Graph-based machine learning model for weight prediction in protein–protein networks
BMC Bioinformatics · 2024
DOI: 10.1186/s12859-024-05973-6 ↗At a glance
Journal article in BMC Bioinformatics, 2024. Written by Hajer Akid and 5 co-authors. Institution: ICube, University of Strasbourg, 67412, Illkirch Cedex, France. akid.hajer@gmail.com. Major MEDLINE topics: Machine Learning, Protein Interaction Mapping, Saccharomyces cerevisiae. Cited 4 times so far (Crossref); 50 references. The full text is freely available (open access, CC BY-NC-ND 4.0).
Abstract (original language)
Proteins interact with each other in complex ways to perform significant biological functions. These interactions, known as protein-protein interactions (PPIs), can be depicted as a graph where proteins are nodes and their interactions are edges. The development of high-throughput experimental technologies allows for the generation of numerous data which permits increasing the sophistication of PPI models. However, despite significant progress, current PPI networks remain incomplete. Discovering missing interactions through experimental techniques can be costly, time-consuming, and challenging. Therefore, computational approaches have emerged as valuable tools for predicting missing interactions. In PPI networks, a graph is usually used to model the interactions between proteins. An edge between two proteins indicates a known interaction, while the absence of an edge means the interaction is not known or missed. However, this binary representation overlooks the reliability of known interactions when predicting new ones. To address this challenge, we propose a novel approach for link prediction in weighted protein-protein networks, where interaction weights denote confidence scores. By leveraging data from the yeast Saccharomyces cerevisiae obtained from the STRING database, we introduce a new model that combines similarity-based algorithms and aggregated confidence score weights for accurate link prediction purposes. Our model significantly improves prediction accuracy, surpassing traditional approaches in terms of Mean Absolute Error, Mean Relative Absolute Error, and Root Mean Square Error. Our proposed approach holds the potential for improved accuracy in predicting PPIs, which is crucial for better understanding the underlying biological processes.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- ICube, University of Strasbourg, 67412, Illkirch Cedex, France. akid.hajer@gmail.com.
- ICube, University of Strasbourg, 67412, Illkirch Cedex, France.
- REGIM-Lab, University of Sfax, 3038, Sfax, Tunisia.
Cite
APA
Akid, H., Chennen, K., Frey, G., Thompson, J., Ben Ayed, M., & Lachiche, N. (2024). Graph-based machine learning model for weight prediction in protein–protein networks. BMC Bioinformatics. https://doi.org/10.1186/s12859-024-05973-6
Vancouver
Akid H, Chennen K, Frey G, Thompson J, Ben Ayed M, Lachiche N. Graph-based machine learning model for weight prediction in protein–protein networks. BMC Bioinformatics. 2024. doi:10.1186/s12859-024-05973-6
BibTeX
@article{Akid2024,
author = {Akid, Hajer and Chennen, Kirsley and Frey, Gabriel and Thompson, Julie and Ben Ayed, Mounir and Lachiche, Nicolas},
title = {Graph-based machine learning model for weight prediction in protein–protein networks},
journal = {BMC Bioinformatics},
year = {2024},
doi = {10.1186/s12859-024-05973-6}
}
EUVIMED