Identification of Protein Complexes from PPI Network Using Ensembling Approach

DOI

10.2991/978-94-6239-628-9_10How to use a DOI?

Keywords

Ensemble learning; base algorithms; protein complex; topology; functional enrichment

Abstract

The study of Protein Protein Interaction (PPI) network and particularly the group of proteins (protein complexes) is gaining wide importance. This is due to the inherent ability of protein complexes to regulate the different cellular and metabolic processes in the living body. Literature is flooded with several protein complex finding algorithms. These algorithms may be either network topology dependent or use a fusion of both network topology and functional information to detect the complexes. A recent approach is the use of ensemble learning which takes the advantage of multiple base clustering algorithms in order to derive quality complexes. Despite the use of multiple base algorithms, another challenge that is being faced is the use of ill quality results in the initial phase itself. In this paper, we have proposed an ensemble complex finding method known as EnCF which uses a ranking based scheme at the base algorithms. The intermediate results are refined based on these scores to get high quality complexes. The most crucial step for obtaining good quality complexes is tackled using the number of common pathways shared between the nodes in any complex. This attribute is used as the final parameter to generate functionally relevant complexes. The performance of EnCF is evaluated based on Sensitivity, Positive Predictive Value and Accuracy on the human PPI dataset.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pooja A. Sharma
AU  - Anuj Pandey
PY  - 2026
DA  - 2026/03/31
TI  - Identification of Protein Complexes from PPI Network Using Ensembling Approach
BT  - Proceedings of the International Conference on Recent Trends in Intelligent Computing, Manufacturing, and Electronics (rTIME 2025)
PB  - Atlantis Press
SP  - 97
EP  - 106
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-628-9_10
DO  - 10.2991/978-94-6239-628-9_10
ID  - Sharma2026
ER  -