Prediction of Transient and Permanent Protein Interactions Using AI Methods

Overview

Journal Bioinformation

Specialty Biology

Date 2023 Oct 27

PMID 37885791

Authors

Kiran Kumar A

Syed Mohammad Shayez Karim

Mayank Kumar

Rathore Ravindranath Singh

Affiliations

Soon will be listed here.

Abstract

Protein-protein interactions (PPIs) can be classified as permanent or transient interactions based on their stability or lifetime. Understanding the precise details of such protein interactions will pave the way for the discovery of inhibitors and for understanding the nature and function of PPIs. In the present work, 43 relevant physicochemical, geometrical and structural features were calculated for a curated dataset from the literature, comprising of 402 protein-protein complexes of permanent and transient categories, and 5 different Supervised Machine Learning models were developed with to predict transient and permanent PPI. Additionally, deep learning method with Artificial Neural Network was also performed using and . Predicted models achieved accuracy ranging from 76.54% to 82.71% and k-NN has achieved the highest accuracy. Detailed analysis of these methods revealed that Interface areas such as Percent interface accessible area, Interface accessible area and Total interface area and the parameters defining the shape of the PPI interface such as Planarity, Eccentricity and Circularity are the most discriminating factors between these two categories. The present method could serve as an effective tool to understand the mechanism of protein association and to predict the transient and permanent interactions, which could supplement the costly and time-consuming experimental techniques.

References

Wang Q, Yu S, Qi X, Hu Y, Zheng W, Shi J . [Overview of logistic regression model analysis and application]. Zhonghua Yu Fang Yi Xue Za Zhi. 2019; 53(9):955-960. DOI: 10.3760/cma.j.issn.0253-9624.2019.09.018. View

Sudha G, Nussinov R, Srinivasan N . An overview of recent advances in structural bioinformatics of protein-protein interactions and a guide to their principles. Prog Biophys Mol Biol. 2014; 116(2-3):141-50. DOI: 10.1016/j.pbiomolbio.2014.07.004. View

Plattner N, Doerr S, De Fabritiis G, Noe F . Complete protein-protein association kinetics in atomic detail revealed by molecular dynamics simulations and Markov modelling. Nat Chem. 2017; 9(10):1005-1011. DOI: 10.1038/nchem.2785. View

Kastritis P, Moal I, Hwang H, Weng Z, Bates P, Bonvin A . A structure-based benchmark for protein-protein binding affinity. Protein Sci. 2011; 20(3):482-91. PMC: 3064828. DOI: 10.1002/pro.580. View

Kim D, Park S, Kim D, Jeong M, Noh J, Kwon Y . Direct visualization of single-molecule membrane protein interactions in living cells. PLoS Biol. 2018; 16(12):e2006660. PMC: 6307816. DOI: 10.1371/journal.pbio.2006660. View

Venkatesan K, Rual J, Vazquez A, Stelzl U, Lemmens I, Hirozane-Kishikawa T . An empirical framework for binary interactome mapping. Nat Methods. 2008; 6(1):83-90. PMC: 2872561. DOI: 10.1038/nmeth.1280. View

La D, Kong M, Hoffman W, Choi Y, Kihara D . Predicting permanent and transient protein-protein interfaces. Proteins. 2012; 81(5):805-18. PMC: 4084939. DOI: 10.1002/prot.24235. View

Peng X, Wang J, Peng W, Wu F, Pan Y . Protein-protein interactions: detection, reliability assessment and applications. Brief Bioinform. 2016; 18(5):798-819. DOI: 10.1093/bib/bbw066. View

Perkins J, Diboun I, Dessailly B, Lees J, Orengo C . Transient protein-protein interactions: structural, functional, and network properties. Structure. 2010; 18(10):1233-43. DOI: 10.1016/j.str.2010.08.007. View

10.

Jayashree S, Murugavel P, Sowdhamini R, Srinivasan N . Interface residues of transient protein-protein complexes have extensive intra-protein interactions apart from inter-protein interactions. Biol Direct. 2019; 14(1):1. PMC: 6334431. DOI: 10.1186/s13062-019-0232-2. View

11.

Zhang S, Li X, Zong M, Zhu X, Wang R . Efficient kNN Classification With Different Numbers of Nearest Neighbors. IEEE Trans Neural Netw Learn Syst. 2017; 29(5):1774-1785. DOI: 10.1109/TNNLS.2017.2673241. View

12.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

13.

Yugandhar K, Gromiha M . Feature selection and classification of protein-protein complexes based on their binding affinities using machine learning approaches. Proteins. 2014; 82(9):2088-96. DOI: 10.1002/prot.24564. View

14.

George A, Lacerda M, Syllwasschy B, Hopp M, Wissbrock A, Imhof D . HeMoQuest: a webserver for qualitative prediction of transient heme binding to protein motifs. BMC Bioinformatics. 2020; 21(1):124. PMC: 7099796. DOI: 10.1186/s12859-020-3420-2. View

15.

Markmiller S, Soltanieh S, Server K, Mak R, Jin W, Fang M . Context-Dependent and Disease-Specific Diversity in Protein Interactions within Stress Granules. Cell. 2018; 172(3):590-604.e13. PMC: 5969999. DOI: 10.1016/j.cell.2017.12.032. View

16.

Rong Y, Padron A, Hagerty K, Nelson N, Chi S, Keyhani N . Post hoc support vector machine learning for impedimetric biosensors based on weak protein-ligand interactions. Analyst. 2018; 143(9):2066-2075. DOI: 10.1039/c8an00065d. View

17.

Block P, Paern J, Hullermeier E, Sanschagrin P, Sotriffer C, Klebe G . Physicochemical descriptors to discriminate protein-protein interactions in permanent and transient complexes selected by means of machine learning algorithms. Proteins. 2006; 65(3):607-22. DOI: 10.1002/prot.21104. View

18.

Nero T, Morton C, Holien J, Wielens J, Parker M . Oncogenic protein interfaces: small molecules, big challenges. Nat Rev Cancer. 2014; 14(4):248-62. DOI: 10.1038/nrc3690. View

19.

Villoutreix B, Kuenemann M, Poyet J, Bruzzoni-Giovanelli H, Labbe C, Lagorce D . Drug-Like Protein-Protein Interaction Modulators: Challenges and Opportunities for Drug Discovery and Chemical Biology. Mol Inform. 2014; 33(6-7):414-437. PMC: 4160817. DOI: 10.1002/minf.201400040. View

20.

Ding Z, Kihara D . Computational identification of protein-protein interactions in model plant proteomes. Sci Rep. 2019; 9(1):8740. PMC: 6584649. DOI: 10.1038/s41598-019-45072-8. View