Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map

Most life activities of organisms are realized through protein–protein interactions, and these interactions are mainly achieved through residue–residue contact between monomer proteins. Consequently, studying residue–residue contact at the protein interaction interface can contribute to a deeper und...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanfen Lyu, Ting Xiong, Shuaibo Shi, Dong Wang, Xueqing Yang, Qihuan Liu, Zhengtan Li, Zhixin Li, Chunxia Wang, Ruiai Chen
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Nanomaterials
Subjects:
Online Access:https://www.mdpi.com/2079-4991/15/3/188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067951340748800
author Yanfen Lyu
Ting Xiong
Shuaibo Shi
Dong Wang
Xueqing Yang
Qihuan Liu
Zhengtan Li
Zhixin Li
Chunxia Wang
Ruiai Chen
author_facet Yanfen Lyu
Ting Xiong
Shuaibo Shi
Dong Wang
Xueqing Yang
Qihuan Liu
Zhengtan Li
Zhixin Li
Chunxia Wang
Ruiai Chen
author_sort Yanfen Lyu
collection DOAJ
description Most life activities of organisms are realized through protein–protein interactions, and these interactions are mainly achieved through residue–residue contact between monomer proteins. Consequently, studying residue–residue contact at the protein interaction interface can contribute to a deeper understanding of the protein–protein interaction mechanism. In this paper, we focus on the research of the trimer protein interface residue pair. Firstly, we utilize the amino acid k-interval product factor descriptor (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="normal">A</mi><mi mathvariant="normal">A</mi><mi mathvariant="normal">I</mi><mi mathvariant="normal">P</mi><mi mathvariant="normal">F</mi><mo>(</mo><mi mathvariant="normal">k</mi><mo>)</mo></mrow></semantics></math></inline-formula>) to integrate the positional information and physicochemical properties of amino acids, combined with the electric properties and geometric shape features of residues, to construct an 8 × 16 multi-feature map. This multi-feature map represents a sample composed of two residues on a trimer protein. Secondly, we construct a CNN-GRU deep learning framework to predict the trimer protein interface residue pair. The results show that when each dimer protein provides 10 prediction results and two protein–protein interaction interfaces of a trimer protein needed to be accurately predicted, the accuracy of our proposed method is 60%. When each dimer protein provides 10 prediction results and one protein–protein interaction interface of a trimer protein needs to be accurately predicted, the accuracy of our proposed method is 93%. Our results can provide experimental researchers with a limited yet precise dataset containing correct trimer protein interface residue pairs, which is of great significance in guiding the experimental resolution of the trimer protein three-dimensional structure. Furthermore, compared to other computational methods, our proposed approach exhibits superior performance in predicting residue–residue contact at the trimer protein interface.
format Article
id doaj-art-b46c778c99a54da68136a3307bf8aca0
institution DOAJ
issn 2079-4991
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Nanomaterials
spelling doaj-art-b46c778c99a54da68136a3307bf8aca02025-08-20T02:48:10ZengMDPI AGNanomaterials2079-49912025-01-0115318810.3390/nano15030188Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature MapYanfen Lyu0Ting Xiong1Shuaibo Shi2Dong Wang3Xueqing Yang4Qihuan Liu5Zhengtan Li6Zhixin Li7Chunxia Wang8Ruiai Chen9College of Veterinary Medicine, South China Agricultural University, Guangzhou 510642, ChinaCollege of Veterinary Medicine, South China Agricultural University, Guangzhou 510642, ChinaSchool of Mathematics and Physics, Hebei University of Engineering, Handan 056038, ChinaSchool of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan 056038, ChinaSchool of Mathematics and Physics, Hebei University of Engineering, Handan 056038, ChinaSchool of Mathematics and Physics, Hebei University of Engineering, Handan 056038, ChinaSchool of Mathematics and Physics, Hebei University of Engineering, Handan 056038, ChinaSchool of Mathematics and Physics, Hebei University of Engineering, Handan 056038, ChinaCollege of Landscape and Ecological Engineering, Hebei University of Engineering, Handan 056038, ChinaCollege of Veterinary Medicine, South China Agricultural University, Guangzhou 510642, ChinaMost life activities of organisms are realized through protein–protein interactions, and these interactions are mainly achieved through residue–residue contact between monomer proteins. Consequently, studying residue–residue contact at the protein interaction interface can contribute to a deeper understanding of the protein–protein interaction mechanism. In this paper, we focus on the research of the trimer protein interface residue pair. Firstly, we utilize the amino acid k-interval product factor descriptor (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="normal">A</mi><mi mathvariant="normal">A</mi><mi mathvariant="normal">I</mi><mi mathvariant="normal">P</mi><mi mathvariant="normal">F</mi><mo>(</mo><mi mathvariant="normal">k</mi><mo>)</mo></mrow></semantics></math></inline-formula>) to integrate the positional information and physicochemical properties of amino acids, combined with the electric properties and geometric shape features of residues, to construct an 8 × 16 multi-feature map. This multi-feature map represents a sample composed of two residues on a trimer protein. Secondly, we construct a CNN-GRU deep learning framework to predict the trimer protein interface residue pair. The results show that when each dimer protein provides 10 prediction results and two protein–protein interaction interfaces of a trimer protein needed to be accurately predicted, the accuracy of our proposed method is 60%. When each dimer protein provides 10 prediction results and one protein–protein interaction interface of a trimer protein needs to be accurately predicted, the accuracy of our proposed method is 93%. Our results can provide experimental researchers with a limited yet precise dataset containing correct trimer protein interface residue pairs, which is of great significance in guiding the experimental resolution of the trimer protein three-dimensional structure. Furthermore, compared to other computational methods, our proposed approach exhibits superior performance in predicting residue–residue contact at the trimer protein interface.https://www.mdpi.com/2079-4991/15/3/188trimer proteinCNN-GRUmulti-feature map
spellingShingle Yanfen Lyu
Ting Xiong
Shuaibo Shi
Dong Wang
Xueqing Yang
Qihuan Liu
Zhengtan Li
Zhixin Li
Chunxia Wang
Ruiai Chen
Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map
Nanomaterials
trimer protein
CNN-GRU
multi-feature map
title Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map
title_full Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map
title_fullStr Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map
title_full_unstemmed Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map
title_short Prediction of the Trimer Protein Interface Residue Pair by CNN-GRU Model Based on Multi-Feature Map
title_sort prediction of the trimer protein interface residue pair by cnn gru model based on multi feature map
topic trimer protein
CNN-GRU
multi-feature map
url https://www.mdpi.com/2079-4991/15/3/188
work_keys_str_mv AT yanfenlyu predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT tingxiong predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT shuaiboshi predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT dongwang predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT xueqingyang predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT qihuanliu predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT zhengtanli predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT zhixinli predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT chunxiawang predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap
AT ruiaichen predictionofthetrimerproteininterfaceresiduepairbycnngrumodelbasedonmultifeaturemap