FIS-PNN: A hybrid computational method for protein-protein interaction prediction

Sakhinah Abu Bakar, Javid Taheri, Albert Y. Zomaya

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

Abstract

The study of protein-protein interactions (PPI) is an active area of research in biology as it mediates most of the biological functions in any organism. Although, there are no concrete properties in predicting PPI, extensive wet-lab experiments suggest (with a high probability) that interacting proteins in the fine level share similar functions, cellular roles and sub-cellular locations. In this study, we developed a technique to predict PPI based on their secondary structures, co-localization, and function annotation. We proposed our approach, namely FIS-PNN, to predict the interacting proteins in yeast using hybrid machine learning algorithms. FIS-PNN has been trained and tested using 1029 proteins with 2965 known positive interactions; it could successfully predict PPI with 96% of accuracy - a level that is significantly greater than all other existing sequence-based prediction methods.

Original languageEnglish
Title of host publicationProceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA
Pages196-203
Number of pages8
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event9th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2011 - Sharm El-Sheikh
Duration: 27 Dec 201130 Dec 2011

Other

Other9th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2011
CitySharm El-Sheikh
Period27/12/1130/12/11

Fingerprint

Computational methods
Proteins
Yeast
Learning algorithms
Learning systems
Concretes

Keywords

  • machine learning
  • protein-protein interaction
  • secondary structure

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Signal Processing
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Abu Bakar, S., Taheri, J., & Zomaya, A. Y. (2011). FIS-PNN: A hybrid computational method for protein-protein interaction prediction. In Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA (pp. 196-203). [6126594] https://doi.org/10.1109/AICCSA.2011.6126594

FIS-PNN : A hybrid computational method for protein-protein interaction prediction. / Abu Bakar, Sakhinah; Taheri, Javid; Zomaya, Albert Y.

Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA. 2011. p. 196-203 6126594.

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

Abu Bakar, S, Taheri, J & Zomaya, AY 2011, FIS-PNN: A hybrid computational method for protein-protein interaction prediction. in Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA., 6126594, pp. 196-203, 9th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2011, Sharm El-Sheikh, 27/12/11. https://doi.org/10.1109/AICCSA.2011.6126594
Abu Bakar S, Taheri J, Zomaya AY. FIS-PNN: A hybrid computational method for protein-protein interaction prediction. In Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA. 2011. p. 196-203. 6126594 https://doi.org/10.1109/AICCSA.2011.6126594
Abu Bakar, Sakhinah ; Taheri, Javid ; Zomaya, Albert Y. / FIS-PNN : A hybrid computational method for protein-protein interaction prediction. Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA. 2011. pp. 196-203
@inproceedings{5007e5e63e214825b3c4689059f87bae,
title = "FIS-PNN: A hybrid computational method for protein-protein interaction prediction",
abstract = "The study of protein-protein interactions (PPI) is an active area of research in biology as it mediates most of the biological functions in any organism. Although, there are no concrete properties in predicting PPI, extensive wet-lab experiments suggest (with a high probability) that interacting proteins in the fine level share similar functions, cellular roles and sub-cellular locations. In this study, we developed a technique to predict PPI based on their secondary structures, co-localization, and function annotation. We proposed our approach, namely FIS-PNN, to predict the interacting proteins in yeast using hybrid machine learning algorithms. FIS-PNN has been trained and tested using 1029 proteins with 2965 known positive interactions; it could successfully predict PPI with 96{\%} of accuracy - a level that is significantly greater than all other existing sequence-based prediction methods.",
keywords = "machine learning, protein-protein interaction, secondary structure",
author = "{Abu Bakar}, Sakhinah and Javid Taheri and Zomaya, {Albert Y.}",
year = "2011",
doi = "10.1109/AICCSA.2011.6126594",
language = "English",
isbn = "9781457704741",
pages = "196--203",
booktitle = "Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA",

}

TY - GEN

T1 - FIS-PNN

T2 - A hybrid computational method for protein-protein interaction prediction

AU - Abu Bakar, Sakhinah

AU - Taheri, Javid

AU - Zomaya, Albert Y.

PY - 2011

Y1 - 2011

N2 - The study of protein-protein interactions (PPI) is an active area of research in biology as it mediates most of the biological functions in any organism. Although, there are no concrete properties in predicting PPI, extensive wet-lab experiments suggest (with a high probability) that interacting proteins in the fine level share similar functions, cellular roles and sub-cellular locations. In this study, we developed a technique to predict PPI based on their secondary structures, co-localization, and function annotation. We proposed our approach, namely FIS-PNN, to predict the interacting proteins in yeast using hybrid machine learning algorithms. FIS-PNN has been trained and tested using 1029 proteins with 2965 known positive interactions; it could successfully predict PPI with 96% of accuracy - a level that is significantly greater than all other existing sequence-based prediction methods.

AB - The study of protein-protein interactions (PPI) is an active area of research in biology as it mediates most of the biological functions in any organism. Although, there are no concrete properties in predicting PPI, extensive wet-lab experiments suggest (with a high probability) that interacting proteins in the fine level share similar functions, cellular roles and sub-cellular locations. In this study, we developed a technique to predict PPI based on their secondary structures, co-localization, and function annotation. We proposed our approach, namely FIS-PNN, to predict the interacting proteins in yeast using hybrid machine learning algorithms. FIS-PNN has been trained and tested using 1029 proteins with 2965 known positive interactions; it could successfully predict PPI with 96% of accuracy - a level that is significantly greater than all other existing sequence-based prediction methods.

KW - machine learning

KW - protein-protein interaction

KW - secondary structure

UR - http://www.scopus.com/inward/record.url?scp=84857769495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857769495&partnerID=8YFLogxK

U2 - 10.1109/AICCSA.2011.6126594

DO - 10.1109/AICCSA.2011.6126594

M3 - Conference contribution

AN - SCOPUS:84857769495

SN - 9781457704741

SP - 196

EP - 203

BT - Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA

ER -