Search

Predicting Protein-Protein Interactions Using Graph Neural Networks: A Study on the SHS27K Dataset

Author(s)

Yiming Huang*

Affiliation(s)

Xi’an Jiaotong-Liverpool University, Suzhou, China *Corresponding Author

Abstract

Protein-protein interactions (PPIs) are fundamental to cellular function and are crucial for understanding biological processes, disease mechanisms, and potential therapeutic targets. This study investigates the role of PPI networks in biological systems, focusing on their significance in cellular processes, disease mechanisms, and drug development. By integrating experimental techniques such as yeast two-hybrid, co-immunoprecipitation, and mass spectrometry with bioinformatics methods, a high-quality PPI network was constructed. Key findings include the identification of critical protein modules and nodes involved in cellular functions like signaling and metabolism, as well as interactions linked to diseases. The research highlights the importance of PPI network analysis in advancing our understanding of life processes and in developing novel therapeutic strategies.

Keywords

Protein-Protein Interactions (PPI); PPI Networks; Bioinformatics; Graph Neural Networks; Computational Biology

References

[1] Zhang Z, Zhao Q, Gong Z, et al. Progress, challenges and opportunities of NMR and XL-MS for cellular structural biology[J]. JACS Au, 2024, 4(2): 369-383. [2] Werelusz P, Galiniak S, Mołoń M. Molecular functions of moonlighting proteins in cell metabolic processes[J]. Biochimica et Biophysica Acta (BBA)-Molecular Cell Research, 2024, 1871(1): 119598. [3] van Hilten N, Verwei N, Methorst J, et al. PMIpred: a physics-informed web server for quantitative protein–membrane interaction prediction[J]. Bioinformatics, 2024, 40(2): btae069. [4] Qi Y, Zhang C, Yuan S, et al. Liquid Y2H-Seq, a rapid and data-rich alternative to conventional yeast two-hybrid screening[J]. 2024. [5] Jin M, Xue H, Wang Z, et al. ProLLM: protein chain-of-thoughts enhanced LLM for protein-protein interaction prediction[J]. bioRxiv, 2024: 2024.04. 18.590025. [6] Zhang Q, Pan W, Bai Z, et al. Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling[J]. Advances in Neural Information Processing Systems, 2024, 37: 3332-3353. [7] Zhu X, Xue H, Zhao Z, et al. LLM as GNN: Graph Vocabulary Learning for Graph Foundation Model[J]. [8] Konstantinidou M, Arkin M R. Molecular glues for protein-protein interactions: Progressing toward a new dream[J]. Cell Chemical Biology, 2024, 31(6): 1064-1088. [9] Breckels L M, Hutchings C, Ingole K D, et al. Advances in spatial proteomics: Mapping proteome architecture from protein complexes to subcellular localizations[J]. Cell Chemical Biology, 2024, 31(9): 1665-1687. [10] Yan R, Islam M T, Xing L. Deep representation learning of protein-protein interaction networks for enhanced pattern discovery[J]. Science Advances, 2024, 10(51): eadq4324.