Accurate Prediction of Virus-host Protein-protein Interactions Via a Siamese Neural Network Using Deep Protein Sequence Embeddings

Overview

Journal Patterns (N Y)

Date 2022 Sep 20

PMID 36124304

Authors

Sumit Madan

Victoria Demina

Marcus Stapf

Oliver Ernst

Holger Frohlich

Affiliations

Soon will be listed here.

Abstract

Prediction and understanding of virus-host protein-protein interactions (PPIs) have relevance for the development of novel therapeutic interventions. In addition, virus-like particles open novel opportunities to deliver therapeutics to targeted cell types and tissues. Given our incomplete knowledge of PPIs on the one hand and the cost and time associated with experimental procedures on the other, we here propose a deep learning approach to predict virus-host PPIs. Our method (Siamese Tailored deep sequence Embedding of Proteins [STEP]) is based on recent deep protein sequence embedding techniques, which we integrate into a Siamese neural network. After showing the state-of-the-art performance of STEP on external datasets, we apply it to two use cases, severe acute respiratory syndrome coronavirus 2 and John Cunningham polyomavirus, to predict virus-host PPIs. Altogether our work highlights the potential of deep sequence embedding techniques originating from the field of NLP as well as explainable artificial intelligence methods for the analysis of biological sequences.

Citing Articles

HBFormer: a single-stream framework based on hybrid attention mechanism for identification of human-virus protein-protein interactions.

Zhang L, Wang S, Wang Y, Zhao T Bioinformatics. 2024; 40(12).

PMID: 39673490 PMC: 11648999. DOI: 10.1093/bioinformatics/btae724.

Transformer models in biomedicine.

Madan S, Lentzen M, Brandt J, Rueckert D, Hofmann-Apitius M, Frohlich H BMC Med Inform Decis Mak. 2024; 24(1):214.

PMID: 39075407 PMC: 11287876. DOI: 10.1186/s12911-024-02600-5.

SENSE-PPI reconstructs interactomes within, across, and between species at the genome scale.

Volzhenin K, Bittner L, Carbone A iScience. 2024; 27(7):110371.

PMID: 39055916 PMC: 11269938. DOI: 10.1016/j.isci.2024.110371.

Exploring Viral-Host Protein Interactions as Antiviral Therapies: A Computational Perspective.

Idrees S, Chen H, Panth N, Paudel K, Hansbro P Microorganisms. 2024; 12(3).

PMID: 38543681 PMC: 10975578. DOI: 10.3390/microorganisms12030630.

On the choice of negative examples for prediction of host-pathogen protein interactions.

Neumann D, Roy S, Minhas F, Ben-Hur A Front Bioinform. 2023; 2:1083292.

PMID: 36591335 PMC: 9798088. DOI: 10.3389/fbinf.2022.1083292.

References

Lalonde S, Ehrhardt D, Loque D, Chen J, Rhee S, Frommer W . Molecular and cellular approaches for the detection of protein-protein interactions: latest techniques and current limitations. Plant J. 2008; 53(4):610-35. DOI: 10.1111/j.1365-313X.2007.03332.x. View

Yang X, Yang S, Li Q, Wuchty S, Zhang Z . Prediction of human-virus protein-protein interactions through a sequence embedding-based machine learning method. Comput Struct Biotechnol J. 2020; 18:153-161. PMC: 6961065. DOI: 10.1016/j.csbj.2019.12.005. View

Ferenczy M, Marshall L, Nelson C, Atwood W, Nath A, Khalili K . Molecular biology, epidemiology, and pathogenesis of progressive multifocal leukoencephalopathy, the JC virus-induced demyelinating disease of the human brain. Clin Microbiol Rev. 2012; 25(3):471-506. PMC: 3416490. DOI: 10.1128/CMR.05031-11. View

Eid F, ElHefnawi M, Heath L . DeNovo: virus-host sequence-based protein-protein interaction prediction. Bioinformatics. 2015; 32(8):1144-50. DOI: 10.1093/bioinformatics/btv737. View

Querbes W, Benmerah A, Tosoni D, Di Fiore P, Atwood W . A JC virus-induced signal is required for infection of glial cells by a clathrin- and eps15-dependent pathway. J Virol. 2003; 78(1):250-6. PMC: 303400. DOI: 10.1128/jvi.78.1.250-256.2004. View

