An immune network approach to learning qualitative models of biological pathways

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

1 Citation (Scopus)
36 Downloads (Pure)

Abstract

In this paper we continue the research on learning qualitative differential equation (QDE) models of biological pathways building on previous work. In particular, we adapt opt-AiNet, an immune-inspired network approach, to effectively search the qualitative model space. To improve the performance of opt-AiNet on the discrete search space, the hypermutation operator has been modified, and the affinity between two antibodies has been redefined. In addition, to accelerate the model verification process, we developed a more efficient Waltz-like inverse model checking algorithm. Finally, a Bayesian scoring function is incorporated into the fitness evaluation to better guide the search. Experimental results on learning the detoxification pathway of Methylglyoxal with various hypothesised hidden species validate the proposed approach, and indicate that our opt-AiNet based approach outperforms the previous CLONALG based approach on qualitative pathway identification.
Original languageEnglish
Title of host publication2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014)
PublisherIEEE Press
Pages1030-1037
Number of pages8
ISBN (Print)978-1-4799-6626-4
DOIs
Publication statusPublished - 2014

Fingerprint

Detoxification
Model checking
Antibodies
Differential equations

Cite this

Pang, W., & Coghill, G. M. (2014). An immune network approach to learning qualitative models of biological pathways. In 2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014) (pp. 1030-1037). IEEE Press. https://doi.org/10.1109/CEC.2014.6900393

An immune network approach to learning qualitative models of biological pathways. / Pang, Wei; Coghill, George M.

2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014). IEEE Press, 2014. p. 1030-1037.

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

Pang, W & Coghill, GM 2014, An immune network approach to learning qualitative models of biological pathways. in 2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014). IEEE Press, pp. 1030-1037. https://doi.org/10.1109/CEC.2014.6900393
Pang W, Coghill GM. An immune network approach to learning qualitative models of biological pathways. In 2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014). IEEE Press. 2014. p. 1030-1037 https://doi.org/10.1109/CEC.2014.6900393
Pang, Wei ; Coghill, George M. / An immune network approach to learning qualitative models of biological pathways. 2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014). IEEE Press, 2014. pp. 1030-1037
@inproceedings{ec776c47487344d8b68065739c3af60e,
title = "An immune network approach to learning qualitative models of biological pathways",
abstract = "In this paper we continue the research on learning qualitative differential equation (QDE) models of biological pathways building on previous work. In particular, we adapt opt-AiNet, an immune-inspired network approach, to effectively search the qualitative model space. To improve the performance of opt-AiNet on the discrete search space, the hypermutation operator has been modified, and the affinity between two antibodies has been redefined. In addition, to accelerate the model verification process, we developed a more efficient Waltz-like inverse model checking algorithm. Finally, a Bayesian scoring function is incorporated into the fitness evaluation to better guide the search. Experimental results on learning the detoxification pathway of Methylglyoxal with various hypothesised hidden species validate the proposed approach, and indicate that our opt-AiNet based approach outperforms the previous CLONALG based approach on qualitative pathway identification.",
author = "Wei Pang and Coghill, {George M}",
note = "ACKNOWLEDGMENT GMC is supported by the CRISP project (Combinatorial Responses In Stress Pathways) funded by the BBSRC (BB/F00513X/1) under the Systems Approaches to Biological Research (SABR) Initiative. WP and GMC are also supported by the partnership fund from dot.rural, RCUK Digital Economy research.",
year = "2014",
doi = "10.1109/CEC.2014.6900393",
language = "English",
isbn = "978-1-4799-6626-4",
pages = "1030--1037",
booktitle = "2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014)",
publisher = "IEEE Press",

}

TY - GEN

T1 - An immune network approach to learning qualitative models of biological pathways

AU - Pang, Wei

AU - Coghill, George M

N1 - ACKNOWLEDGMENT GMC is supported by the CRISP project (Combinatorial Responses In Stress Pathways) funded by the BBSRC (BB/F00513X/1) under the Systems Approaches to Biological Research (SABR) Initiative. WP and GMC are also supported by the partnership fund from dot.rural, RCUK Digital Economy research.

PY - 2014

Y1 - 2014

N2 - In this paper we continue the research on learning qualitative differential equation (QDE) models of biological pathways building on previous work. In particular, we adapt opt-AiNet, an immune-inspired network approach, to effectively search the qualitative model space. To improve the performance of opt-AiNet on the discrete search space, the hypermutation operator has been modified, and the affinity between two antibodies has been redefined. In addition, to accelerate the model verification process, we developed a more efficient Waltz-like inverse model checking algorithm. Finally, a Bayesian scoring function is incorporated into the fitness evaluation to better guide the search. Experimental results on learning the detoxification pathway of Methylglyoxal with various hypothesised hidden species validate the proposed approach, and indicate that our opt-AiNet based approach outperforms the previous CLONALG based approach on qualitative pathway identification.

AB - In this paper we continue the research on learning qualitative differential equation (QDE) models of biological pathways building on previous work. In particular, we adapt opt-AiNet, an immune-inspired network approach, to effectively search the qualitative model space. To improve the performance of opt-AiNet on the discrete search space, the hypermutation operator has been modified, and the affinity between two antibodies has been redefined. In addition, to accelerate the model verification process, we developed a more efficient Waltz-like inverse model checking algorithm. Finally, a Bayesian scoring function is incorporated into the fitness evaluation to better guide the search. Experimental results on learning the detoxification pathway of Methylglyoxal with various hypothesised hidden species validate the proposed approach, and indicate that our opt-AiNet based approach outperforms the previous CLONALG based approach on qualitative pathway identification.

U2 - 10.1109/CEC.2014.6900393

DO - 10.1109/CEC.2014.6900393

M3 - Conference contribution

SN - 978-1-4799-6626-4

SP - 1030

EP - 1037

BT - 2014 IEEE Congress on Evolutionary Computation (IEEE CEC 2014)

PB - IEEE Press

ER -