Graph-based machine learning model for weight prediction in protein-protein networks.

Publisher: BioMed Central Country of Publication: England NLM ID: 100965194 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2105 (Electronic) Linking ISSN: 14712105 NLM ISO Abbreviation: BMC Bioinformatics Subsets: MEDLINE

Original Publication: [London] : BioMed Central, 2000-

Machine Learning* ; Protein Interaction Mapping*/methods ; Saccharomyces cerevisiae*/metabolism; Protein Interaction Maps ; Algorithms ; Databases, Protein ; Saccharomyces cerevisiae Proteins/metabolism ; Computational Biology/methods

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.
(© 2024. The Author(s).)

Comput Struct Biotechnol J. 2022 Sep 19;20:5316-5341. (PMID: 36212542)
Sci Rep. 2020 Nov 5;10(1):19171. (PMID: 33154416)
BMC Bioinformatics. 2020 Dec 16;21(Suppl 16):537. (PMID: 33323120)
Nucleic Acids Res. 2005 Jan 1;33(Database issue):D433-7. (PMID: 15608232)
Brief Bioinform. 2021 Mar 22;22(2):1515-1530. (PMID: 33169146)
Proteomics. 2023 Nov;23(21-22):e2200292. (PMID: 37401192)
Nucleic Acids Res. 2023 Jan 6;51(D1):D638-D646. (PMID: 36370105)
BMC Bioinformatics. 2020 Jul 21;21(1):323. (PMID: 32693790)
Nucleic Acids Res. 2019 Jan 8;47(D1):D529-D541. (PMID: 30476227)
BMC Bioinformatics. 2017 May 12;18(1):257. (PMID: 28499419)
Nat Commun. 2019 Mar 18;10(1):1240. (PMID: 30886144)
EMBO J. 2003 Jul 15;22(14):3486-92. (PMID: 12853464)
Sci Rep. 2018 Nov 19;8(1):17014. (PMID: 30451945)
BMC Bioinformatics. 2017 May 25;18(1):277. (PMID: 28545462)
Cell. 2014 Nov 20;159(5):1212-1226. (PMID: 25416956)
Nat Commun. 2021 Jun 11;12(1):3564. (PMID: 34117231)
Eur J Cell Biol. 2024 Jun;103(2):151393. (PMID: 38306772)
Sci Rep. 2016 Dec 01;6:38208. (PMID: 27905526)
J Biosci. 2019 Sep;44(4):. (PMID: 31502581)
J Chem Inf Model. 2017 Jun 26;57(6):1499-1510. (PMID: 28514151)
Nucleic Acids Res. 2021 Jan 8;49(D1):D605-D612. (PMID: 33237311)
Proc Natl Acad Sci U S A. 2007 Mar 13;104(11):4337-41. (PMID: 17360525)
Chem Rev. 2016 Apr 27;116(8):4884-909. (PMID: 27074302)
Proteomics. 2007 Aug;7(16):2833-42. (PMID: 17640003)
J Proteomics. 2018 Jan 16;171:127-140. (PMID: 28526529)
Sci Rep. 2022 May 19;12(1):8360. (PMID: 35589837)
Bioinformatics. 2018 Sep 1;34(17):i802-i810. (PMID: 30423091)
IEEE/ACM Trans Comput Biol Bioinform. 2023 Sep-Oct;20(5):3182-3194. (PMID: 37155405)
Proc Natl Acad Sci U S A. 2008 May 13;105(19):6959-64. (PMID: 18474861)
Brief Bioinform. 2023 Mar 19;24(2):. (PMID: 36880207)
Comput Struct Biotechnol J. 2021;19:2246-2255. (PMID: 33936565)
Proteomics. 2012 May;12(10):1478-98. (PMID: 22711592)
Proteins. 2017 Jun;85(6):1159-1170. (PMID: 28263438)
PLoS One. 2015 May 06;10(5):e0125811. (PMID: 25946106)
Nucleic Acids Res. 2008 May;36(9):3025-30. (PMID: 18390576)
Phys Rev E Stat Nonlin Soft Matter Phys. 2001 Aug;64(2 Pt 2):025102. (PMID: 11497639)

Keywords: Link prediction; Machine learning; Protein–protein interactions; Weighted graphs

0 (Saccharomyces cerevisiae Proteins)

Date Created: 20241107 Date Completed: 20241108 Latest Revision: 20241116

20250114

PMC11546293

10.1186/s12859-024-05973-6

39511478