Heinzinger M, Elnaggar A, Wang Y, Dallago C, Nechaev D, Matthes F . Modeling aspects of the language of life through transfer-learning protein sequences. BMC Bioinformatics. 2019; 20(1):723. PMC: 6918593. DOI: 10.1186/s12859-019-3220-8. View

Chen M, Ju C, Zhou G, Chen X, Zhang T, Chang K . Multifaceted protein-protein interaction prediction based on Siamese residual RCNN. Bioinformatics. 2019; 35(14):i305-i314. PMC: 6681469. DOI: 10.1093/bioinformatics/btz328. View

Menche J, Sharma A, Kitsak M, Ghiassian S, Vidal M, Loscalzo J . Disease networks. Uncovering disease-disease relationships through the incomplete interactome. Science. 2015; 347(6224):1257601. PMC: 4435741. DOI: 10.1126/science.1257601. View

Yesilkaya U, Balcioglu Y, Sahin S . Reissuing the sigma receptors for SARS-CoV-2. J Clin Neurosci. 2020; 80:72-73. PMC: 7418634. DOI: 10.1016/j.jocn.2020.08.014. View

10.

Du H, Chen F, Liu H, Hong P . Network-based virus-host interaction prediction with application to SARS-CoV-2. Patterns (N Y). 2021; 2(5):100242. PMC: 8006187. DOI: 10.1016/j.patter.2021.100242. View

11.

Oughtred R, Rust J, Chang C, Breitkreutz B, Stark C, Willems A . The BioGRID database: A comprehensive biomedical resource of curated protein, genetic, and chemical interactions. Protein Sci. 2020; 30(1):187-200. PMC: 7737760. DOI: 10.1002/pro.3978. View

12.

Gordon D, Jang G, Bouhaddou M, Xu J, Obernier K, White K . A SARS-CoV-2 protein interaction map reveals targets for drug repurposing. Nature. 2020; 583(7816):459-468. PMC: 7431030. DOI: 10.1038/s41586-020-2286-9. View

13.

Guo Y, Yu L, Wen Z, Li M . Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences. Nucleic Acids Res. 2008; 36(9):3025-30. PMC: 2396404. DOI: 10.1093/nar/gkn159. View

14.

Boothpur R, Brennan D . Human polyoma viruses and disease with emphasis on clinical BK and JC. J Clin Virol. 2010; 47(4):306-12. PMC: 3774018. DOI: 10.1016/j.jcv.2009.12.006. View

15.

Huang Y, Lu H, Zhang L, Wu Z . Sigma-2 receptor ligands and their perspectives in cancer diagnosis and therapy. Med Res Rev. 2013; 34(3):532-66. DOI: 10.1002/med.21297. View

16.

Teichmann S, Chothia C . Immunoglobulin superfamily proteins in Caenorhabditis elegans. J Mol Biol. 2000; 296(5):1367-83. DOI: 10.1006/jmbi.1999.3497. View

17.

Abate C, Niso M, Abatematteo F, Contino M, Colabufo N, Berardi F . PB28, the Sigma-1 and Sigma-2 Receptors Modulator With Potent Anti-SARS-CoV-2 Activity: A Review About Its Pharmacological Properties and Structure Affinity Relationships. Front Pharmacol. 2020; 11:589810. PMC: 7750835. DOI: 10.3389/fphar.2020.589810. View

18.

Guo L, Zhen X . Sigma-2 receptor ligands: neurobiological effects. Curr Med Chem. 2015; 22(8):989-1003. DOI: 10.2174/0929867322666150114163607. View

19.

Ammari M, Gresham C, McCarthy F, Nanduri B . HPIDB 2.0: a curated database for host-pathogen interactions. Database (Oxford). 2016; 2016. PMC: 4930832. DOI: 10.1093/database/baw103. View

20.

Greene C, Krishnan A, Wong A, Ricciotti E, Zelaya R, Himmelstein D . Understanding multicellular function and disease with human tissue-specific networks. Nat Genet. 2015; 47(6):569-76. PMC: 4828725. DOI: 10.1038/ng.3259. View