Characterization of essential proteins based on network topology in proteins interaction networks

Sakhinah Abu Bakar, Javid Taheri, Albert Y. Zomaya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The identification of essential proteins is theoretically and practically important as (1) it is essential to understand the minimal surviving requirements for cellular lives, and (2) it provides fundamental for development of drug. As conducting experimental studies to identify essential proteins are both time and resource consuming, here we present a computational approach in predicting them based on network topology properties from protein-protein interaction networks of Saccharomyces cerevisiae. The proposed method, namely EP3NN (Essential Proteins Prediction using Probabilistic Neural Network) employed a machine learning algorithm called Probabilistic Neural Network as a classifier to identify essential proteins of the organism of interest; it uses degree centrality, closeness centrality, local assortativity and local clustering coefficient of each protein in the network for such predictions. Results show that EP3NN managed to successfully predict essential proteins with an accuracy of 95% for our studied organism. Results also show that most of the essential proteins are close to other proteins, have assortativity behavior and form clusters/sub-graph in the network.

Original languageEnglish
Title of host publicationAIP Conference Proceedings
PublisherAmerican Institute of Physics Inc.
Pages36-42
Number of pages7
Volume1602
ISBN (Print)9780735412361
DOIs
Publication statusPublished - 2014
Event3rd International Conference on Mathematical Sciences, ICMS 2013 - Kuala Lumpur
Duration: 17 Dec 201319 Dec 2013

Other

Other3rd International Conference on Mathematical Sciences, ICMS 2013
CityKuala Lumpur
Period17/12/1319/12/13

Fingerprint

topology
proteins
interactions
organisms
saccharomyces
machine learning
classifiers
predictions
resources
drugs
conduction
requirements
coefficients

Keywords

  • Essential proteins
  • Machine learning algorithm
  • Neural networks
  • Protein interaction networks

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Abu Bakar, S., Taheri, J., & Zomaya, A. Y. (2014). Characterization of essential proteins based on network topology in proteins interaction networks. In AIP Conference Proceedings (Vol. 1602, pp. 36-42). American Institute of Physics Inc.. https://doi.org/10.1063/1.4882463

Characterization of essential proteins based on network topology in proteins interaction networks. / Abu Bakar, Sakhinah; Taheri, Javid; Zomaya, Albert Y.

AIP Conference Proceedings. Vol. 1602 American Institute of Physics Inc., 2014. p. 36-42.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abu Bakar, S, Taheri, J & Zomaya, AY 2014, Characterization of essential proteins based on network topology in proteins interaction networks. in AIP Conference Proceedings. vol. 1602, American Institute of Physics Inc., pp. 36-42, 3rd International Conference on Mathematical Sciences, ICMS 2013, Kuala Lumpur, 17/12/13. https://doi.org/10.1063/1.4882463
Abu Bakar S, Taheri J, Zomaya AY. Characterization of essential proteins based on network topology in proteins interaction networks. In AIP Conference Proceedings. Vol. 1602. American Institute of Physics Inc. 2014. p. 36-42 https://doi.org/10.1063/1.4882463
Abu Bakar, Sakhinah ; Taheri, Javid ; Zomaya, Albert Y. / Characterization of essential proteins based on network topology in proteins interaction networks. AIP Conference Proceedings. Vol. 1602 American Institute of Physics Inc., 2014. pp. 36-42
@inproceedings{1777a855ee114d96a0a693534828d4b0,
title = "Characterization of essential proteins based on network topology in proteins interaction networks",
abstract = "The identification of essential proteins is theoretically and practically important as (1) it is essential to understand the minimal surviving requirements for cellular lives, and (2) it provides fundamental for development of drug. As conducting experimental studies to identify essential proteins are both time and resource consuming, here we present a computational approach in predicting them based on network topology properties from protein-protein interaction networks of Saccharomyces cerevisiae. The proposed method, namely EP3NN (Essential Proteins Prediction using Probabilistic Neural Network) employed a machine learning algorithm called Probabilistic Neural Network as a classifier to identify essential proteins of the organism of interest; it uses degree centrality, closeness centrality, local assortativity and local clustering coefficient of each protein in the network for such predictions. Results show that EP3NN managed to successfully predict essential proteins with an accuracy of 95{\%} for our studied organism. Results also show that most of the essential proteins are close to other proteins, have assortativity behavior and form clusters/sub-graph in the network.",
keywords = "Essential proteins, Machine learning algorithm, Neural networks, Protein interaction networks",
author = "{Abu Bakar}, Sakhinah and Javid Taheri and Zomaya, {Albert Y.}",
year = "2014",
doi = "10.1063/1.4882463",
language = "English",
isbn = "9780735412361",
volume = "1602",
pages = "36--42",
booktitle = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",

}

TY - GEN

T1 - Characterization of essential proteins based on network topology in proteins interaction networks

AU - Abu Bakar, Sakhinah

AU - Taheri, Javid

AU - Zomaya, Albert Y.

PY - 2014

Y1 - 2014

N2 - The identification of essential proteins is theoretically and practically important as (1) it is essential to understand the minimal surviving requirements for cellular lives, and (2) it provides fundamental for development of drug. As conducting experimental studies to identify essential proteins are both time and resource consuming, here we present a computational approach in predicting them based on network topology properties from protein-protein interaction networks of Saccharomyces cerevisiae. The proposed method, namely EP3NN (Essential Proteins Prediction using Probabilistic Neural Network) employed a machine learning algorithm called Probabilistic Neural Network as a classifier to identify essential proteins of the organism of interest; it uses degree centrality, closeness centrality, local assortativity and local clustering coefficient of each protein in the network for such predictions. Results show that EP3NN managed to successfully predict essential proteins with an accuracy of 95% for our studied organism. Results also show that most of the essential proteins are close to other proteins, have assortativity behavior and form clusters/sub-graph in the network.

AB - The identification of essential proteins is theoretically and practically important as (1) it is essential to understand the minimal surviving requirements for cellular lives, and (2) it provides fundamental for development of drug. As conducting experimental studies to identify essential proteins are both time and resource consuming, here we present a computational approach in predicting them based on network topology properties from protein-protein interaction networks of Saccharomyces cerevisiae. The proposed method, namely EP3NN (Essential Proteins Prediction using Probabilistic Neural Network) employed a machine learning algorithm called Probabilistic Neural Network as a classifier to identify essential proteins of the organism of interest; it uses degree centrality, closeness centrality, local assortativity and local clustering coefficient of each protein in the network for such predictions. Results show that EP3NN managed to successfully predict essential proteins with an accuracy of 95% for our studied organism. Results also show that most of the essential proteins are close to other proteins, have assortativity behavior and form clusters/sub-graph in the network.

KW - Essential proteins

KW - Machine learning algorithm

KW - Neural networks

KW - Protein interaction networks

UR - http://www.scopus.com/inward/record.url?scp=84904116035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904116035&partnerID=8YFLogxK

U2 - 10.1063/1.4882463

DO - 10.1063/1.4882463

M3 - Conference contribution

AN - SCOPUS:84904116035

SN - 9780735412361

VL - 1602

SP - 36

EP - 42

BT - AIP Conference Proceedings

PB - American Institute of Physics Inc.

ER -