MultiNNProm: A multi-classifier system for finding genes

Romesh Ranawana, Vasile Palade

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

The computational identification of genes in DNA sequences has become an issue of crucial importance due to the large number of DNA molecules being currently sequenced. We present a novel neural network based multi-classifier system, MultiNNProm, for the identification of promoter regions in E. Coli1 DNA sequences. The DNA sequences were encoded using four different encoding methods and were used to train four different neural networks. The classification results of these neural networks were then aggregated using a variation of the LOP method. The aggregating weights used within the modified LOP aggregating algorithm were obtained through a genetic algorithm. We show that the use of different neural networks, trained on the same set of data, could provide slightly varying results if the data were differently encoded. We also show that the combination of more neural classifiers provides us with better accuracy than the individual networks.

Original languageEnglish
Title of host publicationApplied Soft Computing Technologies: The Challenge of Complexity
EditorsAjith Abraham, Bernard de Baets, Mario Koppen, Bertram Nickolay
PublisherSpringer Verlag
Pages451-463
Number of pages13
Volume34
ISBN (Print)3540316493, 9783540316497
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event9th Online World Conference on Soft Computing in Industrial Applications (WSC9) -
Duration: 20 Sep 20048 Oct 2004
Conference number: 9

Publication series

NameAdvances in Soft Computing
Volume34
ISSN (Print)16153871
ISSN (Electronic)18600794

Conference

Conference9th Online World Conference on Soft Computing in Industrial Applications (WSC9)
Period20/09/048/10/04

Fingerprint

DNA sequences
Classifiers
Genes
Neural networks
DNA
Genetic algorithms
Molecules

Bibliographical note

This paper is not available in Pure.

ASJC Scopus subject areas

  • Computational Mechanics
  • Computer Science Applications
  • Computer Science (miscellaneous)

Cite this

Ranawana, R., & Palade, V. (2006). MultiNNProm: A multi-classifier system for finding genes. In A. Abraham, B. de Baets, M. Koppen, & B. Nickolay (Eds.), Applied Soft Computing Technologies: The Challenge of Complexity (Vol. 34, pp. 451-463). (Advances in Soft Computing; Vol. 34). Springer Verlag. https://doi.org/10.1007/3-540-31662-0_35

MultiNNProm : A multi-classifier system for finding genes. / Ranawana, Romesh; Palade, Vasile.

Applied Soft Computing Technologies: The Challenge of Complexity. ed. / Ajith Abraham; Bernard de Baets; Mario Koppen; Bertram Nickolay. Vol. 34 Springer Verlag, 2006. p. 451-463 (Advances in Soft Computing; Vol. 34).

Research output: Chapter in Book/Report/Conference proceedingChapter

Ranawana, R & Palade, V 2006, MultiNNProm: A multi-classifier system for finding genes. in A Abraham, B de Baets, M Koppen & B Nickolay (eds), Applied Soft Computing Technologies: The Challenge of Complexity. vol. 34, Advances in Soft Computing, vol. 34, Springer Verlag, pp. 451-463, 9th Online World Conference on Soft Computing in Industrial Applications (WSC9), 20/09/04. https://doi.org/10.1007/3-540-31662-0_35
Ranawana R, Palade V. MultiNNProm: A multi-classifier system for finding genes. In Abraham A, de Baets B, Koppen M, Nickolay B, editors, Applied Soft Computing Technologies: The Challenge of Complexity. Vol. 34. Springer Verlag. 2006. p. 451-463. (Advances in Soft Computing). https://doi.org/10.1007/3-540-31662-0_35
Ranawana, Romesh ; Palade, Vasile. / MultiNNProm : A multi-classifier system for finding genes. Applied Soft Computing Technologies: The Challenge of Complexity. editor / Ajith Abraham ; Bernard de Baets ; Mario Koppen ; Bertram Nickolay. Vol. 34 Springer Verlag, 2006. pp. 451-463 (Advances in Soft Computing).
@inbook{fffcb52b99ce4f43ae878e9e0bae97f5,
title = "MultiNNProm: A multi-classifier system for finding genes",
abstract = "The computational identification of genes in DNA sequences has become an issue of crucial importance due to the large number of DNA molecules being currently sequenced. We present a novel neural network based multi-classifier system, MultiNNProm, for the identification of promoter regions in E. Coli1 DNA sequences. The DNA sequences were encoded using four different encoding methods and were used to train four different neural networks. The classification results of these neural networks were then aggregated using a variation of the LOP method. The aggregating weights used within the modified LOP aggregating algorithm were obtained through a genetic algorithm. We show that the use of different neural networks, trained on the same set of data, could provide slightly varying results if the data were differently encoded. We also show that the combination of more neural classifiers provides us with better accuracy than the individual networks.",
author = "Romesh Ranawana and Vasile Palade",
note = "This paper is not available in Pure.",
year = "2006",
doi = "10.1007/3-540-31662-0_35",
language = "English",
isbn = "3540316493",
volume = "34",
series = "Advances in Soft Computing",
publisher = "Springer Verlag",
pages = "451--463",
editor = "Ajith Abraham and {de Baets}, Bernard and Mario Koppen and Bertram Nickolay",
booktitle = "Applied Soft Computing Technologies: The Challenge of Complexity",
address = "Austria",

}

TY - CHAP

T1 - MultiNNProm

T2 - A multi-classifier system for finding genes

AU - Ranawana, Romesh

AU - Palade, Vasile

N1 - This paper is not available in Pure.

PY - 2006

Y1 - 2006

N2 - The computational identification of genes in DNA sequences has become an issue of crucial importance due to the large number of DNA molecules being currently sequenced. We present a novel neural network based multi-classifier system, MultiNNProm, for the identification of promoter regions in E. Coli1 DNA sequences. The DNA sequences were encoded using four different encoding methods and were used to train four different neural networks. The classification results of these neural networks were then aggregated using a variation of the LOP method. The aggregating weights used within the modified LOP aggregating algorithm were obtained through a genetic algorithm. We show that the use of different neural networks, trained on the same set of data, could provide slightly varying results if the data were differently encoded. We also show that the combination of more neural classifiers provides us with better accuracy than the individual networks.

AB - The computational identification of genes in DNA sequences has become an issue of crucial importance due to the large number of DNA molecules being currently sequenced. We present a novel neural network based multi-classifier system, MultiNNProm, for the identification of promoter regions in E. Coli1 DNA sequences. The DNA sequences were encoded using four different encoding methods and were used to train four different neural networks. The classification results of these neural networks were then aggregated using a variation of the LOP method. The aggregating weights used within the modified LOP aggregating algorithm were obtained through a genetic algorithm. We show that the use of different neural networks, trained on the same set of data, could provide slightly varying results if the data were differently encoded. We also show that the combination of more neural classifiers provides us with better accuracy than the individual networks.

UR - http://www.scopus.com/inward/record.url?scp=33845411641&partnerID=8YFLogxK

U2 - 10.1007/3-540-31662-0_35

DO - 10.1007/3-540-31662-0_35

M3 - Chapter

SN - 3540316493

SN - 9783540316497

VL - 34

T3 - Advances in Soft Computing

SP - 451

EP - 463

BT - Applied Soft Computing Technologies: The Challenge of Complexity

A2 - Abraham, Ajith

A2 - de Baets, Bernard

A2 - Koppen, Mario

A2 - Nickolay, Bertram

PB - Springer Verlag

ER -