An immune-inspired approach to qualitative system identification of biological pathways

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this paper, a special-purpose qualitative model learning (QML) system using an immune-inspired algorithm is proposed to qualitatively reconstruct biological pathways. We choose a real-world application, the detoxification pathway of Methylglyoxal (MG), as a case study. First a converter is implemented to convert possible pathways to qualitative models. Then a general learning strategy is presented. To improve the scalability of the proposed QML system and make it adapt to future more complicated pathways, a modified clonal selection algorithm (CLONALG) is employed as the search strategy. The perfor- mance of this immune-inspired approach is compared with those of exhaustive search and two backtracking algorithms. The experimental results indicate that this immune-inspired approach can significantly improve the search efficiency when dealing with some complicated pathways with large-scale search spaces.
Original languageEnglish
Pages (from-to)189-207
Number of pages19
JournalNatural Computing
Volume10
Issue number1
Early online date6 Aug 2010
DOIs
Publication statusPublished - Mar 2011

Fingerprint

Identification (control systems)
Learning systems
Detoxification
Scalability

Keywords

  • clonal selection algorithm
  • immune-inspired algorithm
  • pathway reconstruction
  • qualitative differential equation
  • qualitative model learning
  • qualitative reasoning
  • qualitative simulation

Cite this

An immune-inspired approach to qualitative system identification of biological pathways. / Pang, Wei; Coghill, George M.

In: Natural Computing, Vol. 10, No. 1, 03.2011, p. 189-207.

Research output: Contribution to journalArticle

@article{31e8579716b8482890694ad71ab647cd,
title = "An immune-inspired approach to qualitative system identification of biological pathways",
abstract = "In this paper, a special-purpose qualitative model learning (QML) system using an immune-inspired algorithm is proposed to qualitatively reconstruct biological pathways. We choose a real-world application, the detoxification pathway of Methylglyoxal (MG), as a case study. First a converter is implemented to convert possible pathways to qualitative models. Then a general learning strategy is presented. To improve the scalability of the proposed QML system and make it adapt to future more complicated pathways, a modified clonal selection algorithm (CLONALG) is employed as the search strategy. The perfor- mance of this immune-inspired approach is compared with those of exhaustive search and two backtracking algorithms. The experimental results indicate that this immune-inspired approach can significantly improve the search efficiency when dealing with some complicated pathways with large-scale search spaces.",
keywords = "clonal selection algorithm, immune-inspired algorithm, pathway reconstruction, qualitative differential equation, qualitative model learning, qualitative reasoning, qualitative simulation",
author = "Wei Pang and Coghill, {George M.}",
note = "A paid open access option is available for this journal. Authors own final version only can be archived Publisher's version/PDF cannot be used On author's website immediately On any open access repository after 12 months from publication Published source must be acknowledged Must link to publisher version Set phrase to accompany link to published version (The original publication is available at www.springerlink.com) Articles in some journals can be made Open Access on payment of additional charge",
year = "2011",
month = "3",
doi = "10.1007/s11047-010-9212-2",
language = "English",
volume = "10",
pages = "189--207",
journal = "Natural Computing",
issn = "1567-7818",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - An immune-inspired approach to qualitative system identification of biological pathways

AU - Pang, Wei

AU - Coghill, George M.

N1 - A paid open access option is available for this journal. Authors own final version only can be archived Publisher's version/PDF cannot be used On author's website immediately On any open access repository after 12 months from publication Published source must be acknowledged Must link to publisher version Set phrase to accompany link to published version (The original publication is available at www.springerlink.com) Articles in some journals can be made Open Access on payment of additional charge

PY - 2011/3

Y1 - 2011/3

N2 - In this paper, a special-purpose qualitative model learning (QML) system using an immune-inspired algorithm is proposed to qualitatively reconstruct biological pathways. We choose a real-world application, the detoxification pathway of Methylglyoxal (MG), as a case study. First a converter is implemented to convert possible pathways to qualitative models. Then a general learning strategy is presented. To improve the scalability of the proposed QML system and make it adapt to future more complicated pathways, a modified clonal selection algorithm (CLONALG) is employed as the search strategy. The perfor- mance of this immune-inspired approach is compared with those of exhaustive search and two backtracking algorithms. The experimental results indicate that this immune-inspired approach can significantly improve the search efficiency when dealing with some complicated pathways with large-scale search spaces.

AB - In this paper, a special-purpose qualitative model learning (QML) system using an immune-inspired algorithm is proposed to qualitatively reconstruct biological pathways. We choose a real-world application, the detoxification pathway of Methylglyoxal (MG), as a case study. First a converter is implemented to convert possible pathways to qualitative models. Then a general learning strategy is presented. To improve the scalability of the proposed QML system and make it adapt to future more complicated pathways, a modified clonal selection algorithm (CLONALG) is employed as the search strategy. The perfor- mance of this immune-inspired approach is compared with those of exhaustive search and two backtracking algorithms. The experimental results indicate that this immune-inspired approach can significantly improve the search efficiency when dealing with some complicated pathways with large-scale search spaces.

KW - clonal selection algorithm

KW - immune-inspired algorithm

KW - pathway reconstruction

KW - qualitative differential equation

KW - qualitative model learning

KW - qualitative reasoning

KW - qualitative simulation

U2 - 10.1007/s11047-010-9212-2

DO - 10.1007/s11047-010-9212-2

M3 - Article

VL - 10

SP - 189

EP - 207

JO - Natural Computing

JF - Natural Computing

SN - 1567-7818

IS - 1

ER -