An evolutionary restricted neighborhood search clustering approach for PPI networks

Simona Ester Rombo, Clara Pizzuti

Risultato della ricerca: Article

3 Citazioni (Scopus)

Abstract

Protein-protein interaction networks have been broadly studied in the last few years, in order to understand the behavior of proteins inside the cell. Proteins interacting with each other often share common biological functions or they participate in the same biological process. Thus, discovering protein complexes made of a group of proteins strictly related can be useful to predict protein functions. Clustering techniques have been widely employed to detect significant biological complexes. In this paper, we integrate one of the most popular network clustering techniques, namely the Restricted Neighborhood Search Clustering (RNSC), with evolutionary computation. The two cost functions introduced by RNSC, besides a new one that combines them, are used by a Genetic Algorithm as fitness functions to be optimized. Experimental evaluations performed on two different groups of interactions of the budding yeast Saccharomyces cerevisiae show that the clusters obtained by the genetic approach are a larger number of those found by RNSC, though this method predicts more true complexes.
Lingua originaleEnglish
pagine (da-a)53-61
Numero di pagine9
RivistaNeurocomputing
Volume145
Stato di pubblicazionePublished - 2014

Fingerprint

Cluster Analysis
Proteins
Yeast
Protein Interaction Maps
Biological Phenomena
Saccharomycetales
Saccharomyces cerevisiae
Evolutionary algorithms
Cost functions
Genetic algorithms
Costs and Cost Analysis

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Artificial Intelligence
  • Cognitive Neuroscience

Cita questo

An evolutionary restricted neighborhood search clustering approach for PPI networks. / Rombo, Simona Ester; Pizzuti, Clara.

In: Neurocomputing, Vol. 145, 2014, pag. 53-61.

Risultato della ricerca: Article

@article{b22f5b51274f44f799815b57f5727722,
title = "An evolutionary restricted neighborhood search clustering approach for PPI networks",
abstract = "Protein-protein interaction networks have been broadly studied in the last few years, in order to understand the behavior of proteins inside the cell. Proteins interacting with each other often share common biological functions or they participate in the same biological process. Thus, discovering protein complexes made of a group of proteins strictly related can be useful to predict protein functions. Clustering techniques have been widely employed to detect significant biological complexes. In this paper, we integrate one of the most popular network clustering techniques, namely the Restricted Neighborhood Search Clustering (RNSC), with evolutionary computation. The two cost functions introduced by RNSC, besides a new one that combines them, are used by a Genetic Algorithm as fitness functions to be optimized. Experimental evaluations performed on two different groups of interactions of the budding yeast Saccharomyces cerevisiae show that the clusters obtained by the genetic approach are a larger number of those found by RNSC, though this method predicts more true complexes.",
author = "Rombo, {Simona Ester} and Clara Pizzuti",
year = "2014",
language = "English",
volume = "145",
pages = "53--61",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - An evolutionary restricted neighborhood search clustering approach for PPI networks

AU - Rombo, Simona Ester

AU - Pizzuti, Clara

PY - 2014

Y1 - 2014

N2 - Protein-protein interaction networks have been broadly studied in the last few years, in order to understand the behavior of proteins inside the cell. Proteins interacting with each other often share common biological functions or they participate in the same biological process. Thus, discovering protein complexes made of a group of proteins strictly related can be useful to predict protein functions. Clustering techniques have been widely employed to detect significant biological complexes. In this paper, we integrate one of the most popular network clustering techniques, namely the Restricted Neighborhood Search Clustering (RNSC), with evolutionary computation. The two cost functions introduced by RNSC, besides a new one that combines them, are used by a Genetic Algorithm as fitness functions to be optimized. Experimental evaluations performed on two different groups of interactions of the budding yeast Saccharomyces cerevisiae show that the clusters obtained by the genetic approach are a larger number of those found by RNSC, though this method predicts more true complexes.

AB - Protein-protein interaction networks have been broadly studied in the last few years, in order to understand the behavior of proteins inside the cell. Proteins interacting with each other often share common biological functions or they participate in the same biological process. Thus, discovering protein complexes made of a group of proteins strictly related can be useful to predict protein functions. Clustering techniques have been widely employed to detect significant biological complexes. In this paper, we integrate one of the most popular network clustering techniques, namely the Restricted Neighborhood Search Clustering (RNSC), with evolutionary computation. The two cost functions introduced by RNSC, besides a new one that combines them, are used by a Genetic Algorithm as fitness functions to be optimized. Experimental evaluations performed on two different groups of interactions of the budding yeast Saccharomyces cerevisiae show that the clusters obtained by the genetic approach are a larger number of those found by RNSC, though this method predicts more true complexes.

UR - http://hdl.handle.net/10447/102131

M3 - Article

VL - 145

SP - 53

EP - 61

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -