changsha Hospital of Hunan Normal University), Changsha, ChinaCardiovascular Department, The Fourth Hospital of Changsha (Integrated Traditional Chinese and Western Medicine Hospital of Changsha, Changsha Hospital of Hunan Normal University), Changsha, ChinaSchool of Computer Science and Information Engineering, Hefei University of Technology, Hefei, ChinaCardiovascular Department, The Fourth Hospital of Changsha (Integrated Traditional Chinese and Western Medicine Hospital of Changsha, Changsha Hospital of Hunan Normal University), Changsha, ChinaIntroductionProtein–protein interactions (PPIs) are critical for understanding the molecular mechanisms underlying various biological processes, particularly in microbes associated with cardiovascular disease. Traditional experimental methods for detecting PPIs are often time-consuming and costly, leading to an urgent need for reliable computational approaches.MethodsIn this study, we present a novel model, the deep denoising autoencoder for protein–protein interaction (DAEPPI), which leverages the denoising autoencoder and the CatBoost algorithm to predict PPIs from the evolutionary information of protein sequences.ResultsOur extensive experiments demonstrate the effectiveness of the DAEPPI model, achieving average prediction accuracies of 97.85% and 98.49% on yeast and human datasets, respectively. Comparative analyses with existing effective methods further validate the robustness and reliability of our model in predicting PPIs.DiscussionAdditionally, we explore the application of DAEPPI in the context of cardiovascular disease, showcasing its potential to uncover significant interactions that could contribute to the understanding of disease mechanisms. Our findings indicate that DAEPPI is a powerful tool for advancing research in proteomics and could play a pivotal role in the identification of novel therapeutic targets in cardiovascular disease.https://www.frontiersin.org/articles/10.3389/fphar.2025.1565860/fullprotein–protein interactionscardiovascular diseasedeep denoising autoencoderCatBoostevolutionary information
spellingShingle Senyu Zhou
Jian Luo
Mei Tang
Chaojun Li
Yang Li
Wenhua He
Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
Frontiers in Pharmacology
protein–protein interactions
cardiovascular disease
deep denoising autoencoder
CatBoost
evolutionary information
title Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
title_full Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
title_fullStr Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
title_full_unstemmed Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
title_short Predicting protein–protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
title_sort predicting protein protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information
topic protein–protein interactions
cardiovascular disease
deep denoising autoencoder
CatBoost
evolutionary information
url https://www.frontiersin.org/articles/10.3389/fphar.2025.1565860/full
work_keys_str_mv AT senyuzhou predictingproteinproteininteractionsinmicrobesassociatedwithcardiovasculardiseasesusingdeepdenoisingautoencodersandevolutionaryinformation
AT jianluo predictingproteinproteininteractionsinmicrobesassociatedwithcardiovasculardiseasesusingdeepdenoisingautoencodersandevolutionaryinformation
AT meitang predictingproteinproteininteractionsinmicrobesassociatedwithcardiovasculardiseasesusingdeepdenoisingautoencodersandevolutionaryinformation
AT chaojunli predictingproteinproteininteractionsinmicrobesassociatedwithcardiovasculardiseasesusingdeepdenoisingautoencodersandevolutionaryinformation
AT yangli predictingproteinproteininteractionsinmicrobesassociatedwithcardiovasculardiseasesusingdeepdenoisingautoencodersandevolutionaryinformation
AT wenhuahe predictingproteinproteininteractionsinmicrobesassociatedwithcardiovasculardiseasesusingdeepdenoisingautoencodersandevolutionaryinformation